active meetings type precision

* Identify action items

* Add action items to mock summary

* Add action items validator

* Remove final prefix from action items

* Make on action items callback required

* Don't mutation action items response

* Assign action items to none on error

* Use timeout constant

* Exclude action items from transcript list

.github/workflows/deploy.yml

@@ -1,90 +0,0 @@
-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"

.github/workflows/dockerhub-backend.yml

@@ -1,35 +1,31 @@
-name: Build and Push Frontend Docker Image
+name: Build and Push Backend Docker Image (Docker Hub)
 
 on:
   push:
-    branches:
+    tags:
-      - main
+      - "v*"
-    paths:
-      - 'www/**'
-      - '.github/workflows/docker-frontend.yml'
   workflow_dispatch:
 
 env:
-  REGISTRY: ghcr.io
+  REGISTRY: docker.io
-  IMAGE_NAME: ${{ github.repository }}-frontend
+  IMAGE_NAME: monadicalsas/reflector-backend
 
 jobs:
   build-and-push:
     runs-on: ubuntu-latest
     permissions:
       contents: read
-      packages: write
 
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
 
-      - name: Log in to GitHub Container Registry
+      - name: Log in to Docker Hub
         uses: docker/login-action@v3
         with:
           registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
+          username: monadicalsas
-          password: ${{ secrets.GITHUB_TOKEN }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Extract metadata
         id: meta
@@ -38,7 +34,7 @@ jobs:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           tags: |
             type=ref,event=branch
-            type=sha,prefix={{branch}}-
+            type=ref,event=tag
             type=raw,value=latest,enable={{is_default_branch}}
 
       - name: Set up Docker Buildx
@@ -47,8 +43,8 @@ jobs:
       - name: Build and push Docker image
         uses: docker/build-push-action@v5
         with:
-          context: ./www
+          context: ./server
-          file: ./www/Dockerfile
+          file: ./server/Dockerfile
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}

.github/workflows/dockerhub-frontend.yml

@@ -0,0 +1,70 @@
+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)

.gitignore

@@ -18,3 +18,4 @@ CLAUDE.local.md
 www/.env.development
 www/.env.production
 .playwright-mcp
+.secrets

.secrets.example

@@ -0,0 +1,24 @@
+# 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

CHANGELOG.md

@@ -1,5 +1,115 @@
 # Changelog
 
+## [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)
+
+
+### Features
+
+* link transcript participants ([#737](https://github.com/Monadical-SAS/reflector/issues/737)) ([9bec398](https://github.com/Monadical-SAS/reflector/commit/9bec39808fc6322612d8b87e922a6f7901fc01c1))
+* transcript restart script ([#742](https://github.com/Monadical-SAS/reflector/issues/742)) ([86d5e26](https://github.com/Monadical-SAS/reflector/commit/86d5e26224bb55a0f1cc785aeda52065bb92ee6f))
+
+## [0.19.0](https://github.com/Monadical-SAS/reflector/compare/v0.18.0...v0.19.0) (2025-11-25)
+
+
+### Features
+
+* dailyco api module ([#725](https://github.com/Monadical-SAS/reflector/issues/725)) ([4287f8b](https://github.com/Monadical-SAS/reflector/commit/4287f8b8aeee60e51db7539f4dcbda5f6e696bd8))
+* dailyco poll ([#730](https://github.com/Monadical-SAS/reflector/issues/730)) ([8e438ca](https://github.com/Monadical-SAS/reflector/commit/8e438ca285152bd48fdc42767e706fb448d3525c))
+* multitrack cli ([#735](https://github.com/Monadical-SAS/reflector/issues/735)) ([11731c9](https://github.com/Monadical-SAS/reflector/commit/11731c9d38439b04e93b1c3afbd7090bad11a11f))
+
+
+### Bug Fixes
+
+* default platform fix ([#736](https://github.com/Monadical-SAS/reflector/issues/736)) ([c442a62](https://github.com/Monadical-SAS/reflector/commit/c442a627873ca667656eeaefb63e54ab10b8d19e))
+* parakeet vad not getting the end timestamp ([#728](https://github.com/Monadical-SAS/reflector/issues/728)) ([18ed713](https://github.com/Monadical-SAS/reflector/commit/18ed7133693653ef4ddac6c659a8c14b320d1657))
+* start raw tracks recording ([#729](https://github.com/Monadical-SAS/reflector/issues/729)) ([3e47c2c](https://github.com/Monadical-SAS/reflector/commit/3e47c2c0573504858e0d2e1798b6ed31f16b4a5d))
+
+## [0.18.0](https://github.com/Monadical-SAS/reflector/compare/v0.17.0...v0.18.0) (2025-11-14)
+
+
+### Features
+
+* daily QOL: participants dictionary ([#721](https://github.com/Monadical-SAS/reflector/issues/721)) ([b20cad7](https://github.com/Monadical-SAS/reflector/commit/b20cad76e69fb6a76405af299a005f1ddcf60eae))
+
+
+### Bug Fixes
+
+* add proccessing page to file upload and reprocessing ([#650](https://github.com/Monadical-SAS/reflector/issues/650)) ([28a7258](https://github.com/Monadical-SAS/reflector/commit/28a7258e45317b78e60e6397be2bc503647eaace))
+* copy transcript ([#674](https://github.com/Monadical-SAS/reflector/issues/674)) ([a9a4f32](https://github.com/Monadical-SAS/reflector/commit/a9a4f32324f66c838e081eee42bb9502f38c1db1))
+
 ## [0.17.0](https://github.com/Monadical-SAS/reflector/compare/v0.16.0...v0.17.0) (2025-11-13)
 
 

README.md

@@ -168,6 +168,12 @@ You can manually process an audio file by calling the process tool:
 uv run python -m reflector.tools.process path/to/audio.wav
 ```
 
+## Reprocessing any transcription
+
+```bash
+uv run -m reflector.tools.process_transcript 81ec38d1-9dd7-43d2-b3f8-51f4d34a07cd --sync
+```
+
 ## Build-time env variables
 
 Next.js projects are more used to NEXT_PUBLIC_ prefixed buildtime vars. We don't have those for the reason we need to serve a ccustomizable prebuild docker container.

docker-compose.prod.yml

@@ -3,10 +3,8 @@
 
 services:
   web:
-    build:
+    image: monadicalsas/reflector-frontend:latest
-      context: ./www
+    pull_policy: always
-      dockerfile: Dockerfile
-    image: reflector-frontend:latest
     environment:
       - KV_URL=${KV_URL:-redis://redis:6379}
       - SITE_URL=${SITE_URL}

docs/transcript.md

@@ -0,0 +1,241 @@
+# 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

gpu/modal_deployments/reflector_transcriber_parakeet.py

@@ -81,9 +81,9 @@ image = (
         "cuda-python==12.8.0",
         "fastapi==0.115.12",
         "numpy<2",
-        "librosa==0.10.1",
+        "librosa==0.11.0",
         "requests",
-        "silero-vad==5.1.0",
+        "silero-vad==6.2.0",
         "torch",
     )
     .entrypoint([])  # silence chatty logs by container on start
@@ -306,6 +306,7 @@ class TranscriberParakeetFile:
         ) -> Generator[TimeSegment, None, None]:
             """Generate speech segments using VAD with start/end sample indices"""
             vad_iterator = VADIterator(self.vad_model, sampling_rate=SAMPLERATE)
+            audio_duration = len(audio_array) / float(SAMPLERATE)
             window_size = VAD_CONFIG["window_size"]
             start = None
 
@@ -332,6 +333,10 @@ class TranscriberParakeetFile:
                     yield TimeSegment(start_time, end_time)
                     start = None
 
+            if start is not None:
+                start_time = start / float(SAMPLERATE)
+                yield TimeSegment(start_time, audio_duration)
+
             vad_iterator.reset_states()
 
         def batch_speech_segments(

server/docs/video-platforms/README.md

@@ -89,7 +89,9 @@ This document explains how Reflector receives and identifies multitrack audio re
 
 ---
 
-## Daily.co (Webhook-based)
+## Daily.co
+
+**Note:** Primary discovery via polling (`poll_daily_recordings`), webhooks as backup.
 
 Daily.co uses **webhooks** to notify Reflector when recordings are ready.
 

server/migrations/versions/05f8688d6895_add_action_items.py

@@ -0,0 +1,26 @@
+"""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")

server/migrations/versions/20251217000000_add_skip_consent_to_room.py

@@ -0,0 +1,35 @@
+"""add skip_consent to room
+
+Revision ID: 20251217000000
+Revises: 05f8688d6895
+Create Date: 2025-12-17 00:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "20251217000000"
+down_revision: Union[str, None] = "05f8688d6895"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    with op.batch_alter_table("room", schema=None) as batch_op:
+        batch_op.add_column(
+            sa.Column(
+                "skip_consent",
+                sa.Boolean(),
+                nullable=False,
+                server_default=sa.text("false"),
+            )
+        )
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("room", schema=None) as batch_op:
+        batch_op.drop_column("skip_consent")

server/migrations/versions/2b92a1b03caa_add_daily_participant_session_table_.py

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

server/migrations/versions/5d6b9df9b045_make_room_platform_non_nullable_with_.py

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

server/migrations/versions/bbafedfa510c_add_user_table.py

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

server/pyproject.toml

@@ -126,6 +126,7 @@ 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
 ]
 

server/reflector/asynctask.py

@@ -1,13 +1,19 @@
 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:

server/reflector/auth/auth_jwt.py

@@ -6,8 +6,10 @@ from jose import JWTError, jwt
 from pydantic import BaseModel
 
 from reflector.db.user_api_keys import user_api_keys_controller
+from reflector.db.users import user_controller
 from reflector.logger import logger
 from reflector.settings import settings
+from reflector.utils import generate_uuid4
 
 oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token", auto_error=False)
 api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
@@ -74,9 +76,21 @@ async def _authenticate_user(
     if jwt_token:
         try:
             payload = jwtauth.verify_token(jwt_token)
-            sub = payload["sub"]
+            authentik_uid = payload["sub"]
             email = payload["email"]
-            user_infos.append(UserInfo(sub=sub, email=email))
+
+            user = await user_controller.get_by_authentik_uid(authentik_uid)
+            if not user:
+                logger.info(
+                    f"Creating new user on first login: {authentik_uid} ({email})"
+                )
+                user = await user_controller.create_or_update(
+                    id=generate_uuid4(),
+                    authentik_uid=authentik_uid,
+                    email=email,
+                )
+
+            user_infos.append(UserInfo(sub=user.id, email=email))
         except JWTError as e:
             logger.error(f"JWT error: {e}")
             raise HTTPException(status_code=401, detail="Invalid authentication")

server/reflector/dailyco_api/README.md

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

server/reflector/dailyco_api/__init__.py

@@ -0,0 +1,110 @@
+"""
+Daily.co API Module
+"""
+
+# Client
+from .client import DailyApiClient, DailyApiError
+
+# Request models
+from .requests import (
+    CreateMeetingTokenRequest,
+    CreateRoomRequest,
+    CreateWebhookRequest,
+    MeetingTokenProperties,
+    RecordingsBucketConfig,
+    RoomProperties,
+    UpdateWebhookRequest,
+)
+
+# Response models
+from .responses import (
+    FinishedRecordingResponse,
+    MeetingParticipant,
+    MeetingParticipantsResponse,
+    MeetingResponse,
+    MeetingTokenResponse,
+    RecordingResponse,
+    RecordingS3Info,
+    RoomPresenceParticipant,
+    RoomPresenceResponse,
+    RoomResponse,
+    WebhookResponse,
+)
+
+# Webhook utilities
+from .webhook_utils import (
+    extract_room_name,
+    parse_participant_joined,
+    parse_participant_left,
+    parse_recording_error,
+    parse_recording_ready,
+    parse_recording_started,
+    parse_webhook_payload,
+    verify_webhook_signature,
+)
+
+# Webhook models
+from .webhooks import (
+    DailyTrack,
+    DailyWebhookEvent,
+    DailyWebhookEventUnion,
+    ParticipantJoinedEvent,
+    ParticipantJoinedPayload,
+    ParticipantLeftEvent,
+    ParticipantLeftPayload,
+    RecordingErrorEvent,
+    RecordingErrorPayload,
+    RecordingReadyEvent,
+    RecordingReadyToDownloadPayload,
+    RecordingStartedEvent,
+    RecordingStartedPayload,
+)
+
+__all__ = [
+    # Client
+    "DailyApiClient",
+    "DailyApiError",
+    # Requests
+    "CreateRoomRequest",
+    "RoomProperties",
+    "RecordingsBucketConfig",
+    "CreateMeetingTokenRequest",
+    "MeetingTokenProperties",
+    "CreateWebhookRequest",
+    "UpdateWebhookRequest",
+    # Responses
+    "RoomResponse",
+    "RoomPresenceResponse",
+    "RoomPresenceParticipant",
+    "MeetingParticipantsResponse",
+    "MeetingParticipant",
+    "MeetingResponse",
+    "RecordingResponse",
+    "FinishedRecordingResponse",
+    "RecordingS3Info",
+    "MeetingTokenResponse",
+    "WebhookResponse",
+    # Webhooks
+    "DailyWebhookEvent",
+    "DailyWebhookEventUnion",
+    "DailyTrack",
+    "ParticipantJoinedEvent",
+    "ParticipantJoinedPayload",
+    "ParticipantLeftEvent",
+    "ParticipantLeftPayload",
+    "RecordingStartedEvent",
+    "RecordingStartedPayload",
+    "RecordingReadyEvent",
+    "RecordingReadyToDownloadPayload",
+    "RecordingErrorEvent",
+    "RecordingErrorPayload",
+    # Webhook utilities
+    "verify_webhook_signature",
+    "extract_room_name",
+    "parse_webhook_payload",
+    "parse_participant_joined",
+    "parse_participant_left",
+    "parse_recording_started",
+    "parse_recording_ready",
+    "parse_recording_error",
+]

server/reflector/dailyco_api/client.py

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

server/reflector/dailyco_api/requests.py

@@ -0,0 +1,162 @@
+"""
+Daily.co API Request Models
+
+Reference: https://docs.daily.co/reference/rest-api
+"""
+
+from typing import List, Literal
+
+from pydantic import BaseModel, Field
+
+from reflector.utils.string import NonEmptyString
+
+
+class RecordingsBucketConfig(BaseModel):
+    """
+    S3 bucket configuration for raw-tracks recordings.
+
+    Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
+    """
+
+    bucket_name: NonEmptyString = Field(description="S3 bucket name")
+    bucket_region: NonEmptyString = Field(description="AWS region (e.g., 'us-east-1')")
+    assume_role_arn: NonEmptyString = Field(
+        description="AWS IAM role ARN that Daily.co will assume to write recordings"
+    )
+    allow_api_access: bool = Field(
+        default=True,
+        description="Whether to allow API access to recording metadata",
+    )
+
+
+class RoomProperties(BaseModel):
+    """
+    Room configuration properties.
+    """
+
+    enable_recording: Literal["cloud", "local", "raw-tracks"] | None = Field(
+        default=None,
+        description="Recording mode: 'cloud' for mixed, 'local' for local recording, 'raw-tracks' for multitrack, None to disable",
+    )
+    enable_chat: bool = Field(default=True, description="Enable in-meeting chat")
+    enable_screenshare: bool = Field(default=True, description="Enable screen sharing")
+    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"
+    )
+    start_audio_off: bool = Field(
+        default=False, description="Start with audio muted for all participants"
+    )
+    exp: int | None = Field(
+        None, description="Room expiration timestamp (Unix epoch seconds)"
+    )
+    recordings_bucket: RecordingsBucketConfig | None = Field(
+        None, description="S3 bucket configuration for raw-tracks recordings"
+    )
+
+
+class CreateRoomRequest(BaseModel):
+    """
+    Request to create a new Daily.co room.
+
+    Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
+    """
+
+    name: NonEmptyString = Field(description="Room name (must be unique within domain)")
+    privacy: Literal["public", "private"] = Field(
+        default="public", description="Room privacy setting"
+    )
+    properties: RoomProperties = Field(
+        default_factory=RoomProperties, description="Room configuration properties"
+    )
+
+
+class MeetingTokenProperties(BaseModel):
+    """
+    Properties for meeting token creation.
+
+    Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
+    """
+
+    room_name: NonEmptyString = Field(description="Room name this token is valid for")
+    user_id: NonEmptyString | None = Field(
+        None, description="User identifier to associate with token"
+    )
+    is_owner: bool = Field(
+        default=False, description="Grant owner privileges to token holder"
+    )
+    start_cloud_recording: bool = Field(
+        default=False, description="Automatically start cloud recording on join"
+    )
+    enable_recording_ui: bool = Field(
+        default=True, description="Show recording controls in UI"
+    )
+    eject_at_token_exp: bool = Field(
+        default=False, description="Eject participant when token expires"
+    )
+    nbf: int | None = Field(
+        None, description="Not-before timestamp (Unix epoch seconds)"
+    )
+    exp: int | None = Field(
+        None, description="Expiration timestamp (Unix epoch seconds)"
+    )
+
+
+class CreateMeetingTokenRequest(BaseModel):
+    """
+    Request to create a meeting token for participant authentication.
+
+    Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
+    """
+
+    properties: MeetingTokenProperties = Field(description="Token properties")
+
+
+class CreateWebhookRequest(BaseModel):
+    """
+    Request to create a webhook subscription.
+
+    Reference: https://docs.daily.co/reference/rest-api/webhooks
+    """
+
+    url: NonEmptyString = Field(description="Webhook endpoint URL (must be HTTPS)")
+    eventTypes: List[
+        Literal[
+            "participant.joined",
+            "participant.left",
+            "recording.started",
+            "recording.ready-to-download",
+            "recording.error",
+        ]
+    ] = Field(
+        description="Array of event types to subscribe to (only events we handle)"
+    )
+    hmac: NonEmptyString = Field(
+        description="Base64-encoded HMAC secret for webhook signature verification"
+    )
+    basicAuth: NonEmptyString | None = Field(
+        None, description="Optional basic auth credentials for webhook endpoint"
+    )
+
+
+class UpdateWebhookRequest(BaseModel):
+    """
+    Request to update an existing webhook.
+
+    Note: Daily.co API may not support PATCH for webhooks.
+    Common pattern is to delete and recreate.
+
+    Reference: https://docs.daily.co/reference/rest-api/webhooks
+    """
+
+    url: NonEmptyString | None = Field(None, description="New webhook endpoint URL")
+    eventTypes: List[NonEmptyString] | None = Field(
+        None, description="New array of event types"
+    )
+    hmac: NonEmptyString | None = Field(None, description="New HMAC secret")
+    basicAuth: NonEmptyString | None = Field(
+        None, description="New basic auth credentials"
+    )

server/reflector/dailyco_api/responses.py

@@ -0,0 +1,217 @@
+"""
+Daily.co API Response Models
+"""
+
+from typing import Any, Dict, List, Literal
+
+from pydantic import BaseModel, Field
+
+from reflector.dailyco_api.webhooks import DailyTrack
+from reflector.utils.string import NonEmptyString
+
+# not documented in daily; we fill it according to observations
+RecordingStatus = Literal["in-progress", "finished"]
+
+
+class RoomResponse(BaseModel):
+    """
+    Response from room creation or retrieval.
+
+    Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
+    """
+
+    id: NonEmptyString = Field(description="Unique room identifier (UUID)")
+    name: NonEmptyString = Field(description="Room name used in URLs")
+    api_created: bool = Field(description="Whether room was created via API")
+    privacy: Literal["public", "private"] = Field(description="Room privacy setting")
+    url: NonEmptyString = Field(description="Full room URL")
+    created_at: NonEmptyString = Field(description="ISO 8601 creation timestamp")
+    config: Dict[NonEmptyString, Any] = Field(
+        default_factory=dict, description="Room configuration properties"
+    )
+
+
+class RoomPresenceParticipant(BaseModel):
+    """
+    Participant presence information in a room.
+
+    Reference: https://docs.daily.co/reference/rest-api/rooms/get-room-presence
+    """
+
+    room: NonEmptyString = Field(description="Room name")
+    id: NonEmptyString = Field(description="Participant session ID")
+    userId: NonEmptyString | None = Field(None, description="User ID if provided")
+    userName: NonEmptyString | None = Field(None, description="User display name")
+    joinTime: NonEmptyString = Field(description="ISO 8601 join timestamp")
+    duration: int = Field(description="Duration in room (seconds)")
+
+
+class RoomPresenceResponse(BaseModel):
+    """
+    Response from room presence endpoint.
+
+    Reference: https://docs.daily.co/reference/rest-api/rooms/get-room-presence
+    """
+
+    total_count: int = Field(
+        description="Total number of participants currently in room"
+    )
+    data: List[RoomPresenceParticipant] = Field(
+        default_factory=list, description="Array of participant presence data"
+    )
+
+
+class MeetingParticipant(BaseModel):
+    """
+    Historical participant data from a meeting.
+
+    Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-participants
+    """
+
+    user_id: NonEmptyString | None = Field(None, description="User identifier")
+    participant_id: NonEmptyString = Field(description="Participant session identifier")
+    user_name: NonEmptyString | None = Field(None, description="User display name")
+    join_time: int = Field(description="Join timestamp (Unix epoch seconds)")
+    duration: int = Field(description="Duration in meeting (seconds)")
+
+
+class MeetingParticipantsResponse(BaseModel):
+    """
+    Response from meeting participants endpoint.
+
+    Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-participants
+    """
+
+    data: List[MeetingParticipant] = Field(
+        default_factory=list, description="Array of participant data"
+    )
+
+
+class MeetingResponse(BaseModel):
+    """
+    Response from meeting information endpoint.
+
+    Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-information
+    """
+
+    id: NonEmptyString = Field(description="Meeting session identifier (UUID)")
+    room: NonEmptyString = Field(description="Room name where meeting occurred")
+    start_time: int = Field(
+        description="Meeting start Unix timestamp (~15s granularity)"
+    )
+    duration: int = Field(description="Total meeting duration in seconds")
+    ongoing: bool = Field(description="Whether meeting is currently active")
+    max_participants: int = Field(description="Peak concurrent participant count")
+    participants: List[MeetingParticipant] = Field(
+        default_factory=list, description="Array of participant session data"
+    )
+
+
+class RecordingS3Info(BaseModel):
+    """
+    S3 bucket information for a recording.
+
+    Reference: https://docs.daily.co/reference/rest-api/recordings
+    """
+
+    bucket_name: NonEmptyString
+    bucket_region: NonEmptyString
+    endpoint: NonEmptyString | None = None
+
+
+class RecordingResponse(BaseModel):
+    """
+    Response from recording retrieval endpoint (network layer).
+
+    Duration may be None for recordings still being processed by Daily.
+    Use FinishedRecordingResponse for recordings ready for processing.
+
+    Reference: https://docs.daily.co/reference/rest-api/recordings
+    """
+
+    id: NonEmptyString = Field(description="Recording identifier")
+    room_name: NonEmptyString = Field(description="Room where recording occurred")
+    start_ts: int = Field(description="Recording start timestamp (Unix epoch seconds)")
+    status: RecordingStatus = Field(
+        description="Recording status ('in-progress' or 'finished')"
+    )
+    max_participants: int | None = Field(
+        None, description="Maximum participants during recording (may be missing)"
+    )
+    duration: int | None = Field(
+        None, description="Recording duration in seconds (None if still processing)"
+    )
+    share_token: NonEmptyString | None = Field(
+        None, description="Token for sharing recording"
+    )
+    s3: RecordingS3Info | None = Field(None, description="S3 bucket information")
+    tracks: list[DailyTrack] = Field(
+        default_factory=list,
+        description="Track list for raw-tracks recordings (always array, never null)",
+    )
+    # this is not a mistake but a deliberate Daily.co naming decision
+    mtgSessionId: NonEmptyString | None = Field(
+        None, description="Meeting session identifier (may be missing)"
+    )
+
+    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):
+    """
+    Response from meeting token creation.
+
+    Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
+    """
+
+    token: NonEmptyString = Field(
+        description="JWT meeting token for participant authentication"
+    )
+
+
+class WebhookResponse(BaseModel):
+    """
+    Response from webhook creation or retrieval.
+
+    Reference: https://docs.daily.co/reference/rest-api/webhooks
+    """
+
+    uuid: NonEmptyString = Field(description="Unique webhook identifier")
+    url: NonEmptyString = Field(description="Webhook endpoint URL")
+    hmac: NonEmptyString | None = Field(
+        None, description="Base64-encoded HMAC secret for signature verification"
+    )
+    basicAuth: NonEmptyString | None = Field(
+        None, description="Basic auth credentials if configured"
+    )
+    eventTypes: List[NonEmptyString] = Field(
+        default_factory=list,
+        description="Array of event types (e.g., ['recording.started', 'participant.joined'])",
+    )
+    state: Literal["ACTIVE", "FAILED"] = Field(
+        description="Webhook state - FAILED after 3+ consecutive failures"
+    )
+    failedCount: int = Field(default=0, description="Number of consecutive failures")
+    lastMomentPushed: NonEmptyString | None = Field(
+        None, description="ISO 8601 timestamp of last successful push"
+    )
+    domainId: NonEmptyString = Field(description="Daily.co domain/account identifier")
+    createdAt: NonEmptyString = Field(description="ISO 8601 creation timestamp")
+    updatedAt: NonEmptyString = Field(description="ISO 8601 last update timestamp")

server/reflector/dailyco_api/webhook_utils.py

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

server/reflector/dailyco_api/webhooks.py

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

server/reflector/db/__init__.py

@@ -25,11 +25,13 @@ def get_database() -> databases.Database:
 
 # import models
 import reflector.db.calendar_events  # noqa
+import reflector.db.daily_participant_sessions  # noqa
 import reflector.db.meetings  # noqa
 import reflector.db.recordings  # noqa
 import reflector.db.rooms  # noqa
 import reflector.db.transcripts  # noqa
 import reflector.db.user_api_keys  # noqa
+import reflector.db.users  # noqa
 
 kwargs = {}
 if "postgres" not in settings.DATABASE_URL:

server/reflector/db/daily_participant_sessions.py

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

server/reflector/db/meetings.py

@@ -10,7 +10,6 @@ from reflector.db.rooms import Room
 from reflector.schemas.platform import WHEREBY_PLATFORM, Platform
 from reflector.utils import generate_uuid4
 from reflector.utils.string import assert_equal
-from reflector.video_platforms.factory import get_platform
 
 meetings = sa.Table(
     "meeting",
@@ -140,14 +139,17 @@ class MeetingController:
             recording_trigger=room.recording_trigger,
             calendar_event_id=calendar_event_id,
             calendar_metadata=calendar_metadata,
-            platform=get_platform(room.platform),
+            platform=room.platform,
         )
         query = meetings.insert().values(**meeting.model_dump())
         await get_database().execute(query)
         return meeting
 
-    async def get_all_active(self) -> list[Meeting]:
+    async def get_all_active(self, platform: str | None = None) -> list[Meeting]:
-        query = meetings.select().where(meetings.c.is_active)
+        conditions = [meetings.c.is_active]
+        if platform is not None:
+            conditions.append(meetings.c.platform == platform)
+        query = meetings.select().where(sa.and_(*conditions))
         results = await get_database().fetch_all(query)
         return [Meeting(**result) for result in results]
 

server/reflector/db/recordings.py

@@ -3,6 +3,7 @@ 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
@@ -35,8 +36,15 @@ 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):
@@ -44,12 +52,14 @@ class RecordingController:
         await get_database().execute(query)
         return recording
 
-    async def get_by_id(self, id: str) -> Recording:
+    async def get_by_id(self, id: str) -> Recording | None:
         query = recordings.select().where(recordings.c.id == id)
         result = await get_database().fetch_one(query)
         return Recording(**result) if result else None
 
-    async def get_by_object_key(self, bucket_name: str, object_key: str) -> Recording:
+    async def get_by_object_key(
+        self, bucket_name: str, object_key: str
+    ) -> Recording | None:
         query = recordings.select().where(
             recordings.c.bucket_name == bucket_name,
             recordings.c.object_key == object_key,
@@ -61,5 +71,44 @@ class RecordingController:
         query = recordings.delete().where(recordings.c.id == id)
         await get_database().execute(query)
 
+    # no check for existence
+    async def get_by_ids(self, recording_ids: list[str]) -> list[Recording]:
+        if not recording_ids:
+            return []
+
+        query = recordings.select().where(recordings.c.id.in_(recording_ids))
+        results = await get_database().fetch_all(query)
+        return [Recording(**row) for row in results]
+
+    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()

server/reflector/db/rooms.py

@@ -10,6 +10,7 @@ from sqlalchemy.sql import false, or_
 
 from reflector.db import get_database, metadata
 from reflector.schemas.platform import Platform
+from reflector.settings import settings
 from reflector.utils import generate_uuid4
 
 rooms = sqlalchemy.Table(
@@ -54,8 +55,13 @@ rooms = sqlalchemy.Table(
     sqlalchemy.Column(
         "platform",
         sqlalchemy.String,
-        nullable=True,
+        nullable=False,
-        server_default=None,
+    ),
+    sqlalchemy.Column(
+        "skip_consent",
+        sqlalchemy.Boolean,
+        nullable=False,
+        server_default=sqlalchemy.sql.false(),
     ),
     sqlalchemy.Index("idx_room_is_shared", "is_shared"),
     sqlalchemy.Index("idx_room_ics_enabled", "ics_enabled"),
@@ -84,7 +90,8 @@ class Room(BaseModel):
     ics_enabled: bool = False
     ics_last_sync: datetime | None = None
     ics_last_etag: str | None = None
-    platform: Platform | None = None
+    platform: Platform = Field(default_factory=lambda: settings.DEFAULT_VIDEO_PLATFORM)
+    skip_consent: bool = False
 
 
 class RoomController:
@@ -138,7 +145,8 @@ class RoomController:
         ics_url: str | None = None,
         ics_fetch_interval: int = 300,
         ics_enabled: bool = False,
-        platform: Platform | None = None,
+        platform: Platform = settings.DEFAULT_VIDEO_PLATFORM,
+        skip_consent: bool = False,
     ):
         """
         Add a new room
@@ -146,24 +154,27 @@ class RoomController:
         if webhook_url and not webhook_secret:
             webhook_secret = secrets.token_urlsafe(32)
 
-        room = Room(
+        room_data = {
-            name=name,
+            "name": name,
-            user_id=user_id,
+            "user_id": user_id,
-            zulip_auto_post=zulip_auto_post,
+            "zulip_auto_post": zulip_auto_post,
-            zulip_stream=zulip_stream,
+            "zulip_stream": zulip_stream,
-            zulip_topic=zulip_topic,
+            "zulip_topic": zulip_topic,
-            is_locked=is_locked,
+            "is_locked": is_locked,
-            room_mode=room_mode,
+            "room_mode": room_mode,
-            recording_type=recording_type,
+            "recording_type": recording_type,
-            recording_trigger=recording_trigger,
+            "recording_trigger": recording_trigger,
-            is_shared=is_shared,
+            "is_shared": is_shared,
-            webhook_url=webhook_url,
+            "webhook_url": webhook_url,
-            webhook_secret=webhook_secret,
+            "webhook_secret": webhook_secret,
-            ics_url=ics_url,
+            "ics_url": ics_url,
-            ics_fetch_interval=ics_fetch_interval,
+            "ics_fetch_interval": ics_fetch_interval,
-            ics_enabled=ics_enabled,
+            "ics_enabled": ics_enabled,
-            platform=platform,
+            "platform": platform,
-        )
+            "skip_consent": skip_consent,
+        }
+
+        room = Room(**room_data)
         query = rooms.insert().values(**room.model_dump())
         try:
             await get_database().execute(query)

server/reflector/db/transcripts.py

@@ -44,6 +44,7 @@ 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),
@@ -164,6 +165,10 @@ class TranscriptFinalLongSummary(BaseModel):
     long_summary: str
 
 
+class TranscriptActionItems(BaseModel):
+    action_items: dict
+
+
 class TranscriptFinalTitle(BaseModel):
     title: str
 
@@ -204,6 +209,7 @@ 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 = []
@@ -368,7 +374,12 @@ class TranscriptController:
         room_id: str | None = None,
         search_term: str | None = None,
         return_query: bool = False,
-        exclude_columns: list[str] = ["topics", "events", "participants"],
+        exclude_columns: list[str] = [
+            "topics",
+            "events",
+            "participants",
+            "action_items",
+        ],
     ) -> list[Transcript]:
         """
         Get all transcripts

server/reflector/db/users.py

@@ -0,0 +1,98 @@
+"""User table for storing Authentik user information."""
+
+from datetime import datetime, timezone
+
+import sqlalchemy
+from pydantic import BaseModel, Field
+
+from reflector.db import get_database, metadata
+from reflector.utils import generate_uuid4
+from reflector.utils.string import NonEmptyString
+
+users = sqlalchemy.Table(
+    "user",
+    metadata,
+    sqlalchemy.Column("id", sqlalchemy.String, primary_key=True),
+    sqlalchemy.Column("email", sqlalchemy.String, nullable=False),
+    sqlalchemy.Column("authentik_uid", sqlalchemy.String, nullable=False),
+    sqlalchemy.Column("created_at", sqlalchemy.DateTime(timezone=True), nullable=False),
+    sqlalchemy.Column("updated_at", sqlalchemy.DateTime(timezone=True), nullable=False),
+    sqlalchemy.Index("idx_user_authentik_uid", "authentik_uid", unique=True),
+    sqlalchemy.Index("idx_user_email", "email", unique=False),
+)
+
+
+class User(BaseModel):
+    id: NonEmptyString = Field(default_factory=generate_uuid4)
+    email: NonEmptyString
+    authentik_uid: NonEmptyString
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+
+
+class UserController:
+    @staticmethod
+    async def get_by_id(user_id: NonEmptyString) -> User | None:
+        query = users.select().where(users.c.id == user_id)
+        result = await get_database().fetch_one(query)
+        return User(**result) if result else None
+
+    @staticmethod
+    async def get_by_authentik_uid(authentik_uid: NonEmptyString) -> User | None:
+        query = users.select().where(users.c.authentik_uid == authentik_uid)
+        result = await get_database().fetch_one(query)
+        return User(**result) if result else None
+
+    @staticmethod
+    async def get_by_email(email: NonEmptyString) -> User | None:
+        query = users.select().where(users.c.email == email)
+        result = await get_database().fetch_one(query)
+        return User(**result) if result else None
+
+    @staticmethod
+    async def create_or_update(
+        id: NonEmptyString, authentik_uid: NonEmptyString, email: NonEmptyString
+    ) -> User:
+        existing = await UserController.get_by_authentik_uid(authentik_uid)
+        now = datetime.now(timezone.utc)
+
+        if existing:
+            query = (
+                users.update()
+                .where(users.c.authentik_uid == authentik_uid)
+                .values(email=email, updated_at=now)
+            )
+            await get_database().execute(query)
+            return User(
+                id=existing.id,
+                authentik_uid=authentik_uid,
+                email=email,
+                created_at=existing.created_at,
+                updated_at=now,
+            )
+        else:
+            user = User(
+                id=id,
+                authentik_uid=authentik_uid,
+                email=email,
+                created_at=now,
+                updated_at=now,
+            )
+            query = users.insert().values(**user.model_dump())
+            await get_database().execute(query)
+            return user
+
+    @staticmethod
+    async def list_all() -> list[User]:
+        query = users.select().order_by(users.c.created_at.desc())
+        results = await get_database().fetch_all(query)
+        return [User(**r) for r in results]
+
+    @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()

server/reflector/llm.py

@@ -1,13 +1,32 @@
-from typing import Type, TypeVar
+import logging
+from contextvars import ContextVar
+from typing import Generic, Type, TypeVar
+from uuid import uuid4
 
 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
+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:
@@ -19,6 +38,158 @@ 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
@@ -29,11 +200,12 @@ 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,
@@ -43,6 +215,7 @@ 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(
@@ -59,25 +232,38 @@ class LLM:
         texts: list[str],
         output_cls: Type[T],
         tone_name: str | None = None,
+        timeout: int | None = None,
     ) -> T:
-        """Get structured output from LLM for non-function-calling models"""
+        """Get structured output from LLM with validation retry via Workflow."""
-        summarizer = TreeSummarize(verbose=True)
+        if timeout is None:
-        response = await summarizer.aget_response(prompt, texts, tone_name=tone_name)
+            timeout = self.settings_obj.LLM_STRUCTURED_RESPONSE_TIMEOUT
 
-        output_parser = PydanticOutputParser(output_cls)
+        async def run_workflow():
+            workflow = StructuredOutputWorkflow(
+                output_cls=output_cls,
+                max_retries=self.settings_obj.LLM_PARSE_MAX_RETRIES + 1,
+                timeout=timeout,
+            )
 
-        program = LLMTextCompletionProgram.from_defaults(
+            result = await workflow.run(
-            output_parser=output_parser,
+                prompt=prompt,
-            prompt_template_str=STRUCTURED_RESPONSE_PROMPT_TEMPLATE,
+                texts=texts,
-            verbose=False,
+                tone_name=tone_name,
+            )
+
+            if "error" in result:
+                error_msg = result["error"] or "Max retries exceeded"
+                raise LLMParseError(
+                    output_cls=output_cls,
+                    error_msg=error_msg,
+                    attempts=result.get("attempts", 0),
+                )
+
+            return result["success"]
+
+        return await retry(run_workflow)(
+            retry_attempts=3,
+            retry_backoff_interval=1.0,
+            retry_backoff_max=30.0,
+            retry_ignore_exc_types=(WorkflowTimeoutError,),
         )
-
-        format_instructions = output_parser.format(
-            "Please structure the above information in the following JSON format:"
-        )
-
-        output = await program.acall(
-            analysis=str(response), format_instructions=format_instructions
-        )
-
-        return output

server/reflector/pipelines/main_file_pipeline.py

@@ -309,6 +309,7 @@ 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,
         )
@@ -340,7 +341,6 @@ 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")

server/reflector/pipelines/main_live_pipeline.py

@@ -27,6 +27,7 @@ from reflector.db.recordings import recordings_controller
 from reflector.db.rooms import rooms_controller
 from reflector.db.transcripts import (
     Transcript,
+    TranscriptActionItems,
     TranscriptDuration,
     TranscriptFinalLongSummary,
     TranscriptFinalShortSummary,
@@ -111,7 +112,7 @@ def get_transcript(func):
         transcript_id = kwargs.pop("transcript_id")
         transcript = await transcripts_controller.get_by_id(transcript_id=transcript_id)
         if not transcript:
-            raise Exception("Transcript {transcript_id} not found")
+            raise Exception(f"Transcript {transcript_id} not found")
 
         # Enhanced logger with Celery task context
         tlogger = logger.bind(transcript_id=transcript.id)
@@ -306,6 +307,23 @@ 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():
@@ -465,6 +483,7 @@ 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,
             ),
         ]
 

server/reflector/pipelines/main_multitrack_pipeline.py

@@ -9,7 +9,10 @@ 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,
@@ -29,7 +32,12 @@ 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
@@ -414,7 +422,15 @@ class PipelineMainMultitrack(PipelineMainBase):
             # Open all containers with cleanup guaranteed
             for i, url in enumerate(valid_track_urls):
                 try:
-                    c = av.open(url)
+                    c = av.open(
+                        url,
+                        options={
+                            # it's trying to stream from s3 by default
+                            "reconnect": "1",
+                            "reconnect_streamed": "1",
+                            "reconnect_delay_max": "5",
+                        },
+                    )
                     containers.append(c)
                 except Exception as e:
                     self.logger.warning(
@@ -443,6 +459,8 @@ 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:
@@ -462,8 +480,6 @@ 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()
@@ -494,6 +510,90 @@ 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():
@@ -502,9 +602,12 @@ class PipelineMainMultitrack(PipelineMainBase):
                 {
                     "events": [],
                     "topics": [],
+                    "participants": [],
                 },
             )
 
+        await self.update_participants_from_daily(transcript, track_keys)
+
         source_storage = get_transcripts_storage()
         transcript_storage = source_storage
 
@@ -582,7 +685,8 @@ class PipelineMainMultitrack(PipelineMainBase):
             t = await self.transcribe_file(padded_url, transcript.source_language)
 
             if not t.words:
-                continue
+                self.logger.debug(f"no words in track {idx}")
+                # not skipping, it may be silence or indistinguishable mumbling
 
             for w in t.words:
                 w.speaker = idx
@@ -668,6 +772,7 @@ 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,
         )

server/reflector/pipelines/topic_processing.py

@@ -89,6 +89,7 @@ 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,
 ):
@@ -96,11 +97,14 @@ async def generate_summaries(
         logger.warning("No topics for summary generation")
         return
 
-    processor = TranscriptFinalSummaryProcessor(
+    processor_kwargs = {
-        transcript=transcript,
+        "transcript": transcript,
-        callback=on_long_summary_callback,
+        "callback": on_long_summary_callback,
-        on_short_summary=on_short_summary_callback,
+        "on_short_summary": on_short_summary_callback,
-    )
+        "on_action_items": on_action_items_callback,
+    }
+
+    processor = TranscriptFinalSummaryProcessor(**processor_kwargs)
     processor.set_pipeline(empty_pipeline)
 
     for topic in topics:

server/reflector/processors/summary/summary_builder.py

@@ -96,6 +96,36 @@ 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:
@@ -155,6 +185,53 @@ 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
@@ -166,6 +243,8 @@ 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)
 
@@ -189,13 +268,20 @@ class SummaryBuilder:
         self.llm = llm
 
     async def _get_structured_response(
-        self, prompt: str, output_cls: Type[T], tone_name: str | None = None
+        self,
+        prompt: str,
+        output_cls: Type[T],
+        tone_name: str | None = None,
+        timeout: int | 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
+            enhanced_prompt,
+            [self.transcript],
+            output_cls,
+            tone_name=tone_name,
+            timeout=timeout,
         )
 
     async def _get_response(
@@ -216,11 +302,19 @@ class SummaryBuilder:
     # Participants
     # ----------------------------------------------------------------------------
 
-    def set_known_participants(self, participants: list[str]) -> None:
+    def set_known_participants(
+        self,
+        participants: list[str],
+        participant_name_to_id: dict[str, str] | None = None,
+    ) -> 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")
@@ -231,10 +325,12 @@ 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"""
@@ -413,6 +509,92 @@ 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.
@@ -424,6 +606,7 @@ class SummaryBuilder:
 
         await self.generate_subject_summaries()
         await self.generate_recap()
+        await self.identify_action_items()
 
     # ----------------------------------------------------------------------------
     # Markdown
@@ -526,8 +709,6 @@ if __name__ == "__main__":
         if args.summary:
             await sm.generate_summary()
 
-        # Note: action items generation has been removed
-
         print("")
         print("-" * 80)
         print("")

server/reflector/processors/transcript_final_summary.py

@@ -1,7 +1,12 @@
 from reflector.llm import LLM
 from reflector.processors.base import Processor
 from reflector.processors.summary.summary_builder import SummaryBuilder
-from reflector.processors.types import FinalLongSummary, FinalShortSummary, TitleSummary
+from reflector.processors.types import (
+    ActionItems,
+    FinalLongSummary,
+    FinalShortSummary,
+    TitleSummary,
+)
 from reflector.settings import settings
 
 
@@ -27,15 +32,20 @@ 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"
                 )
-                builder.set_known_participants(participant_names)
+                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
+                )
             else:
                 self.logger.info(
                     "Participants field exists but is empty, identifying participants"
@@ -63,7 +73,6 @@ class TranscriptFinalSummaryProcessor(Processor):
             self.logger.warning("No summary to output")
             return
 
-        # build the speakermap from the transcript
         speakermap = {}
         if self.transcript:
             speakermap = {
@@ -76,8 +85,6 @@ 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:
@@ -111,4 +118,9 @@ 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)

server/reflector/processors/transcript_topic_detector.py

@@ -78,7 +78,11 @@ class TranscriptTopicDetectorProcessor(Processor):
         """
         prompt = TOPIC_PROMPT.format(text=text)
         response = await self.llm.get_structured_response(
-            prompt, [text], TopicResponse, tone_name="Topic analyzer"
+            prompt,
+            [text],
+            TopicResponse,
+            tone_name="Topic analyzer",
+            timeout=settings.LLM_STRUCTURED_RESPONSE_TIMEOUT,
         )
         return response
 

server/reflector/processors/types.py

@@ -1,6 +1,7 @@
 import io
 import re
 import tempfile
+from collections import defaultdict
 from pathlib import Path
 from typing import Annotated, TypedDict
 
@@ -16,6 +17,17 @@ 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):
@@ -76,7 +88,6 @@ 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:
@@ -106,7 +117,7 @@ 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_LENGTH):
+        if have_punc and (len(current_segment.text) > MAX_SEGMENT_CHARS):
             segments.append(current_segment)
             current_segment = None
 
@@ -116,6 +127,70 @@ 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] = []
@@ -154,7 +229,9 @@ class Transcript(BaseModel):
             word.start += offset
             word.end += offset
 
-    def as_segments(self) -> list[TranscriptSegment]:
+    def as_segments(self, is_multitrack: bool = False) -> list[TranscriptSegment]:
+        if is_multitrack:
+            return words_to_segments_by_sentence(self.words)
         return words_to_segments(self.words)
 
 
@@ -187,6 +264,10 @@ class FinalShortSummary(BaseModel):
     duration: float
 
 
+class ActionItems(BaseModel):
+    action_items: dict  # JSON-serializable dict from ActionItemsResponse
+
+
 class FinalTitle(BaseModel):
     title: str
 

server/reflector/schemas/transcript_formats.py

@@ -0,0 +1,17 @@
+"""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

server/reflector/services/transcript_process.py

@@ -0,0 +1,171 @@
+"""
+Transcript processing service - shared logic for HTTP endpoints and Celery tasks.
+
+This module provides result-based error handling that works in both contexts:
+- HTTP endpoint: converts errors to HTTPException
+- Celery task: converts errors to Exception
+"""
+
+from dataclasses import dataclass
+from typing import Literal, Union, assert_never
+
+import celery
+from celery.result import AsyncResult
+
+from reflector.db.recordings import recordings_controller
+from reflector.db.transcripts import Transcript
+from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
+from reflector.pipelines.main_multitrack_pipeline import (
+    task_pipeline_multitrack_process,
+)
+from reflector.utils.string import NonEmptyString
+
+
+@dataclass
+class ProcessError:
+    detail: NonEmptyString
+
+
+@dataclass
+class FileProcessingConfig:
+    transcript_id: NonEmptyString
+    mode: Literal["file"] = "file"
+
+
+@dataclass
+class MultitrackProcessingConfig:
+    transcript_id: NonEmptyString
+    bucket_name: NonEmptyString
+    track_keys: list[str]
+    mode: Literal["multitrack"] = "multitrack"
+
+
+ProcessingConfig = Union[FileProcessingConfig, MultitrackProcessingConfig]
+PrepareResult = Union[ProcessingConfig, ProcessError]
+
+
+@dataclass
+class ValidationOk:
+    # transcript currently doesnt always have recording_id
+    recording_id: NonEmptyString | None
+    transcript_id: NonEmptyString
+
+
+@dataclass
+class ValidationLocked:
+    detail: NonEmptyString
+
+
+@dataclass
+class ValidationNotReady:
+    detail: NonEmptyString
+
+
+@dataclass
+class ValidationAlreadyScheduled:
+    detail: NonEmptyString
+
+
+ValidationError = Union[
+    ValidationNotReady, ValidationLocked, ValidationAlreadyScheduled
+]
+ValidationResult = Union[ValidationOk, ValidationError]
+
+
+@dataclass
+class DispatchOk:
+    status: Literal["ok"] = "ok"
+
+
+@dataclass
+class DispatchAlreadyRunning:
+    status: Literal["already_running"] = "already_running"
+
+
+DispatchResult = Union[
+    DispatchOk, DispatchAlreadyRunning, ProcessError, ValidationError
+]
+
+
+async def validate_transcript_for_processing(
+    transcript: Transcript,
+) -> ValidationResult:
+    if transcript.locked:
+        return ValidationLocked(detail="Recording is locked")
+
+    if transcript.status == "idle":
+        return ValidationNotReady(detail="Recording is not ready for processing")
+
+    if task_is_scheduled_or_active(
+        "reflector.pipelines.main_file_pipeline.task_pipeline_file_process",
+        transcript_id=transcript.id,
+    ) or task_is_scheduled_or_active(
+        "reflector.pipelines.main_multitrack_pipeline.task_pipeline_multitrack_process",
+        transcript_id=transcript.id,
+    ):
+        return ValidationAlreadyScheduled(detail="already running")
+
+    return ValidationOk(
+        recording_id=transcript.recording_id, transcript_id=transcript.id
+    )
+
+
+async def prepare_transcript_processing(validation: ValidationOk) -> PrepareResult:
+    """
+    Determine processing mode from transcript/recording data.
+    """
+    bucket_name: str | None = None
+    track_keys: list[str] | None = None
+
+    if validation.recording_id:
+        recording = await recordings_controller.get_by_id(validation.recording_id)
+        if recording:
+            bucket_name = recording.bucket_name
+            track_keys = recording.track_keys
+
+            if track_keys is not None and len(track_keys) == 0:
+                return ProcessError(
+                    detail="No track keys found, must be either > 0 or None",
+                )
+            if track_keys is not None and not bucket_name:
+                return ProcessError(
+                    detail="Bucket name must be specified",
+                )
+
+    if track_keys:
+        return MultitrackProcessingConfig(
+            bucket_name=bucket_name,  # type: ignore (validated above)
+            track_keys=track_keys,
+            transcript_id=validation.transcript_id,
+        )
+
+    return FileProcessingConfig(
+        transcript_id=validation.transcript_id,
+    )
+
+
+def dispatch_transcript_processing(config: ProcessingConfig) -> AsyncResult:
+    if isinstance(config, MultitrackProcessingConfig):
+        return task_pipeline_multitrack_process.delay(
+            transcript_id=config.transcript_id,
+            bucket_name=config.bucket_name,
+            track_keys=config.track_keys,
+        )
+    elif isinstance(config, FileProcessingConfig):
+        return task_pipeline_file_process.delay(transcript_id=config.transcript_id)
+    else:
+        assert_never(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 task in tasks:
+            if task["name"] == task_name and task["kwargs"] == kwargs:
+                return True
+
+    return False

server/reflector/settings.py

@@ -74,6 +74,13 @@ 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"
@@ -138,7 +145,6 @@ class Settings(BaseSettings):
     DAILY_WEBHOOK_UUID: str | None = (
         None  # Webhook UUID for this environment. Not used by production code
     )
-
     # Platform Configuration
     DEFAULT_VIDEO_PLATFORM: Platform = WHEREBY_PLATFORM
 

server/reflector/tools/cli_multitrack.py

@@ -0,0 +1,347 @@
+import asyncio
+import sys
+import time
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, Protocol
+
+import structlog
+from celery.result import AsyncResult
+
+from reflector.db import get_database
+from reflector.db.transcripts import SourceKind, Transcript, transcripts_controller
+from reflector.pipelines.main_multitrack_pipeline import (
+    task_pipeline_multitrack_process,
+)
+from reflector.storage import get_transcripts_storage
+from reflector.tools.process import (
+    extract_result_from_entry,
+    parse_s3_url,
+    validate_s3_objects,
+)
+
+logger = structlog.get_logger(__name__)
+
+DEFAULT_PROCESSING_TIMEOUT_SECONDS = 3600
+
+MAX_ERROR_MESSAGE_LENGTH = 500
+
+TASK_POLL_INTERVAL_SECONDS = 2
+
+
+class StatusCallback(Protocol):
+    def __call__(self, state: str, elapsed_seconds: int) -> None: ...
+
+
+@dataclass
+class MultitrackTaskResult:
+    success: bool
+    transcript_id: str
+    error: Optional[str] = None
+
+
+async def create_multitrack_transcript(
+    bucket_name: str,
+    track_keys: List[str],
+    source_language: str,
+    target_language: str,
+    user_id: Optional[str] = None,
+) -> Transcript:
+    num_tracks = len(track_keys)
+    track_word = "track" if num_tracks == 1 else "tracks"
+    transcript_name = f"Multitrack ({num_tracks} {track_word})"
+
+    transcript = await transcripts_controller.add(
+        transcript_name,
+        source_kind=SourceKind.FILE,
+        source_language=source_language,
+        target_language=target_language,
+        user_id=user_id,
+    )
+
+    logger.info(
+        "Created multitrack transcript",
+        transcript_id=transcript.id,
+        name=transcript_name,
+        bucket=bucket_name,
+        num_tracks=len(track_keys),
+    )
+
+    return transcript
+
+
+def submit_multitrack_task(
+    transcript_id: str, bucket_name: str, track_keys: List[str]
+) -> AsyncResult:
+    result = task_pipeline_multitrack_process.delay(
+        transcript_id=transcript_id,
+        bucket_name=bucket_name,
+        track_keys=track_keys,
+    )
+
+    logger.info(
+        "Multitrack task submitted",
+        transcript_id=transcript_id,
+        task_id=result.id,
+        bucket=bucket_name,
+        num_tracks=len(track_keys),
+    )
+
+    return result
+
+
+async def wait_for_task(
+    result: AsyncResult,
+    transcript_id: str,
+    timeout_seconds: int = DEFAULT_PROCESSING_TIMEOUT_SECONDS,
+    poll_interval: int = TASK_POLL_INTERVAL_SECONDS,
+    status_callback: Optional[StatusCallback] = None,
+) -> MultitrackTaskResult:
+    start_time = time.time()
+    last_status = None
+
+    while not result.ready():
+        elapsed = time.time() - start_time
+        if elapsed > timeout_seconds:
+            error_msg = (
+                f"Task {result.id} did not complete within {timeout_seconds}s "
+                f"for transcript {transcript_id}"
+            )
+            logger.error(
+                "Task timeout",
+                task_id=result.id,
+                transcript_id=transcript_id,
+                elapsed_seconds=elapsed,
+            )
+            raise TimeoutError(error_msg)
+
+        if result.state != last_status:
+            if status_callback:
+                status_callback(result.state, int(elapsed))
+            last_status = result.state
+
+        await asyncio.sleep(poll_interval)
+
+    if result.failed():
+        error_info = result.info
+        traceback_info = getattr(result, "traceback", None)
+
+        logger.error(
+            "Multitrack task failed",
+            transcript_id=transcript_id,
+            task_id=result.id,
+            error=str(error_info),
+            has_traceback=bool(traceback_info),
+        )
+
+        error_detail = str(error_info)
+        if traceback_info:
+            error_detail += f"\nTraceback:\n{traceback_info}"
+
+        return MultitrackTaskResult(
+            success=False, transcript_id=transcript_id, error=error_detail
+        )
+
+    logger.info(
+        "Multitrack task completed",
+        transcript_id=transcript_id,
+        task_id=result.id,
+        state=result.state,
+    )
+
+    return MultitrackTaskResult(success=True, transcript_id=transcript_id)
+
+
+async def update_transcript_status(
+    transcript_id: str,
+    status: str,
+    error: Optional[str] = None,
+    max_error_length: int = MAX_ERROR_MESSAGE_LENGTH,
+) -> None:
+    database = get_database()
+    connected = False
+
+    try:
+        await database.connect()
+        connected = True
+
+        transcript = await transcripts_controller.get_by_id(transcript_id)
+        if transcript:
+            update_data: Dict[str, Any] = {"status": status}
+
+            if error:
+                if len(error) > max_error_length:
+                    error = error[: max_error_length - 3] + "..."
+                update_data["error"] = error
+
+            await transcripts_controller.update(transcript, update_data)
+
+            logger.info(
+                "Updated transcript status",
+                transcript_id=transcript_id,
+                status=status,
+                has_error=bool(error),
+            )
+    except Exception as e:
+        logger.warning(
+            "Failed to update transcript status",
+            transcript_id=transcript_id,
+            error=str(e),
+        )
+    finally:
+        if connected:
+            try:
+                await database.disconnect()
+            except Exception as e:
+                logger.warning(f"Database disconnect failed: {e}")
+
+
+async def process_multitrack(
+    bucket_name: str,
+    track_keys: List[str],
+    source_language: str,
+    target_language: str,
+    user_id: Optional[str] = None,
+    timeout_seconds: int = DEFAULT_PROCESSING_TIMEOUT_SECONDS,
+    status_callback: Optional[StatusCallback] = None,
+) -> MultitrackTaskResult:
+    """High-level orchestration for multitrack processing."""
+    database = get_database()
+    transcript = None
+    connected = False
+
+    try:
+        await database.connect()
+        connected = True
+
+        transcript = await create_multitrack_transcript(
+            bucket_name=bucket_name,
+            track_keys=track_keys,
+            source_language=source_language,
+            target_language=target_language,
+            user_id=user_id,
+        )
+
+        result = submit_multitrack_task(
+            transcript_id=transcript.id, bucket_name=bucket_name, track_keys=track_keys
+        )
+
+    except Exception as e:
+        if transcript:
+            try:
+                await update_transcript_status(
+                    transcript_id=transcript.id, status="failed", error=str(e)
+                )
+            except Exception as update_error:
+                logger.error(
+                    "Failed to update transcript status after error",
+                    original_error=str(e),
+                    update_error=str(update_error),
+                    transcript_id=transcript.id,
+                )
+        raise
+    finally:
+        if connected:
+            try:
+                await database.disconnect()
+            except Exception as e:
+                logger.warning(f"Database disconnect failed: {e}")
+
+    # Poll outside database connection
+    task_result = await wait_for_task(
+        result=result,
+        transcript_id=transcript.id,
+        timeout_seconds=timeout_seconds,
+        poll_interval=2,
+        status_callback=status_callback,
+    )
+
+    if not task_result.success:
+        await update_transcript_status(
+            transcript_id=transcript.id, status="failed", error=task_result.error
+        )
+
+    return task_result
+
+
+def print_progress(message: str) -> None:
+    """Print progress message to stderr for CLI visibility."""
+    print(f"{message}", file=sys.stderr)
+
+
+def create_status_callback() -> StatusCallback:
+    """Create callback for task status updates during polling."""
+
+    def callback(state: str, elapsed_seconds: int) -> None:
+        print_progress(
+            f"Multitrack pipeline status: {state} (elapsed: {elapsed_seconds}s)"
+        )
+
+    return callback
+
+
+async def process_multitrack_cli(
+    s3_urls: List[str],
+    source_language: str,
+    target_language: str,
+    output_path: Optional[str] = None,
+) -> None:
+    if not s3_urls:
+        raise ValueError("At least one track required for multitrack processing")
+
+    bucket_keys = []
+    for url in s3_urls:
+        try:
+            bucket, key = parse_s3_url(url)
+            bucket_keys.append((bucket, key))
+        except ValueError as e:
+            raise ValueError(f"Invalid S3 URL '{url}': {e}") from e
+
+    buckets = set(bucket for bucket, _ in bucket_keys)
+    if len(buckets) > 1:
+        raise ValueError(
+            f"All tracks must be in the same S3 bucket. "
+            f"Found {len(buckets)} different buckets: {sorted(buckets)}. "
+            f"Please upload all files to a single bucket."
+        )
+
+    primary_bucket = bucket_keys[0][0]
+    track_keys = [key for _, key in bucket_keys]
+
+    print_progress(
+        f"Starting multitrack CLI processing: "
+        f"bucket={primary_bucket}, num_tracks={len(track_keys)}, "
+        f"source_language={source_language}, target_language={target_language}"
+    )
+
+    storage = get_transcripts_storage()
+    await validate_s3_objects(storage, bucket_keys)
+    print_progress(f"S3 validation complete: {len(bucket_keys)} objects verified")
+
+    result = await process_multitrack(
+        bucket_name=primary_bucket,
+        track_keys=track_keys,
+        source_language=source_language,
+        target_language=target_language,
+        user_id=None,
+        timeout_seconds=3600,
+        status_callback=create_status_callback(),
+    )
+
+    if not result.success:
+        error_msg = (
+            f"Multitrack pipeline failed for transcript {result.transcript_id}\n"
+        )
+        if result.error:
+            error_msg += f"Error: {result.error}\n"
+        raise RuntimeError(error_msg)
+
+    print_progress(
+        f"Multitrack processing complete for transcript {result.transcript_id}"
+    )
+
+    database = get_database()
+    await database.connect()
+    try:
+        await extract_result_from_entry(result.transcript_id, output_path)
+    finally:
+        await database.disconnect()

server/reflector/tools/process.py

@@ -9,7 +9,10 @@ import shutil
 import sys
 import time
 from pathlib import Path
-from typing import Any, Dict, List, Literal
+from typing import Any, Dict, List, Literal, Tuple
+from urllib.parse import unquote, urlparse
+
+from botocore.exceptions import BotoCoreError, ClientError, NoCredentialsError
 
 from reflector.db.transcripts import SourceKind, TranscriptTopic, transcripts_controller
 from reflector.logger import logger
@@ -20,10 +23,119 @@ from reflector.pipelines.main_live_pipeline import pipeline_post as live_pipelin
 from reflector.pipelines.main_live_pipeline import (
     pipeline_process as live_pipeline_process,
 )
+from reflector.storage import Storage
+
+
+def validate_s3_bucket_name(bucket: str) -> None:
+    if not bucket:
+        raise ValueError("Bucket name cannot be empty")
+    if len(bucket) > 255:  # Absolute max for any region
+        raise ValueError(f"Bucket name too long: {len(bucket)} characters (max 255)")
+
+
+def validate_s3_key(key: str) -> None:
+    if not key:
+        raise ValueError("S3 key cannot be empty")
+    if len(key) > 1024:
+        raise ValueError(f"S3 key too long: {len(key)} characters (max 1024)")
+
+
+def parse_s3_url(url: str) -> Tuple[str, str]:
+    parsed = urlparse(url)
+
+    if parsed.scheme == "s3":
+        bucket = parsed.netloc
+        key = parsed.path.lstrip("/")
+        if parsed.fragment:
+            logger.debug(
+                "URL fragment ignored (not part of S3 key)",
+                url=url,
+                fragment=parsed.fragment,
+            )
+        if not bucket or not key:
+            raise ValueError(f"Invalid S3 URL: {url} (missing bucket or key)")
+        bucket = unquote(bucket)
+        key = unquote(key)
+        validate_s3_bucket_name(bucket)
+        validate_s3_key(key)
+        return bucket, key
+
+    elif parsed.scheme in ("http", "https"):
+        if ".s3." in parsed.netloc or parsed.netloc.endswith(".s3.amazonaws.com"):
+            bucket = parsed.netloc.split(".")[0]
+            key = parsed.path.lstrip("/")
+            if parsed.fragment:
+                logger.debug("URL fragment ignored", url=url, fragment=parsed.fragment)
+            if not bucket or not key:
+                raise ValueError(f"Invalid S3 URL: {url} (missing bucket or key)")
+            bucket = unquote(bucket)
+            key = unquote(key)
+            validate_s3_bucket_name(bucket)
+            validate_s3_key(key)
+            return bucket, key
+
+        elif parsed.netloc.startswith("s3.") and "amazonaws.com" in parsed.netloc:
+            path_parts = parsed.path.lstrip("/").split("/", 1)
+            if len(path_parts) != 2:
+                raise ValueError(f"Invalid S3 URL: {url} (missing bucket or key)")
+            bucket, key = path_parts
+            if parsed.fragment:
+                logger.debug("URL fragment ignored", url=url, fragment=parsed.fragment)
+            bucket = unquote(bucket)
+            key = unquote(key)
+            validate_s3_bucket_name(bucket)
+            validate_s3_key(key)
+            return bucket, key
+
+        else:
+            raise ValueError(f"Invalid S3 URL format: {url} (not recognized as S3 URL)")
+
+    else:
+        raise ValueError(f"Invalid S3 URL scheme: {url} (must be s3:// or https://)")
+
+
+async def validate_s3_objects(
+    storage: Storage, bucket_keys: List[Tuple[str, str]]
+) -> None:
+    async with storage.session.client("s3") as client:
+
+        async def check_object(bucket: str, key: str) -> None:
+            try:
+                await client.head_object(Bucket=bucket, Key=key)
+            except ClientError as e:
+                error_code = e.response["Error"]["Code"]
+                if error_code in ("404", "NoSuchKey"):
+                    raise ValueError(f"S3 object not found: s3://{bucket}/{key}") from e
+                elif error_code in ("403", "Forbidden", "AccessDenied"):
+                    raise ValueError(
+                        f"Access denied for S3 object: s3://{bucket}/{key}. "
+                        f"Check AWS credentials and permissions"
+                    ) from e
+                else:
+                    raise ValueError(
+                        f"S3 error {error_code} for s3://{bucket}/{key}: "
+                        f"{e.response['Error'].get('Message', 'Unknown error')}"
+                    ) from e
+            except NoCredentialsError as e:
+                raise ValueError(
+                    "AWS credentials not configured. Set AWS_ACCESS_KEY_ID and "
+                    "AWS_SECRET_ACCESS_KEY environment variables"
+                ) from e
+            except BotoCoreError as e:
+                raise ValueError(
+                    f"AWS service error for s3://{bucket}/{key}: {str(e)}"
+                ) from e
+            except Exception as e:
+                raise ValueError(
+                    f"Unexpected error validating s3://{bucket}/{key}: {str(e)}"
+                ) from e
+
+        await asyncio.gather(
+            *(check_object(bucket, key) for bucket, key in bucket_keys)
+        )
 
 
 def serialize_topics(topics: List[TranscriptTopic]) -> List[Dict[str, Any]]:
-    """Convert TranscriptTopic objects to JSON-serializable dicts"""
     serialized = []
     for topic in topics:
         topic_dict = topic.model_dump()
@@ -32,7 +144,6 @@ def serialize_topics(topics: List[TranscriptTopic]) -> List[Dict[str, Any]]:
 
 
 def debug_print_speakers(serialized_topics: List[Dict[str, Any]]) -> None:
-    """Print debug info about speakers found in topics"""
     all_speakers = set()
     for topic_dict in serialized_topics:
         for word in topic_dict.get("words", []):
@@ -47,8 +158,6 @@ def debug_print_speakers(serialized_topics: List[Dict[str, Any]]) -> None:
 TranscriptId = str
 
 
-# common interface for every flow: it needs an Entry in db with specific ceremony (file path + status + actual file in file system)
-# ideally we want to get rid of it at some point
 async def prepare_entry(
     source_path: str,
     source_language: str,
@@ -65,9 +174,7 @@ async def prepare_entry(
         user_id=None,
     )
 
-    logger.info(
+    logger.info(f"Created transcript {transcript.id} for {file_path.name}")
-        f"Created empty transcript {transcript.id} for file {file_path.name} because technically we need an empty transcript before we start transcript"
-    )
 
     # pipelines expect files as upload.*
 
@@ -83,7 +190,6 @@ async def prepare_entry(
     return transcript.id
 
 
-# same reason as prepare_entry
 async def extract_result_from_entry(
     transcript_id: TranscriptId, output_path: str
 ) -> None:
@@ -193,13 +299,20 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         description="Process audio files with speaker diarization"
     )
-    parser.add_argument("source", help="Source file (mp3, wav, mp4...)")
+    parser.add_argument(
+        "source",
+        help="Source file (mp3, wav, mp4...) or comma-separated S3 URLs with --multitrack",
+    )
     parser.add_argument(
         "--pipeline",
-        required=True,
         choices=["live", "file"],
         help="Pipeline type to use for processing (live: streaming/incremental, file: batch/parallel)",
     )
+    parser.add_argument(
+        "--multitrack",
+        action="store_true",
+        help="Process multiple audio tracks from comma-separated S3 URLs",
+    )
     parser.add_argument(
         "--source-language", default="en", help="Source language code (default: en)"
     )
@@ -209,12 +322,40 @@ if __name__ == "__main__":
     parser.add_argument("--output", "-o", help="Output file (output.jsonl)")
     args = parser.parse_args()
 
-    asyncio.run(
+    if args.multitrack:
-        process(
+        if not args.source:
-            args.source,
+            parser.error("Source URLs required for multitrack processing")
-            args.source_language,
+
-            args.target_language,
+        s3_urls = [url.strip() for url in args.source.split(",") if url.strip()]
-            args.pipeline,
+
-            args.output,
+        if not s3_urls:
+            parser.error("At least one S3 URL required for multitrack processing")
+
+        from reflector.tools.cli_multitrack import process_multitrack_cli
+
+        asyncio.run(
+            process_multitrack_cli(
+                s3_urls,
+                args.source_language,
+                args.target_language,
+                args.output,
+            )
+        )
+    else:
+        if not args.pipeline:
+            parser.error("--pipeline is required for single-track processing")
+
+        if "," in args.source:
+            parser.error(
+                "Multiple files detected. Use --multitrack flag for multitrack processing"
+            )
+
+        asyncio.run(
+            process(
+                args.source,
+                args.source_language,
+                args.target_language,
+                args.pipeline,
+                args.output,
+            )
         )
-    )

server/reflector/tools/process_transcript.py

@@ -0,0 +1,127 @@
+"""
+Process transcript by ID - auto-detects multitrack vs file pipeline.
+
+Usage:
+    uv run -m reflector.tools.process_transcript <transcript_id>
+
+    # Or via docker:
+    docker compose exec server uv run -m reflector.tools.process_transcript <transcript_id>
+"""
+
+import argparse
+import asyncio
+import sys
+import time
+from typing import Callable
+
+from celery.result import AsyncResult
+
+from reflector.db.transcripts import Transcript, transcripts_controller
+from reflector.services.transcript_process import (
+    FileProcessingConfig,
+    MultitrackProcessingConfig,
+    PrepareResult,
+    ProcessError,
+    ValidationError,
+    ValidationResult,
+    dispatch_transcript_processing,
+    prepare_transcript_processing,
+    validate_transcript_for_processing,
+)
+
+
+async def process_transcript_inner(
+    transcript: Transcript,
+    on_validation: Callable[[ValidationResult], None],
+    on_preprocess: Callable[[PrepareResult], None],
+) -> AsyncResult:
+    validation = await validate_transcript_for_processing(transcript)
+    on_validation(validation)
+    config = await prepare_transcript_processing(validation)
+    on_preprocess(config)
+    return dispatch_transcript_processing(config)
+
+
+async def process_transcript(transcript_id: str, sync: bool = False) -> None:
+    """
+    Process a transcript by ID, auto-detecting multitrack vs file pipeline.
+
+    Args:
+        transcript_id: The transcript UUID
+        sync: If True, wait for task completion. If False, dispatch and exit.
+    """
+    from reflector.db import get_database
+
+    database = get_database()
+    await database.connect()
+
+    try:
+        transcript = await transcripts_controller.get_by_id(transcript_id)
+        if not transcript:
+            print(f"Error: Transcript {transcript_id} not found", file=sys.stderr)
+            sys.exit(1)
+
+        print(f"Found transcript: {transcript.title or transcript_id}", file=sys.stderr)
+        print(f"  Status: {transcript.status}", file=sys.stderr)
+        print(f"  Recording ID: {transcript.recording_id or 'None'}", file=sys.stderr)
+
+        def on_validation(validation: ValidationResult) -> None:
+            if isinstance(validation, ValidationError):
+                print(f"Error: {validation.detail}", file=sys.stderr)
+                sys.exit(1)
+
+        def on_preprocess(config: PrepareResult) -> None:
+            if isinstance(config, ProcessError):
+                print(f"Error: {config.detail}", file=sys.stderr)
+                sys.exit(1)
+            elif isinstance(config, MultitrackProcessingConfig):
+                print(f"Dispatching multitrack pipeline", file=sys.stderr)
+                print(f"  Bucket: {config.bucket_name}", file=sys.stderr)
+                print(f"  Tracks: {len(config.track_keys)}", file=sys.stderr)
+            elif isinstance(config, FileProcessingConfig):
+                print(f"Dispatching file pipeline", file=sys.stderr)
+
+        result = await process_transcript_inner(
+            transcript, on_validation=on_validation, on_preprocess=on_preprocess
+        )
+
+        if sync:
+            print("Waiting for task completion...", file=sys.stderr)
+            while not result.ready():
+                print(f"  Status: {result.state}", file=sys.stderr)
+                time.sleep(5)
+
+            if result.successful():
+                print("Task completed successfully", file=sys.stderr)
+            else:
+                print(f"Task failed: {result.result}", file=sys.stderr)
+                sys.exit(1)
+        else:
+            print(
+                "Task dispatched (use --sync to wait for completion)", file=sys.stderr
+            )
+
+    finally:
+        await database.disconnect()
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Process transcript by ID - auto-detects multitrack vs file pipeline"
+    )
+    parser.add_argument(
+        "transcript_id",
+        help="Transcript UUID to process",
+    )
+    parser.add_argument(
+        "--sync",
+        action="store_true",
+        help="Wait for task completion instead of just dispatching",
+    )
+
+    args = parser.parse_args()
+    asyncio.run(process_transcript(args.transcript_id, sync=args.sync))
+
+
+if __name__ == "__main__":
+    main()

server/reflector/utils/daily.py

@@ -1,6 +1,72 @@
+import os
+import re
+from typing import NamedTuple
+
 from reflector.utils.string import NonEmptyString
 
-DailyRoomName = str
+DailyRoomName = NonEmptyString
+
+
+class DailyRecordingFilename(NamedTuple):
+    """Parsed components from Daily.co recording filename.
+
+    Format: {recording_start_ts}-{participant_id}-cam-audio-{track_start_ts}
+    Example: 1763152299562-12f0b87c-97d4-4dd3-a65c-cee1f854a79c-cam-audio-1763152314582
+
+    Note: S3 object keys have no extension, but browsers add .webm when downloading
+    from S3 UI due to MIME type headers. If you download manually and wonder.
+    """
+
+    recording_start_ts: int
+    participant_id: str
+    track_start_ts: int
+
+
+def parse_daily_recording_filename(filename: str) -> DailyRecordingFilename:
+    """Parse Daily.co recording filename to extract timestamps and participant ID.
+
+    Args:
+        filename: Full path or basename of Daily.co recording file
+                 Format: {recording_start_ts}-{participant_id}-cam-audio-{track_start_ts}
+
+    Returns:
+        DailyRecordingFilename with parsed components
+
+    Raises:
+        ValueError: If filename doesn't match expected format
+
+    Examples:
+        >>> parse_daily_recording_filename("1763152299562-12f0b87c-97d4-4dd3-a65c-cee1f854a79c-cam-audio-1763152314582")
+        DailyRecordingFilename(recording_start_ts=1763152299562, participant_id='12f0b87c-97d4-4dd3-a65c-cee1f854a79c', track_start_ts=1763152314582)
+    """
+    base = os.path.basename(filename)
+    pattern = r"(\d{13,})-([0-9a-fA-F-]{36})-cam-audio-(\d{13,})"
+    match = re.search(pattern, base)
+
+    if not match:
+        raise ValueError(
+            f"Invalid Daily.co recording filename: {filename}. "
+            f"Expected format: {{recording_start_ts}}-{{participant_id}}-cam-audio-{{track_start_ts}}"
+        )
+
+    recording_start_ts = int(match.group(1))
+    participant_id = match.group(2)
+    track_start_ts = int(match.group(3))
+
+    return DailyRecordingFilename(
+        recording_start_ts=recording_start_ts,
+        participant_id=participant_id,
+        track_start_ts=track_start_ts,
+    )
+
+
+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:

server/reflector/utils/transcript_formats.py

@@ -0,0 +1,133 @@
+"""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

server/reflector/utils/webvtt.py

@@ -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),
+            start=seconds_to_timestamp(segment.start),
-            end=_seconds_to_timestamp(segment.end),
+            end=seconds_to_timestamp(segment.end),
             text=text,
         )
         vtt.captions.append(caption)

server/reflector/video_platforms/base.py

@@ -1,10 +1,10 @@
 from abc import ABC, abstractmethod
 from datetime import datetime
-from typing import TYPE_CHECKING, Any, Dict, List, Optional
+from typing import TYPE_CHECKING, Any, Dict, Optional
 
 from ..schemas.platform import Platform
 from ..utils.string import NonEmptyString
-from .models import MeetingData, VideoPlatformConfig
+from .models import MeetingData, SessionData, VideoPlatformConfig
 
 if TYPE_CHECKING:
     from reflector.db.rooms import Room
@@ -26,11 +26,8 @@ class VideoPlatformClient(ABC):
         pass
 
     @abstractmethod
-    async def get_room_sessions(self, room_name: str) -> List[Any] | None:
+    async def get_room_sessions(self, room_name: str) -> list[SessionData]:
-        pass
+        """Get session history for a room."""
-
-    @abstractmethod
-    async def delete_room(self, room_name: str) -> bool:
         pass
 
     @abstractmethod

server/reflector/video_platforms/daily.py

@@ -1,37 +1,46 @@
-import base64
-import hmac
 from datetime import datetime
-from hashlib import sha256
-from http import HTTPStatus
-from typing import Any, Dict, List, Optional
-
-import httpx
 
+from reflector.dailyco_api import (
+    CreateMeetingTokenRequest,
+    CreateRoomRequest,
+    DailyApiClient,
+    MeetingParticipantsResponse,
+    MeetingTokenProperties,
+    RecordingResponse,
+    RecordingsBucketConfig,
+    RoomPresenceResponse,
+    RoomProperties,
+    verify_webhook_signature,
+)
+from reflector.db.daily_participant_sessions import (
+    daily_participant_sessions_controller,
+)
 from reflector.db.rooms import Room
 from reflector.logger import logger
 from reflector.storage import get_dailyco_storage
 
+from ..dailyco_api.responses import RecordingStatus
 from ..schemas.platform import Platform
 from ..utils.daily import DailyRoomName
 from ..utils.string import NonEmptyString
 from .base import ROOM_PREFIX_SEPARATOR, VideoPlatformClient
-from .models import MeetingData, RecordingType, VideoPlatformConfig
+from .models import MeetingData, RecordingType, SessionData, VideoPlatformConfig
 
 
 class DailyClient(VideoPlatformClient):
     PLATFORM_NAME: Platform = "daily"
-    TIMEOUT = 10
-    BASE_URL = "https://api.daily.co/v1"
     TIMESTAMP_FORMAT = "%Y%m%d%H%M%S"
     RECORDING_NONE: RecordingType = "none"
+    RECORDING_LOCAL: RecordingType = "local"
     RECORDING_CLOUD: RecordingType = "cloud"
 
     def __init__(self, config: VideoPlatformConfig):
         super().__init__(config)
-        self.headers = {
+        self._api_client = DailyApiClient(
-            "Authorization": f"Bearer {config.api_key}",
+            api_key=config.api_key,
-            "Content-Type": "application/json",
+            webhook_secret=config.webhook_secret,
-        }
+            timeout=10.0,
+        )
 
     async def create_meeting(
         self, room_name_prefix: NonEmptyString, end_date: datetime, room: Room
@@ -46,153 +55,150 @@ class DailyClient(VideoPlatformClient):
         timestamp = datetime.now().strftime(self.TIMESTAMP_FORMAT)
         room_name = f"{room_name_prefix}{ROOM_PREFIX_SEPARATOR}{timestamp}"
 
-        data = {
+        enable_recording = None
-            "name": room_name,
+        if room.recording_type == self.RECORDING_LOCAL:
-            "privacy": "private" if room.is_locked else "public",
+            enable_recording = "local"
-            "properties": {
+        elif room.recording_type == self.RECORDING_CLOUD:
-                "enable_recording": "raw-tracks"
+            enable_recording = "raw-tracks"
-                if room.recording_type != self.RECORDING_NONE
-                else False,
-                "enable_chat": True,
-                "enable_screenshare": True,
-                "start_video_off": False,
-                "start_audio_off": False,
-                "exp": int(end_date.timestamp()),
-            },
-        }
 
-        # Get storage config for passing to Daily API
+        properties = RoomProperties(
-        daily_storage = get_dailyco_storage()
+            enable_recording=enable_recording,
-        assert daily_storage.bucket_name, "S3 bucket must be configured"
+            enable_chat=True,
-        data["properties"]["recordings_bucket"] = {
+            enable_screenshare=True,
-            "bucket_name": daily_storage.bucket_name,
+            enable_knocking=room.is_locked,
-            "bucket_region": daily_storage.region,
+            start_video_off=False,
-            "assume_role_arn": daily_storage.role_credential,
+            start_audio_off=False,
-            "allow_api_access": True,
+            exp=int(end_date.timestamp()),
-        }
-
-        async with httpx.AsyncClient() as client:
-            response = await client.post(
-                f"{self.BASE_URL}/rooms",
-                headers=self.headers,
-                json=data,
-                timeout=self.TIMEOUT,
-            )
-            if response.status_code >= 400:
-                logger.error(
-                    "Daily.co API error",
-                    status_code=response.status_code,
-                    response_body=response.text,
-                    request_data=data,
-                )
-            response.raise_for_status()
-            result = response.json()
-
-        room_url = result["url"]
-
-        return MeetingData(
-            meeting_id=result["id"],
-            room_name=result["name"],
-            room_url=room_url,
-            host_room_url=room_url,
-            platform=self.PLATFORM_NAME,
-            extra_data=result,
         )
 
-    async def get_room_sessions(self, room_name: str) -> List[Any] | None:
+        if room.recording_type == self.RECORDING_CLOUD:
-        # no such api
+            daily_storage = get_dailyco_storage()
-        return None
+            assert daily_storage.bucket_name, "S3 bucket must be configured"
-
+            properties.recordings_bucket = RecordingsBucketConfig(
-    async def get_room_presence(self, room_name: str) -> Dict[str, Any]:
+                bucket_name=daily_storage.bucket_name,
-        async with httpx.AsyncClient() as client:
+                bucket_region=daily_storage.region,
-            response = await client.get(
+                assume_role_arn=daily_storage.role_credential,
-                f"{self.BASE_URL}/rooms/{room_name}/presence",
+                allow_api_access=True,
-                headers=self.headers,
-                timeout=self.TIMEOUT,
             )
-            response.raise_for_status()
-            return response.json()
 
-    async def get_meeting_participants(self, meeting_id: str) -> Dict[str, Any]:
+        request = CreateRoomRequest(
-        async with httpx.AsyncClient() as client:
+            name=room_name,
-            response = await client.get(
+            privacy="private" if room.is_locked else "public",
-                f"{self.BASE_URL}/meetings/{meeting_id}/participants",
+            properties=properties,
-                headers=self.headers,
+        )
-                timeout=self.TIMEOUT,
-            )
-            response.raise_for_status()
-            return response.json()
 
-    async def get_recording(self, recording_id: str) -> Dict[str, Any]:
+        result = await self._api_client.create_room(request)
-        async with httpx.AsyncClient() as client:
-            response = await client.get(
-                f"{self.BASE_URL}/recordings/{recording_id}",
-                headers=self.headers,
-                timeout=self.TIMEOUT,
-            )
-            response.raise_for_status()
-            return response.json()
 
-    async def delete_room(self, room_name: str) -> bool:
+        return MeetingData(
-        async with httpx.AsyncClient() as client:
+            meeting_id=result.id,
-            response = await client.delete(
+            room_name=result.name,
-                f"{self.BASE_URL}/rooms/{room_name}",
+            room_url=result.url,
-                headers=self.headers,
+            host_room_url=result.url,
-                timeout=self.TIMEOUT,
+            platform=self.PLATFORM_NAME,
+            extra_data=result.model_dump(),
+        )
+
+    async def get_room_sessions(self, room_name: str) -> list[SessionData]:
+        """Get room session history from database (webhook-stored sessions).
+
+        Daily.co doesn't provide historical session API, so we query our database
+        where participant.joined/left webhooks are stored.
+        """
+        from reflector.db.meetings import meetings_controller  # noqa: PLC0415
+
+        meeting = await meetings_controller.get_by_room_name(room_name)
+        if not meeting:
+            return []
+
+        sessions = await daily_participant_sessions_controller.get_by_meeting(
+            meeting.id
+        )
+
+        return [
+            SessionData(
+                session_id=s.id,
+                started_at=s.joined_at,
+                ended_at=s.left_at,
             )
-            return response.status_code in (HTTPStatus.OK, HTTPStatus.NOT_FOUND)
+            for s in sessions
+        ]
+
+    async def get_room_presence(self, room_name: str) -> RoomPresenceResponse:
+        """Get room presence/session data for a Daily.co room."""
+        return await self._api_client.get_room_presence(room_name)
+
+    async def get_meeting_participants(
+        self, meeting_id: str
+    ) -> MeetingParticipantsResponse:
+        """Get participant data for a specific Daily.co meeting."""
+        return await self._api_client.get_meeting_participants(meeting_id)
+
+    async def get_recording(self, recording_id: str) -> RecordingResponse:
+        return await self._api_client.get_recording(recording_id)
+
+    async def list_recordings(
+        self,
+        room_name: NonEmptyString | None = None,
+        starting_after: str | None = None,
+        ending_before: str | None = None,
+        limit: int = 100,
+    ) -> list[RecordingResponse]:
+        return await self._api_client.list_recordings(
+            room_name=room_name,
+            starting_after=starting_after,
+            ending_before=ending_before,
+            limit=limit,
+        )
+
+    async def get_recording_status(
+        self, recording_id: NonEmptyString
+    ) -> RecordingStatus:
+        recording = await self.get_recording(recording_id)
+        return recording.status
 
     async def upload_logo(self, room_name: str, logo_path: str) -> bool:
         return True
 
     def verify_webhook_signature(
-        self, body: bytes, signature: str, timestamp: Optional[str] = None
+        self, body: bytes, signature: str, timestamp: str | None = None
     ) -> bool:
-        """Verify Daily.co webhook signature.
+        """Verify Daily.co webhook signature using dailyco_api module."""
-
+        if not self.config.webhook_secret:
-        Daily.co uses:
+            logger.warning("Webhook secret not configured")
-        - X-Webhook-Signature header
-        - X-Webhook-Timestamp header
-        - Signature format: HMAC-SHA256(base64_decode(secret), timestamp + '.' + body)
-        - Result is base64 encoded
-        """
-        if not signature or not timestamp:
             return False
 
-        try:
+        return verify_webhook_signature(
-            secret_bytes = base64.b64decode(self.config.webhook_secret)
+            body=body,
-
+            signature=signature,
-            signed_content = timestamp.encode() + b"." + body
+            timestamp=timestamp or "",
-
+            webhook_secret=self.config.webhook_secret,
-            expected = hmac.new(secret_bytes, signed_content, sha256).digest()
+        )
-            expected_b64 = base64.b64encode(expected).decode()
-
-            return hmac.compare_digest(expected_b64, signature)
-        except Exception as e:
-            logger.error("Daily.co webhook signature verification failed", exc_info=e)
-            return False
 
     async def create_meeting_token(
         self,
         room_name: DailyRoomName,
-        enable_recording: bool,
+        start_cloud_recording: bool,
-        user_id: Optional[str] = None,
+        enable_recording_ui: bool,
-    ) -> str:
+        user_id: NonEmptyString | None = None,
-        data = {"properties": {"room_name": room_name}}
+        is_owner: bool = False,
+    ) -> NonEmptyString:
+        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,
+        )
+        request = CreateMeetingTokenRequest(properties=properties)
+        result = await self._api_client.create_meeting_token(request)
+        return result.token
 
-        if enable_recording:
+    async def close(self):
-            data["properties"]["start_cloud_recording"] = True
+        """Clean up API client resources."""
-            data["properties"]["enable_recording_ui"] = False
+        await self._api_client.close()
 
-        if user_id:
+    async def __aenter__(self):
-            data["properties"]["user_id"] = user_id
+        return self
 
-        async with httpx.AsyncClient() as client:
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
-            response = await client.post(
+        await self.close()
-                f"{self.BASE_URL}/meeting-tokens",
-                headers=self.headers,
-                json=data,
-                timeout=self.TIMEOUT,
-            )
-            response.raise_for_status()
-            return response.json()["token"]

server/reflector/video_platforms/factory.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from reflector.settings import settings
 from reflector.storage import get_dailyco_storage, get_whereby_storage
 
@@ -53,10 +51,3 @@ def get_platform_config(platform: Platform) -> VideoPlatformConfig:
 def create_platform_client(platform: Platform) -> VideoPlatformClient:
     config = get_platform_config(platform)
     return get_platform_client(platform, config)
-
-
-def get_platform(room_platform: Optional[Platform] = None) -> Platform:
-    if room_platform:
-        return room_platform
-
-    return settings.DEFAULT_VIDEO_PLATFORM

server/reflector/video_platforms/models.py

@@ -1,18 +1,38 @@
+from datetime import datetime
 from typing import Any, Dict, Literal, Optional
 
 from pydantic import BaseModel, Field
 
 from reflector.schemas.platform import WHEREBY_PLATFORM, Platform
+from reflector.utils.string import NonEmptyString
 
 RecordingType = Literal["none", "local", "cloud"]
 
 
+class SessionData(BaseModel):
+    """Platform-agnostic session data.
+
+    Represents a participant session in a meeting room, regardless of platform.
+    Used to determine if a meeting is still active or has ended.
+    """
+
+    session_id: NonEmptyString = Field(description="Unique session identifier")
+    started_at: datetime = Field(description="When session started (UTC)")
+    ended_at: datetime | None = Field(
+        description="When session ended (UTC), None if still active"
+    )
+
+
 class MeetingData(BaseModel):
     platform: Platform
-    meeting_id: str = Field(description="Platform-specific meeting identifier")
+    meeting_id: NonEmptyString = Field(
-    room_url: str = Field(description="URL for participants to join")
+        description="Platform-specific meeting identifier"
-    host_room_url: str = Field(description="URL for hosts (may be same as room_url)")
+    )
-    room_name: str = Field(description="Human-readable room name")
+    room_url: NonEmptyString = Field(description="URL for participants to join")
+    host_room_url: NonEmptyString = Field(
+        description="URL for hosts (may be same as room_url)"
+    )
+    room_name: NonEmptyString = Field(description="Human-readable room name")
     extra_data: Dict[str, Any] = Field(default_factory=dict)
 
     class Config:

server/reflector/video_platforms/whereby.py

@@ -4,7 +4,7 @@ import re
 import time
 from datetime import datetime
 from hashlib import sha256
-from typing import Any, Dict, Optional
+from typing import Optional
 
 import httpx
 
@@ -13,11 +13,8 @@ from reflector.storage import get_whereby_storage
 
 from ..schemas.platform import WHEREBY_PLATFORM, Platform
 from ..utils.string import NonEmptyString
-from .base import (
+from .base import VideoPlatformClient
-    MeetingData,
+from .models import MeetingData, SessionData, VideoPlatformConfig
-    VideoPlatformClient,
-    VideoPlatformConfig,
-)
 from .whereby_utils import whereby_room_name_prefix
 
 
@@ -80,18 +77,50 @@ class WherebyClient(VideoPlatformClient):
             extra_data=result,
         )
 
-    async def get_room_sessions(self, room_name: str) -> Dict[str, Any]:
+    async def get_room_sessions(self, room_name: str) -> list[SessionData]:
+        """Get room session history from Whereby API.
+
+        Whereby API returns: [{"sessionId": "...", "startedAt": "...", "endedAt": "..." | null}, ...]
+        """
         async with httpx.AsyncClient() as client:
+            """
+                        {
+              "cursor": "text",
+              "results": [
+                {
+                  "roomSessionId": "e2f29530-46ec-4cee-8b27-e565cb5bb2e9",
+                  "roomName": "/room-prefix-793e9ec1-c686-423d-9043-9b7a10c553fd",
+                  "startedAt": "2025-01-01T00:00:00.000Z",
+                  "endedAt": "2025-01-01T01:00:00.000Z",
+                  "totalParticipantMinutes": 124,
+                  "totalRecorderMinutes": 120,
+                  "totalStreamerMinutes": 120,
+                  "totalUniqueParticipants": 4,
+                  "totalUniqueRecorders": 3,
+                  "totalUniqueStreamers": 2
+                }
+              ]
+            }"""
             response = await client.get(
                 f"{self.config.api_url}/insights/room-sessions?roomName={room_name}",
                 headers=self.headers,
                 timeout=self.TIMEOUT,
             )
             response.raise_for_status()
-            return response.json().get("results", [])
+            results = response.json().get("results", [])
 
-    async def delete_room(self, room_name: str) -> bool:
+            return [
-        return True
+                SessionData(
+                    session_id=s["roomSessionId"],
+                    started_at=datetime.fromisoformat(
+                        s["startedAt"].replace("Z", "+00:00")
+                    ),
+                    ended_at=datetime.fromisoformat(s["endedAt"].replace("Z", "+00:00"))
+                    if s.get("endedAt")
+                    else None,
+                )
+                for s in results
+            ]
 
     async def upload_logo(self, room_name: str, logo_path: str) -> bool:
         async with httpx.AsyncClient() as client:

server/reflector/views/daily.py

@@ -1,49 +1,53 @@
 import json
-from typing import Any, Dict, Literal
+from typing import assert_never
 
 from fastapi import APIRouter, HTTPException, Request
-from pydantic import BaseModel
+from pydantic import TypeAdapter
 
+from reflector.dailyco_api import (
+    DailyWebhookEventUnion,
+    ParticipantJoinedEvent,
+    ParticipantLeftEvent,
+    RecordingErrorEvent,
+    RecordingReadyEvent,
+    RecordingStartedEvent,
+)
 from reflector.db.meetings import meetings_controller
 from reflector.logger import logger as _logger
 from reflector.settings import settings
-from reflector.utils.daily import DailyRoomName
 from reflector.video_platforms.factory import create_platform_client
-from reflector.worker.process import process_multitrack_recording
+from reflector.worker.process import (
+    poll_daily_room_presence_task,
+    process_multitrack_recording,
+)
 
 router = APIRouter()
 
 logger = _logger.bind(platform="daily")
 
 
-class DailyTrack(BaseModel):
-    type: Literal["audio", "video"]
-    s3Key: str
-    size: int
-
-
-class DailyWebhookEvent(BaseModel):
-    version: str
-    type: str
-    id: str
-    payload: Dict[str, Any]
-    event_ts: float
-
-
-def _extract_room_name(event: DailyWebhookEvent) -> DailyRoomName | None:
-    """Extract room name from Daily event payload.
-
-    Daily.co API inconsistency:
-    - participant.* events use "room" field
-    - recording.* events use "room_name" field
-    """
-    return event.payload.get("room_name") or event.payload.get("room")
-
-
 @router.post("/webhook")
 async def webhook(request: Request):
     """Handle Daily webhook events.
 
+    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
     """
@@ -53,18 +57,14 @@ async def webhook(request: Request):
 
     client = create_platform_client("daily")
 
-    # TEMPORARY: Bypass signature check for testing
+    if not client.verify_webhook_signature(body, signature, timestamp):
-    # TODO: Remove this after testing is complete
+        logger.warning(
-    BYPASS_FOR_TESTING = True
+            "Invalid webhook signature",
-    if not BYPASS_FOR_TESTING:
+            signature=signature,
-        if not client.verify_webhook_signature(body, signature, timestamp):
+            timestamp=timestamp,
-            logger.warning(
+            has_body=bool(body),
-                "Invalid webhook signature",
+        )
-                signature=signature,
+        raise HTTPException(status_code=401, detail="Invalid webhook signature")
-                timestamp=timestamp,
-                has_body=bool(body),
-            )
-            raise HTTPException(status_code=401, detail="Invalid webhook signature")
 
     try:
         body_json = json.loads(body)
@@ -75,68 +75,83 @@ async def webhook(request: Request):
         logger.info("Received Daily webhook test event")
         return {"status": "ok"}
 
-    # Parse as actual event
+    event_adapter = TypeAdapter(DailyWebhookEventUnion)
     try:
-        event = DailyWebhookEvent(**body_json)
+        event = event_adapter.validate_python(body_json)
     except Exception as e:
         logger.error("Failed to parse webhook event", error=str(e), body=body.decode())
         raise HTTPException(status_code=422, detail="Invalid event format")
 
-    # Handle participant events
+    match event:
-    if event.type == "participant.joined":
+        case ParticipantJoinedEvent():
-        await _handle_participant_joined(event)
+            await _handle_participant_joined(event)
-    elif event.type == "participant.left":
+        case ParticipantLeftEvent():
-        await _handle_participant_left(event)
+            await _handle_participant_left(event)
-    elif event.type == "recording.started":
+        case RecordingStartedEvent():
-        await _handle_recording_started(event)
+            await _handle_recording_started(event)
-    elif event.type == "recording.ready-to-download":
+        case RecordingReadyEvent():
-        await _handle_recording_ready(event)
+            await _handle_recording_ready(event)
-    elif event.type == "recording.error":
+        case RecordingErrorEvent():
-        await _handle_recording_error(event)
+            await _handle_recording_error(event)
-    else:
+        case _:
-        logger.warning(
+            assert_never(event)
-            "Unhandled Daily webhook event type",
-            event_type=event.type,
-            payload=event.payload,
-        )
 
     return {"status": "ok"}
 
 
-async def _handle_participant_joined(event: DailyWebhookEvent):
+async def _queue_poll_for_room(
-    daily_room_name = _extract_room_name(event)
+    room_name: str | None,
-    if not daily_room_name:
+    event_type: str,
-        logger.warning("participant.joined: no room in payload", payload=event.payload)
+    user_id: str | None,
-        return
+    session_id: str | None,
-
+    **log_kwargs,
-    meeting = await meetings_controller.get_by_room_name(daily_room_name)
+) -> None:
-    if meeting:
+    """Queue poll task for room by name, handling missing room/meeting cases."""
-        await meetings_controller.increment_num_clients(meeting.id)
-        logger.info(
-            "Participant joined",
-            meeting_id=meeting.id,
-            room_name=daily_room_name,
-            recording_type=meeting.recording_type,
-            recording_trigger=meeting.recording_trigger,
-        )
-    else:
-        logger.warning(
-            "participant.joined: meeting not found", room_name=daily_room_name
-        )
-
-
-async def _handle_participant_left(event: DailyWebhookEvent):
-    room_name = _extract_room_name(event)
     if not room_name:
+        logger.warning(f"{event_type}: no room in payload")
         return
 
     meeting = await meetings_controller.get_by_room_name(room_name)
-    if meeting:
+    if not meeting:
-        await meetings_controller.decrement_num_clients(meeting.id)
+        logger.warning(f"{event_type}: meeting not found", room_name=room_name)
+        return
+
+    poll_daily_room_presence_task.delay(meeting.id)
+
+    logger.info(
+        f"{event_type.replace('.', ' ').title()} - poll queued",
+        meeting_id=meeting.id,
+        room_name=room_name,
+        user_id=user_id,
+        session_id=session_id,
+        **log_kwargs,
+    )
 
 
-async def _handle_recording_started(event: DailyWebhookEvent):
+async def _handle_participant_joined(event: ParticipantJoinedEvent):
-    room_name = _extract_room_name(event)
+    """Queue poll task for presence reconciliation."""
+    await _queue_poll_for_room(
+        event.payload.room_name,
+        "participant.joined",
+        event.payload.user_id,
+        event.payload.session_id,
+        user_name=event.payload.user_name,
+    )
+
+
+async def _handle_participant_left(event: ParticipantLeftEvent):
+    """Queue poll task for presence reconciliation."""
+    await _queue_poll_for_room(
+        event.payload.room_name,
+        "participant.left",
+        event.payload.user_id,
+        event.payload.session_id,
+        duration=event.payload.duration,
+    )
+
+
+async def _handle_recording_started(event: RecordingStartedEvent):
+    room_name = event.payload.room_name
     if not room_name:
         logger.warning(
             "recording.started: no room_name in payload", payload=event.payload
@@ -149,49 +164,27 @@ async def _handle_recording_started(event: DailyWebhookEvent):
             "Recording started",
             meeting_id=meeting.id,
             room_name=room_name,
-            recording_id=event.payload.get("recording_id"),
+            recording_id=event.payload.recording_id,
             platform="daily",
         )
     else:
         logger.warning("recording.started: meeting not found", room_name=room_name)
 
 
-async def _handle_recording_ready(event: DailyWebhookEvent):
+async def _handle_recording_ready(event: RecordingReadyEvent):
-    """Handle recording ready for download event.
+    room_name = event.payload.room_name
+    recording_id = event.payload.recording_id
+    tracks = event.payload.tracks
 
-    Daily.co webhook payload for raw-tracks recordings:
+    if not tracks:
-    {
-      "recording_id": "...",
-      "room_name": "test2-20251009192341",
-      "tracks": [
-        {"type": "audio", "s3Key": "monadical/test2-.../uuid-cam-audio-123.webm", "size": 400000},
-        {"type": "video", "s3Key": "monadical/test2-.../uuid-cam-video-456.webm", "size": 30000000}
-      ]
-    }
-    """
-    room_name = _extract_room_name(event)
-    recording_id = event.payload.get("recording_id")
-    tracks_raw = event.payload.get("tracks", [])
-
-    if not room_name or not tracks_raw:
         logger.warning(
-            "recording.ready-to-download: missing room_name or tracks",
+            "recording.ready-to-download: missing tracks",
             room_name=room_name,
-            has_tracks=bool(tracks_raw),
+            recording_id=recording_id,
             payload=event.payload,
         )
         return
 
-    try:
-        tracks = [DailyTrack(**t) for t in tracks_raw]
-    except Exception as e:
-        logger.error(
-            "recording.ready-to-download: invalid tracks structure",
-            error=str(e),
-            tracks=tracks_raw,
-        )
-        return
-
     logger.info(
         "Recording ready for download",
         room_name=room_name,
@@ -209,6 +202,12 @@ async def _handle_recording_ready(event: DailyWebhookEvent):
 
     track_keys = [t.s3Key for t in tracks if t.type == "audio"]
 
+    logger.info(
+        "Recording webhook queuing processing",
+        recording_id=recording_id,
+        room_name=room_name,
+    )
+
     process_multitrack_recording.delay(
         bucket_name=bucket_name,
         daily_room_name=room_name,
@@ -217,17 +216,18 @@ async def _handle_recording_ready(event: DailyWebhookEvent):
     )
 
 
-async def _handle_recording_error(event: DailyWebhookEvent):
+async def _handle_recording_error(event: RecordingErrorEvent):
-    room_name = _extract_room_name(event)
+    payload = event.payload
-    error = event.payload.get("error", "Unknown error")
+    room_name = payload.room_name
 
-    if room_name:
+    meeting = await meetings_controller.get_by_room_name(room_name)
-        meeting = await meetings_controller.get_by_room_name(room_name)
+    if meeting:
-        if meeting:
+        logger.error(
-            logger.error(
+            "Recording error",
-                "Recording error",
+            meeting_id=meeting.id,
-                meeting_id=meeting.id,
+            room_name=room_name,
-                room_name=room_name,
+            error=payload.error_msg,
-                error=error,
+            platform="daily",
-                platform="daily",
+        )
-            )
+    else:
+        logger.warning("recording.error: meeting not found", room_name=room_name)

server/reflector/views/rooms.py

@@ -19,10 +19,7 @@ from reflector.schemas.platform import Platform
 from reflector.services.ics_sync import ics_sync_service
 from reflector.settings import settings
 from reflector.utils.url import add_query_param
-from reflector.video_platforms.factory import (
+from reflector.video_platforms.factory import create_platform_client
-    create_platform_client,
-    get_platform,
-)
 from reflector.worker.webhook import test_webhook
 
 logger = logging.getLogger(__name__)
@@ -47,6 +44,7 @@ class Room(BaseModel):
     ics_last_sync: Optional[datetime] = None
     ics_last_etag: Optional[str] = None
     platform: Platform
+    skip_consent: bool = False
 
 
 class RoomDetails(Room):
@@ -92,7 +90,8 @@ class CreateRoom(BaseModel):
     ics_url: Optional[str] = None
     ics_fetch_interval: int = 300
     ics_enabled: bool = False
-    platform: Optional[Platform] = None
+    platform: Platform
+    skip_consent: bool = False
 
 
 class UpdateRoom(BaseModel):
@@ -111,6 +110,7 @@ class UpdateRoom(BaseModel):
     ics_fetch_interval: Optional[int] = None
     ics_enabled: Optional[bool] = None
     platform: Optional[Platform] = None
+    skip_consent: Optional[bool] = None
 
 
 class CreateRoomMeeting(BaseModel):
@@ -190,9 +190,6 @@ async def rooms_list(
         ),
     )
 
-    for room in paginated.items:
-        room.platform = get_platform(room.platform)
-
     return paginated
 
 
@@ -207,7 +204,6 @@ async def rooms_get(
         raise HTTPException(status_code=404, detail="Room not found")
     if not room.is_shared and (user_id is None or room.user_id != user_id):
         raise HTTPException(status_code=403, detail="Room access denied")
-    room.platform = get_platform(room.platform)
     return room
 
 
@@ -229,8 +225,6 @@ async def rooms_get_by_name(
         room_dict["webhook_url"] = None
         room_dict["webhook_secret"] = None
 
-    room_dict["platform"] = get_platform(room.platform)
-
     return RoomDetails(**room_dict)
 
 
@@ -258,6 +252,7 @@ async def rooms_create(
         ics_fetch_interval=room.ics_fetch_interval,
         ics_enabled=room.ics_enabled,
         platform=room.platform,
+        skip_consent=room.skip_consent,
     )
 
 
@@ -275,7 +270,6 @@ async def rooms_update(
         raise HTTPException(status_code=403, detail="Not authorized")
     values = info.dict(exclude_unset=True)
     await rooms_controller.update(room, values)
-    room.platform = get_platform(room.platform)
     return room
 
 
@@ -320,10 +314,26 @@ 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)
 
-                platform = get_platform(room.platform)
+                platform = room.platform
                 client = create_platform_client(platform)
 
                 meeting_data = await client.create_meeting(
@@ -347,19 +357,7 @@ async def rooms_create_meeting(
             status_code=503, detail="Meeting creation in progress, please try again"
         )
 
-    if meeting.platform == "daily" and room.recording_trigger != "none":
+    if user_id != room.user_id and meeting.platform == "whereby":
-        client = create_platform_client(meeting.platform)
-        token = await client.create_meeting_token(
-            meeting.room_name,
-            enable_recording=True,
-            user_id=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:
         meeting.host_room_url = ""
 
     return meeting
@@ -513,13 +511,13 @@ async def rooms_list_active_meetings(
         room=room, current_time=current_time
     )
 
-    effective_platform = get_platform(room.platform)
     for meeting in meetings:
-        meeting.platform = effective_platform
+        meeting.platform = room.platform
 
     if user_id != room.user_id:
         for meeting in meetings:
-            meeting.host_room_url = ""
+            if meeting.platform == "whereby":
+                meeting.host_room_url = ""
 
     return meetings
 
@@ -541,7 +539,7 @@ async def rooms_get_meeting(
     if not meeting:
         raise HTTPException(status_code=404, detail="Meeting not found")
 
-    if user_id != room.user_id and not room.is_shared:
+    if user_id != room.user_id and not room.is_shared and meeting.platform == "whereby":
         meeting.host_room_url = ""
 
     return meeting
@@ -571,7 +569,23 @@ async def rooms_join_meeting(
     if meeting.end_date <= current_time:
         raise HTTPException(status_code=400, detail="Meeting has ended")
 
-    if user_id != room.user_id:
+    if meeting.platform == "daily" and user_id is not None:
-        meeting.host_room_url = ""
+        client = create_platform_client(meeting.platform)
+        # Show Daily's built-in recording UI when:
+        # - local recording (user controls when to record), OR
+        # - cloud recording with consent disabled (skip_consent=True)
+        # Hide it when cloud recording with consent enabled (we show custom consent UI)
+        enable_recording_ui = meeting.recording_type == "local" or (
+            meeting.recording_type == "cloud" and room.skip_consent
+        )
+        token = await client.create_meeting_token(
+            meeting.room_name,
+            start_cloud_recording=meeting.recording_type == "cloud",
+            enable_recording_ui=enable_recording_ui,
+            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)
 
     return meeting

server/reflector/views/transcripts.py

@@ -1,14 +1,23 @@
 from datetime import datetime, timedelta, timezone
-from typing import Annotated, Literal, Optional
+from typing import Annotated, Literal, Optional, assert_never
 
 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, Field, constr, field_serializer
+from pydantic import (
+    AwareDatetime,
+    BaseModel,
+    Discriminator,
+    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,
@@ -29,9 +38,17 @@ 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,
@@ -46,6 +63,14 @@ 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
@@ -88,8 +113,86 @@ class GetTranscriptMinimal(BaseModel):
     audio_deleted: bool | None = None
 
 
-class GetTranscript(GetTranscriptMinimal):
+class TranscriptParticipantWithEmail(TranscriptParticipant):
-    participants: list[TranscriptParticipant] | None
+    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 CreateTranscript(BaseModel):
@@ -228,7 +331,7 @@ async def transcripts_search(
     )
 
 
-@router.post("/transcripts", response_model=GetTranscript)
+@router.post("/transcripts", response_model=GetTranscriptWithParticipants)
 async def transcripts_create(
     info: CreateTranscript,
     user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
@@ -272,7 +375,7 @@ class GetTranscriptTopic(BaseModel):
     segments: list[GetTranscriptSegmentTopic] = []
 
     @classmethod
-    def from_transcript_topic(cls, topic: TranscriptTopic):
+    def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
         if not topic.words:
             # In previous version, words were missing
             # Just output a segment with speaker 0
@@ -296,7 +399,7 @@ class GetTranscriptTopic(BaseModel):
                     start=segment.start,
                     speaker=segment.speaker,
                 )
-                for segment in transcript.as_segments()
+                for segment in transcript.as_segments(is_multitrack)
             ]
         return cls(
             id=topic.id,
@@ -313,8 +416,8 @@ class GetTranscriptTopicWithWords(GetTranscriptTopic):
     words: list[Word] = []
 
     @classmethod
-    def from_transcript_topic(cls, topic: TranscriptTopic):
+    def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
-        instance = super().from_transcript_topic(topic)
+        instance = super().from_transcript_topic(topic, is_multitrack)
         if topic.words:
             instance.words = topic.words
         return instance
@@ -329,8 +432,8 @@ class GetTranscriptTopicWithWordsPerSpeaker(GetTranscriptTopic):
     words_per_speaker: list[SpeakerWords] = []
 
     @classmethod
-    def from_transcript_topic(cls, topic: TranscriptTopic):
+    def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
-        instance = super().from_transcript_topic(topic)
+        instance = super().from_transcript_topic(topic, is_multitrack)
         if topic.words:
             words_per_speakers = []
             # group words by speaker
@@ -362,14 +465,95 @@ 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
-    return await transcripts_controller.get_by_id_for_http(
+    transcript = await transcripts_controller.get_by_id_for_http(
         transcript_id, user_id=user_id
     )
 
+    is_multitrack = await _get_is_multitrack(transcript)
 
-@router.patch("/transcripts/{transcript_id}", response_model=GetTranscript)
+    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
+)
 async def transcript_update(
     transcript_id: str,
     info: UpdateTranscript,
@@ -419,9 +603,12 @@ 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) for topic in transcript.topics
+        GetTranscriptTopic.from_transcript_topic(topic, is_multitrack)
+        for topic in transcript.topics
     ]
 
 
@@ -438,9 +625,11 @@ 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)
+        GetTranscriptTopicWithWords.from_transcript_topic(topic, is_multitrack)
         for topic in transcript.topics
     ]
 
@@ -459,13 +648,17 @@ 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)
+    return GetTranscriptTopicWithWordsPerSpeaker.from_transcript_topic(
+        topic, is_multitrack
+    )
 
 
 @router.post("/transcripts/{transcript_id}/zulip")

server/reflector/views/transcripts_process.py

@@ -1,15 +1,19 @@
-from typing import Annotated, Optional
+from typing import Annotated, Optional, assert_never
 
-import celery
 from fastapi import APIRouter, Depends, HTTPException
 from pydantic import BaseModel
 
 import reflector.auth as auth
-from reflector.db.recordings import recordings_controller
 from reflector.db.transcripts import transcripts_controller
-from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
+from reflector.services.transcript_process import (
-from reflector.pipelines.main_multitrack_pipeline import (
+    ProcessError,
-    task_pipeline_multitrack_process,
+    ValidationAlreadyScheduled,
+    ValidationError,
+    ValidationLocked,
+    ValidationOk,
+    dispatch_transcript_processing,
+    prepare_transcript_processing,
+    validate_transcript_for_processing,
 )
 
 router = APIRouter()
@@ -23,59 +27,28 @@ class ProcessStatus(BaseModel):
 async def transcript_process(
     transcript_id: str,
     user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
-):
+) -> ProcessStatus:
     user_id = user["sub"] if user else None
     transcript = await transcripts_controller.get_by_id_for_http(
         transcript_id, user_id=user_id
     )
 
-    if transcript.locked:
+    validation = await validate_transcript_for_processing(transcript)
-        raise HTTPException(status_code=400, detail="Transcript is locked")
+    if isinstance(validation, ValidationLocked):
-
+        raise HTTPException(status_code=400, detail=validation.detail)
-    if transcript.status == "idle":
+    elif isinstance(validation, ValidationError):
-        raise HTTPException(
+        raise HTTPException(status_code=400, detail=validation.detail)
-            status_code=400, detail="Recording is not ready for processing"
+    elif isinstance(validation, ValidationAlreadyScheduled):
-        )
+        return ProcessStatus(status=validation.detail)
-
+    elif isinstance(validation, ValidationOk):
-    # avoid duplicate scheduling for either pipeline
+        pass
-    if task_is_scheduled_or_active(
-        "reflector.pipelines.main_file_pipeline.task_pipeline_file_process",
-        transcript_id=transcript_id,
-    ) or task_is_scheduled_or_active(
-        "reflector.pipelines.main_multitrack_pipeline.task_pipeline_multitrack_process",
-        transcript_id=transcript_id,
-    ):
-        return ProcessStatus(status="already running")
-
-    # Determine processing mode strictly from DB to avoid S3 scans
-    bucket_name = None
-    track_keys: list[str] = []
-
-    if transcript.recording_id:
-        recording = await recordings_controller.get_by_id(transcript.recording_id)
-        if recording:
-            bucket_name = recording.bucket_name
-            track_keys = list(getattr(recording, "track_keys", []) or [])
-
-    if bucket_name:
-        task_pipeline_multitrack_process.delay(
-            transcript_id=transcript_id,
-            bucket_name=bucket_name,
-            track_keys=track_keys,
-        )
     else:
-        # Default single-file pipeline
+        assert_never(validation)
-        task_pipeline_file_process.delay(transcript_id=transcript_id)
 
-    return ProcessStatus(status="ok")
+    config = await prepare_transcript_processing(validation)
 
-
+    if isinstance(config, ProcessError):
-def task_is_scheduled_or_active(task_name: str, **kwargs):
+        raise HTTPException(status_code=500, detail=config.detail)
-    inspect = celery.current_app.control.inspect()
+    else:
-
+        dispatch_transcript_processing(config)
-    for worker, tasks in (inspect.scheduled() | inspect.active()).items():
+        return ProcessStatus(status="ok")
-        for task in tasks:
-            if task["name"] == task_name and task["kwargs"] == kwargs:
-                return True
-
-    return False

server/reflector/views/user_websocket.py

@@ -3,6 +3,7 @@ from typing import Optional
 from fastapi import APIRouter, WebSocket
 
 from reflector.auth.auth_jwt import JWTAuth  # type: ignore
+from reflector.db.users import user_controller
 from reflector.ws_manager import get_ws_manager
 
 router = APIRouter()
@@ -29,7 +30,18 @@ async def user_events_websocket(websocket: WebSocket):
 
     try:
         payload = JWTAuth().verify_token(token)
-        user_id = payload.get("sub")
+        authentik_uid = payload.get("sub")
+
+        if authentik_uid:
+            user = await user_controller.get_by_authentik_uid(authentik_uid)
+            if user:
+                user_id = user.id
+            else:
+                await websocket.close(code=UNAUTHORISED)
+                return
+        else:
+            await websocket.close(code=UNAUTHORISED)
+            return
     except Exception:
         await websocket.close(code=UNAUTHORISED)
         return

server/reflector/worker/app.py

@@ -38,6 +38,18 @@ 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)
+        },
+        "trigger_daily_reconciliation": {
+            "task": "reflector.worker.process.trigger_daily_reconciliation",
+            "schedule": 30.0,  # Every 30 seconds (queues poll tasks for all active meetings)
+        },
         "sync_all_ics_calendars": {
             "task": "reflector.worker.ics_sync.sync_all_ics_calendars",
             "schedule": 60.0,  # Run every minute to check which rooms need sync

server/reflector/worker/healthcheck.py

@@ -7,6 +7,12 @@ from reflector.settings import settings
 logger = structlog.get_logger(__name__)
 
 
+@shared_task(name="celery.ping")
+def celery_ping():
+    """Compatibility task for Celery 5.x - celery.ping was removed but monitoring tools still call it."""
+    return "pong"
+
+
 @shared_task
 def healthcheck_ping():
     url = settings.HEALTHCHECK_URL

server/reflector/worker/ics_sync.py

@@ -10,7 +10,7 @@ from reflector.db.meetings import meetings_controller
 from reflector.db.rooms import Room, rooms_controller
 from reflector.redis_cache import RedisAsyncLock
 from reflector.services.ics_sync import SyncStatus, ics_sync_service
-from reflector.video_platforms.factory import create_platform_client, get_platform
+from reflector.video_platforms.factory import create_platform_client
 
 logger = structlog.wrap_logger(get_task_logger(__name__))
 
@@ -104,10 +104,10 @@ async def create_upcoming_meetings_for_event(event, create_window, room: Room):
     try:
         end_date = event.end_time or (event.start_time + MEETING_DEFAULT_DURATION)
 
-        client = create_platform_client(get_platform(room.platform))
+        client = create_platform_client(room.platform)
 
         meeting_data = await client.create_meeting(
-            "",
+            room.name,
             end_date=end_date,
             room=room,
         )

server/reflector/worker/process.py

@@ -2,6 +2,7 @@ import json
 import os
 import re
 from datetime import datetime, timezone
+from typing import List
 from urllib.parse import unquote
 
 import av
@@ -10,14 +11,17 @@ import structlog
 from celery import shared_task
 from celery.utils.log import get_task_logger
 from pydantic import ValidationError
-from redis.exceptions import LockError
 
+from reflector.dailyco_api import FinishedRecordingResponse, RecordingResponse
+from reflector.db.daily_participant_sessions import (
+    DailyParticipantSession,
+    daily_participant_sessions_controller,
+)
 from reflector.db.meetings import meetings_controller
 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
@@ -28,10 +32,15 @@ from reflector.pipelines.main_multitrack_pipeline import (
 from reflector.pipelines.topic_processing import EmptyPipeline
 from reflector.processors import AudioFileWriterProcessor
 from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
-from reflector.redis_cache import get_redis_client
+from reflector.redis_cache import RedisAsyncLock
 from reflector.settings import settings
 from reflector.storage import get_transcripts_storage
-from reflector.utils.daily import DailyRoomName, extract_base_room_name
+from reflector.utils.daily import (
+    DailyRoomName,
+    extract_base_room_name,
+    filter_cam_audio_tracks,
+    recording_lock_key,
+)
 from reflector.video_platforms.factory import create_platform_client
 from reflector.video_platforms.whereby_utils import (
     parse_whereby_recording_filename,
@@ -178,6 +187,42 @@ async def process_multitrack_recording(
         logger.warning("No audio track keys provided")
         return
 
+    lock_key = recording_lock_key(recording_id)
+    async with RedisAsyncLock(
+        key=lock_key,
+        timeout=600,  # 10min for processing (includes API calls, DB writes)
+        extend_interval=60,  # Auto-extend every 60s
+        skip_if_locked=True,
+        blocking=False,
+    ) as lock:
+        if not lock.acquired:
+            logger.warning(
+                "Recording processing skipped - lock already held (duplicate task or concurrent worker)",
+                recording_id=recording_id,
+                lock_key=lock_key,
+                reason="duplicate_task_or_concurrent_worker",
+            )
+            return
+
+        logger.info(
+            "Recording worker acquired lock - starting processing",
+            recording_id=recording_id,
+            lock_key=lock_key,
+        )
+
+        await _process_multitrack_recording_inner(
+            bucket_name, daily_room_name, recording_id, track_keys
+        )
+
+
+async def _process_multitrack_recording_inner(
+    bucket_name: str,
+    daily_room_name: DailyRoomName,
+    recording_id: str,
+    track_keys: list[str],
+):
+    """Inner function containing the actual processing logic."""
+
     tz = timezone.utc
     recorded_at = datetime.now(tz)
     try:
@@ -225,20 +270,10 @@ async def process_multitrack_recording(
                 track_keys=track_keys,
             )
         )
-    else:
+    # else: Recording already exists; metadata set at creation time
-        # Recording already exists; assume metadata was set at creation time
-        pass
 
     transcript = await transcripts_controller.get_by_recording_id(recording.id)
-    if transcript:
+    if not transcript:
-        await transcripts_controller.update(
-            transcript,
-            {
-                "topics": [],
-                "participants": [],
-            },
-        )
-    else:
         transcript = await transcripts_controller.add(
             "",
             source_kind=SourceKind.ROOM,
@@ -251,72 +286,238 @@ async def process_multitrack_recording(
             room_id=room.id,
         )
 
-    try:
-        daily_client = create_platform_client("daily")
-
-        id_to_name = {}
-        id_to_user_id = {}
-
-        mtg_session_id = None
-        try:
-            rec_details = await daily_client.get_recording(recording_id)
-            mtg_session_id = rec_details.get("mtgSessionId")
-        except Exception as e:
-            logger.warning(
-                "Failed to fetch Daily recording details",
-                error=str(e),
-                recording_id=recording_id,
-                exc_info=True,
-            )
-
-        if mtg_session_id:
-            try:
-                payload = await daily_client.get_meeting_participants(mtg_session_id)
-                for p in payload.get("data", []):
-                    pid = p.get("participant_id")
-                    name = p.get("user_name")
-                    user_id = p.get("user_id")
-                    if pid and name:
-                        id_to_name[pid] = name
-                    if pid and 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,
-            )
-
-        for idx, key in enumerate(track_keys):
-            base = os.path.basename(key)
-            m = re.search(r"\d{13,}-([0-9a-fA-F-]{36})-cam-audio-", base)
-            participant_id = m.group(1) if m else None
-
-            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=track_keys,
+        track_keys=filter_cam_audio_tracks(track_keys),
     )
 
 
+@shared_task
+@asynctask
+async def poll_daily_recordings():
+    """Poll Daily.co API for recordings and process missing ones.
+
+    Fetches latest recordings from Daily.co API (default limit 100), compares with DB,
+    and queues processing for recordings not already in DB.
+
+    For each missing recording, uses audio tracks from API response.
+
+    Worker-level locking provides idempotency (see process_multitrack_recording).
+    """
+    bucket_name = settings.DAILYCO_STORAGE_AWS_BUCKET_NAME
+    if not bucket_name:
+        logger.debug(
+            "DAILYCO_STORAGE_AWS_BUCKET_NAME not configured; skipping recording poll"
+        )
+        return
+
+    async with create_platform_client("daily") as daily_client:
+        # latest 100. TODO cursor-based state
+        api_recordings: List[RecordingResponse] = await daily_client.list_recordings()
+
+    if not api_recordings:
+        logger.debug(
+            "No recordings found from Daily.co API",
+        )
+        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]
+    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
+    ]
+
+    if not missing_recordings:
+        logger.debug(
+            "All recordings already in DB",
+            api_count=len(finished_recordings),
+            existing_count=len(existing_recordings),
+        )
+        return
+
+    logger.info(
+        "Found recordings missing from DB",
+        missing_count=len(missing_recordings),
+        total_api_count=len(finished_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,
+                )
+            continue
+
+        track_keys = [t.s3Key for t in recording.tracks if t.type == "audio"]
+
+        if not track_keys:
+            logger.warning(
+                "No audio tracks found in recording (only video tracks)",
+                recording_id=recording.id,
+                room_name=recording.room_name,
+                total_tracks=len(recording.tracks),
+            )
+            continue
+
+        logger.info(
+            "Queueing missing recording for processing",
+            recording_id=recording.id,
+            room_name=recording.room_name,
+            track_count=len(track_keys),
+        )
+
+        process_multitrack_recording.delay(
+            bucket_name=bucket_name,
+            daily_room_name=recording.room_name,
+            recording_id=recording.id,
+            track_keys=track_keys,
+        )
+
+
+async def poll_daily_room_presence(meeting_id: str) -> None:
+    """Poll Daily.co room presence and reconcile with DB sessions. New presence is added, old presence is marked as closed.
+    Warning: Daily api returns only current state, so there could be missed presence updates, people who went and left the room quickly.
+    Therefore, set(presences) != set(recordings) even if everyone said something. This is not a problem but should be noted."""
+
+    async with RedisAsyncLock(
+        key=f"meeting_presence_poll:{meeting_id}",
+        timeout=120,
+        extend_interval=30,
+        skip_if_locked=True,
+        blocking=False,
+    ) as lock:
+        if not lock.acquired:
+            logger.debug(
+                "Concurrent poll skipped (duplicate task)", meeting_id=meeting_id
+            )
+            return
+
+        meeting = await meetings_controller.get_by_id(meeting_id)
+        if not meeting:
+            logger.warning("Meeting not found", meeting_id=meeting_id)
+            return
+
+        async with create_platform_client("daily") as daily_client:
+            try:
+                presence = await daily_client.get_room_presence(meeting.room_name)
+            except Exception as e:
+                logger.error(
+                    "Daily.co API fetch failed",
+                    meeting_id=meeting.id,
+                    room_name=meeting.room_name,
+                    error=str(e),
+                    exc_info=True,
+                )
+                return
+
+        api_participants = {p.id: p for p in presence.data}
+        db_sessions = (
+            await daily_participant_sessions_controller.get_all_sessions_for_meeting(
+                meeting.id
+            )
+        )
+
+        active_session_ids = {
+            sid for sid, s in db_sessions.items() if s.left_at is None
+        }
+        missing_session_ids = set(api_participants.keys()) - active_session_ids
+        stale_session_ids = active_session_ids - set(api_participants.keys())
+
+        if missing_session_ids:
+            missing_sessions = []
+            for session_id in missing_session_ids:
+                p = api_participants[session_id]
+                session = DailyParticipantSession(
+                    id=f"{meeting.id}:{session_id}",
+                    meeting_id=meeting.id,
+                    room_id=meeting.room_id,
+                    session_id=session_id,
+                    user_id=p.userId,
+                    user_name=p.userName,
+                    joined_at=datetime.fromisoformat(p.joinTime),
+                    left_at=None,
+                )
+                missing_sessions.append(session)
+
+            await daily_participant_sessions_controller.batch_upsert_sessions(
+                missing_sessions
+            )
+            logger.info(
+                "Sessions added",
+                meeting_id=meeting.id,
+                count=len(missing_sessions),
+            )
+
+        if stale_session_ids:
+            composite_ids = [f"{meeting.id}:{sid}" for sid in stale_session_ids]
+            await daily_participant_sessions_controller.batch_close_sessions(
+                composite_ids,
+                left_at=datetime.now(timezone.utc),
+            )
+            logger.info(
+                "Stale sessions closed",
+                meeting_id=meeting.id,
+                count=len(composite_ids),
+            )
+
+        final_active_count = len(api_participants)
+        if meeting.num_clients != final_active_count:
+            await meetings_controller.update_meeting(
+                meeting.id,
+                num_clients=final_active_count,
+            )
+            logger.info(
+                "num_clients updated",
+                meeting_id=meeting.id,
+                old_value=meeting.num_clients,
+                new_value=final_active_count,
+            )
+
+
+@shared_task
+@asynctask
+async def poll_daily_room_presence_task(meeting_id: str) -> None:
+    """Celery task wrapper for poll_daily_room_presence.
+
+    Queued by webhooks or reconciliation timer.
+    """
+    await poll_daily_room_presence(meeting_id)
+
+
 @shared_task
 @asynctask
 async def process_meetings():
@@ -335,72 +536,71 @@ async def process_meetings():
     Uses distributed locking to prevent race conditions when multiple workers
     process the same meeting simultaneously.
     """
-    logger.debug("Processing meetings")
+
     meetings = await meetings_controller.get_all_active()
+    logger.info(f"Processing {len(meetings)} meetings")
     current_time = datetime.now(timezone.utc)
-    redis_client = get_redis_client()
     processed_count = 0
     skipped_count = 0
-
     for meeting in meetings:
         logger_ = logger.bind(meeting_id=meeting.id, room_name=meeting.room_name)
-        lock_key = f"meeting_process_lock:{meeting.id}"
+        logger_.info("Processing meeting")
-        lock = redis_client.lock(lock_key, timeout=120)
 
         try:
-            if not lock.acquire(blocking=False):
+            async with RedisAsyncLock(
-                logger_.debug("Meeting is being processed by another worker, skipping")
+                key=f"meeting_process_lock:{meeting.id}",
-                skipped_count += 1
+                timeout=120,
-                continue
+                extend_interval=30,
+                skip_if_locked=True,
+                blocking=False,
+            ) as lock:
+                if not lock.acquired:
+                    logger_.debug(
+                        "Meeting is being processed by another worker, skipping"
+                    )
+                    skipped_count += 1
+                    continue
 
-            # Process the meeting
+                # Process the meeting
-            should_deactivate = False
+                should_deactivate = False
-            end_date = meeting.end_date
+                end_date = meeting.end_date
-            if end_date.tzinfo is None:
+                if end_date.tzinfo is None:
-                end_date = end_date.replace(tzinfo=timezone.utc)
+                    end_date = end_date.replace(tzinfo=timezone.utc)
 
-            # This API call could be slow, extend lock if needed
+                client = create_platform_client(meeting.platform)
-            client = create_platform_client(meeting.platform)
+                room_sessions = await client.get_room_sessions(meeting.room_name)
-            room_sessions = await client.get_room_sessions(meeting.room_name)
 
-            try:
+                has_active_sessions = bool(
-                # Extend lock after slow operation to ensure we still hold it
+                    room_sessions and any(s.ended_at is None for s in room_sessions)
-                lock.extend(120, replace_ttl=True)
+                )
-            except LockError:
+                has_had_sessions = bool(room_sessions)
-                logger_.warning("Lost lock for meeting, skipping")
+                logger_.info(
-                continue
+                    f"has_active_sessions={has_active_sessions}, has_had_sessions={has_had_sessions}"
-
-            has_active_sessions = room_sessions and any(
-                rs["endedAt"] is None for rs in room_sessions
-            )
-            has_had_sessions = bool(room_sessions)
-
-            if has_active_sessions:
-                logger_.debug("Meeting still has active sessions, keep it")
-            elif has_had_sessions:
-                should_deactivate = True
-                logger_.info("Meeting ended - all participants left")
-            elif current_time > end_date:
-                should_deactivate = True
-                logger_.info(
-                    "Meeting deactivated - scheduled time ended with no participants",
                 )
-            else:
-                logger_.debug("Meeting not yet started, keep it")
 
-            if should_deactivate:
+                if has_active_sessions:
-                await meetings_controller.update_meeting(meeting.id, is_active=False)
+                    logger_.debug("Meeting still has active sessions, keep it")
-                logger_.info("Meeting is deactivated")
+                elif has_had_sessions:
+                    should_deactivate = True
+                    logger_.info("Meeting ended - all participants left")
+                elif current_time > end_date:
+                    should_deactivate = True
+                    logger_.info(
+                        "Meeting deactivated - scheduled time ended with no participants",
+                    )
+                else:
+                    logger_.debug("Meeting not yet started, keep it")
 
-            processed_count += 1
+                if should_deactivate:
+                    await meetings_controller.update_meeting(
+                        meeting.id, is_active=False
+                    )
+                    logger_.info("Meeting is deactivated")
+
+                processed_count += 1
 
         except Exception:
             logger_.error("Error processing meeting", exc_info=True)
-        finally:
-            try:
-                lock.release()
-            except LockError:
-                pass  # Lock already released or expired
 
     logger.debug(
         "Processed meetings finished",
@@ -471,7 +671,7 @@ 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 recordings are processed via webhooks, not this cron job.
+    Note: Daily.co multitrack recordings are handled by reprocess_failed_daily_recordings.
     """
     logger.info("Checking Whereby recordings that need processing or reprocessing")
 
@@ -522,3 +722,131 @@ async def reprocess_failed_recordings():
 
     logger.info(f"Reprocessing complete. Requeued {reprocessed_count} 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:
+    """Daily.co pull"""
+    try:
+        active_meetings = await meetings_controller.get_all_active(platform="daily")
+        queued_count = 0
+
+        for meeting in active_meetings:
+            try:
+                poll_daily_room_presence_task.delay(meeting.id)
+                queued_count += 1
+            except Exception as e:
+                logger.error(
+                    "Failed to queue reconciliation poll",
+                    meeting_id=meeting.id,
+                    error=str(e),
+                    exc_info=True,
+                )
+                raise
+
+        if queued_count > 0:
+            logger.debug(
+                "Reconciliation polls queued",
+                count=queued_count,
+            )
+
+    except Exception as e:
+        logger.error("Reconciliation trigger failed", error=str(e), exc_info=True)

server/reflector/worker/webhook.py

@@ -123,6 +123,7 @@ 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,

server/scripts/list_daily_webhooks.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from reflector.dailyco_api import DailyApiClient
+from reflector.settings import settings
+
+
+async def list_webhooks():
+    """List all Daily.co webhooks for this account using dailyco_api module."""
+    if not settings.DAILY_API_KEY:
+        print("Error: DAILY_API_KEY not set")
+        return 1
+
+    async with DailyApiClient(api_key=settings.DAILY_API_KEY) as client:
+        try:
+            webhooks = await client.list_webhooks()
+
+            if not webhooks:
+                print("No webhooks found")
+                return 0
+
+            print(f"Found {len(webhooks)} webhook(s):\n")
+
+            for webhook in webhooks:
+                print("=" * 80)
+                print(f"UUID:         {webhook.uuid}")
+                print(f"URL:          {webhook.url}")
+                print(f"State:        {webhook.state}")
+                print(f"Event Types:  {', '.join(webhook.eventTypes)}")
+                print(
+                    f"HMAC Secret:  {'✓ Configured' if webhook.hmac else '✗ Not set'}"
+                )
+                print()
+
+            print("=" * 80)
+            print(
+                f"\nCurrent DAILY_WEBHOOK_UUID in settings: {settings.DAILY_WEBHOOK_UUID or '(not set)'}"
+            )
+
+            return 0
+
+        except Exception as e:
+            print(f"Error fetching webhooks: {e}")
+            return 1
+
+
+if __name__ == "__main__":
+    sys.exit(asyncio.run(list_webhooks()))

server/scripts/migrate_user_ids.py

@@ -0,0 +1,292 @@
+#!/usr/bin/env python3
+"""
+Manual Migration Script: Migrate user_id from Authentik UID to internal user.id
+
+This script should be run manually AFTER applying the database schema migrations.
+
+Usage:
+    AUTHENTIK_API_URL=https://your-authentik-url \
+    AUTHENTIK_API_TOKEN=your-token \
+    DATABASE_URL=postgresql://... \
+    python scripts/migrate_user_ids.py
+
+What this script does:
+1. Collects all unique Authentik UIDs currently used in the database
+2. Fetches only those users from Authentik API to populate the users table
+3. Updates user_id in: user_api_key, transcript, room, meeting_consent
+4. Uses user.authentik_uid to lookup the corresponding user.id
+
+The script is idempotent:
+- User inserts use ON CONFLICT DO NOTHING (safe if users already exist)
+- Update queries only match authentik_uid->uuid pairs (no-op if already migrated)
+- Safe to run multiple times without side effects
+
+Prerequisites:
+- AUTHENTIK_API_URL environment variable must be set
+- AUTHENTIK_API_TOKEN environment variable must be set
+- DATABASE_URL environment variable must be set
+- Authentik API must be accessible
+"""
+
+import asyncio
+import os
+import sys
+from datetime import datetime, timezone
+from typing import Any
+
+import httpx
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import AsyncConnection, create_async_engine
+
+TABLES_WITH_USER_ID = ["user_api_key", "transcript", "room", "meeting_consent"]
+NULLABLE_USER_ID_TABLES = {"transcript", "meeting_consent"}
+AUTHENTIK_PAGE_SIZE = 100
+HTTP_TIMEOUT = 30.0
+
+
+class AuthentikClient:
+    def __init__(self, api_url: str, api_token: str):
+        self.api_url = api_url
+        self.api_token = api_token
+
+    def _get_headers(self) -> dict[str, str]:
+        return {
+            "Authorization": f"Bearer {self.api_token}",
+            "Accept": "application/json",
+        }
+
+    async def fetch_all_users(self) -> list[dict[str, Any]]:
+        all_users = []
+        page = 1
+
+        try:
+            async with httpx.AsyncClient(timeout=HTTP_TIMEOUT) as client:
+                while True:
+                    url = f"{self.api_url}/api/v3/core/users/"
+                    params = {
+                        "page": page,
+                        "page_size": AUTHENTIK_PAGE_SIZE,
+                        "include_groups": "false",
+                    }
+
+                    print(f"  Fetching users from Authentik (page {page})...")
+                    response = await client.get(
+                        url, headers=self._get_headers(), params=params
+                    )
+                    response.raise_for_status()
+                    data = response.json()
+
+                    results = data.get("results", [])
+                    if not results:
+                        break
+
+                    all_users.extend(results)
+                    print(f"  Fetched {len(results)} users from page {page}")
+
+                    if not data.get("next"):
+                        break
+
+                    page += 1
+
+            print(f"  Total: {len(all_users)} users fetched from Authentik")
+            return all_users
+
+        except httpx.HTTPError as e:
+            raise Exception(f"Failed to fetch users from Authentik: {e}") from e
+
+
+async def collect_used_authentik_uids(connection: AsyncConnection) -> set[str]:
+    print("\nStep 1: Collecting Authentik UIDs from database tables...")
+    used_authentik_uids = set()
+
+    for table in TABLES_WITH_USER_ID:
+        result = await connection.execute(
+            text(f'SELECT DISTINCT user_id FROM "{table}" WHERE user_id IS NOT NULL')
+        )
+        authentik_uids = [row[0] for row in result.fetchall()]
+        used_authentik_uids.update(authentik_uids)
+        print(f"  Found {len(authentik_uids)} unique Authentik UIDs in {table}")
+
+    print(f"  Total unique user IDs found: {len(used_authentik_uids)}")
+
+    if used_authentik_uids:
+        sample_id = next(iter(used_authentik_uids))
+        if len(sample_id) == 36 and sample_id.count("-") == 4:
+            print(
+                f"\n✅ User IDs are already in UUID format (e.g., {sample_id[:20]}...)"
+            )
+            print("Migration has already been completed!")
+            return set()
+
+    return used_authentik_uids
+
+
+def filter_users_by_authentik_uid(
+    authentik_users: list[dict[str, Any]], used_authentik_uids: set[str]
+) -> tuple[list[dict[str, Any]], set[str]]:
+    used_authentik_users = [
+        user for user in authentik_users if user.get("uid") in used_authentik_uids
+    ]
+
+    missing_ids = used_authentik_uids - {u.get("uid") for u in used_authentik_users}
+
+    print(
+        f"  Found {len(used_authentik_users)} matching users in Authentik "
+        f"(out of {len(authentik_users)} total)"
+    )
+
+    if missing_ids:
+        print(
+            f"  ⚠ Warning: {len(missing_ids)} Authentik UIDs in database not found in Authentik:"
+        )
+        for user_id in sorted(missing_ids):
+            print(f"    - {user_id}")
+
+    return used_authentik_users, missing_ids
+
+
+async def sync_users_to_database(
+    connection: AsyncConnection, authentik_users: list[dict[str, Any]]
+) -> tuple[int, int]:
+    created = 0
+    skipped = 0
+    now = datetime.now(timezone.utc)
+
+    for authentik_user in authentik_users:
+        user_id = authentik_user["uuid"]
+        authentik_uid = authentik_user["uid"]
+        email = authentik_user.get("email")
+
+        if not email:
+            print(f"  ⚠ Skipping user {authentik_uid} (no email)")
+            skipped += 1
+            continue
+
+        result = await connection.execute(
+            text("""
+                INSERT INTO "user" (id, email, authentik_uid, created_at, updated_at)
+                VALUES (:id, :email, :authentik_uid, :created_at, :updated_at)
+                ON CONFLICT (id) DO NOTHING
+            """),
+            {
+                "id": user_id,
+                "email": email,
+                "authentik_uid": authentik_uid,
+                "created_at": now,
+                "updated_at": now,
+            },
+        )
+        if result.rowcount > 0:
+            created += 1
+
+    return created, skipped
+
+
+async def migrate_all_user_ids(connection: AsyncConnection) -> int:
+    print("\nStep 3: Migrating user_id columns from Authentik UID to internal UUID...")
+    print("(If no rows are updated, migration may have already been completed)")
+
+    total_updated = 0
+
+    for table in TABLES_WITH_USER_ID:
+        null_check = (
+            f"AND {table}.user_id IS NOT NULL"
+            if table in NULLABLE_USER_ID_TABLES
+            else ""
+        )
+
+        query = f"""
+            UPDATE {table}
+            SET user_id = u.id
+            FROM "user" u
+            WHERE {table}.user_id = u.authentik_uid
+            {null_check}
+        """
+
+        print(f"  Updating {table}.user_id...")
+        result = await connection.execute(text(query))
+        rows = result.rowcount
+        print(f"    ✓ Updated {rows} rows")
+        total_updated += rows
+
+    return total_updated
+
+
+async def run_migration(
+    database_url: str, authentik_api_url: str, authentik_api_token: str
+) -> None:
+    engine = create_async_engine(database_url)
+
+    try:
+        async with engine.begin() as connection:
+            used_authentik_uids = await collect_used_authentik_uids(connection)
+            if not used_authentik_uids:
+                print("\n⚠️  No user IDs found in database. Nothing to migrate.")
+                print("Migration complete (no-op)!")
+                return
+
+            print("\nStep 2: Fetching user data from Authentik and syncing users...")
+            print("(This script is idempotent - safe to run multiple times)")
+            print(f"Authentik API URL: {authentik_api_url}")
+
+            client = AuthentikClient(authentik_api_url, authentik_api_token)
+            authentik_users = await client.fetch_all_users()
+
+            if not authentik_users:
+                print("\nERROR: No users returned from Authentik API.")
+                print(
+                    "Please verify your Authentik configuration and ensure users exist."
+                )
+                sys.exit(1)
+
+            used_authentik_users, _ = filter_users_by_authentik_uid(
+                authentik_users, used_authentik_uids
+            )
+            created, skipped = await sync_users_to_database(
+                connection, used_authentik_users
+            )
+
+            if created > 0:
+                print(f"✓ Created {created} users from Authentik")
+            else:
+                print("✓ No new users created (users may already exist)")
+
+            if skipped > 0:
+                print(f"  ⚠ Skipped {skipped} users without email")
+
+            result = await connection.execute(text('SELECT COUNT(*) FROM "user"'))
+            user_count = result.scalar()
+            print(f"✓ Users table now has {user_count} users")
+
+            total_updated = await migrate_all_user_ids(connection)
+
+            if total_updated > 0:
+                print(f"\n✅ Migration complete! Updated {total_updated} total rows.")
+            else:
+                print(
+                    "\n✅ Migration complete! (No rows updated - migration may have already been completed)"
+                )
+
+    except Exception as e:
+        print(f"\n❌ ERROR: Migration failed: {e}")
+        sys.exit(1)
+    finally:
+        await engine.dispose()
+
+
+async def main() -> None:
+    database_url = os.getenv("DATABASE_URL")
+    authentik_api_url = os.getenv("AUTHENTIK_API_URL")
+    authentik_api_token = os.getenv("AUTHENTIK_API_TOKEN")
+
+    if not database_url or not authentik_api_url or not authentik_api_token:
+        print(
+            "ERROR: DATABASE_URL, AUTHENTIK_API_URL, and AUTHENTIK_API_TOKEN must be set"
+        )
+        sys.exit(1)
+
+    await run_migration(database_url, authentik_api_url, authentik_api_token)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

server/scripts/recreate_daily_webhook.py

@@ -6,56 +6,60 @@ from pathlib import Path
 
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
-import httpx
+from reflector.dailyco_api import (
-
+    CreateWebhookRequest,
+    DailyApiClient,
+)
 from reflector.settings import settings
 
 
 async def setup_webhook(webhook_url: str):
     """
-    Create or update Daily.co webhook for this environment.
+    Create or update Daily.co webhook for this environment using dailyco_api module.
     Uses DAILY_WEBHOOK_UUID to identify existing webhook.
     """
     if not settings.DAILY_API_KEY:
         print("Error: DAILY_API_KEY not set")
         return 1
 
-    headers = {
+    if not settings.DAILY_WEBHOOK_SECRET:
-        "Authorization": f"Bearer {settings.DAILY_API_KEY}",
+        print("Error: DAILY_WEBHOOK_SECRET not set")
-        "Content-Type": "application/json",
+        return 1
-    }
 
-    webhook_data = {
+    event_types = [
-        "url": webhook_url,
+        "participant.joined",
-        "eventTypes": [
+        "participant.left",
-            "participant.joined",
+        "recording.started",
-            "participant.left",
+        "recording.ready-to-download",
-            "recording.started",
+        "recording.error",
-            "recording.ready-to-download",
+    ]
-            "recording.error",
-        ],
-        "hmac": settings.DAILY_WEBHOOK_SECRET,
-    }
 
-    async with httpx.AsyncClient() as client:
+    async with DailyApiClient(api_key=settings.DAILY_API_KEY) as client:
         webhook_uuid = settings.DAILY_WEBHOOK_UUID
 
         if webhook_uuid:
-            # Update existing webhook
             print(f"Updating existing webhook {webhook_uuid}...")
             try:
-                resp = await client.patch(
+                # Note: Daily.co doesn't support PATCH well, so we delete + recreate
-                    f"https://api.daily.co/v1/webhooks/{webhook_uuid}",
+                await client.delete_webhook(webhook_uuid)
-                    headers=headers,
+                print(f"Deleted old webhook {webhook_uuid}")
-                    json=webhook_data,
+
+                request = CreateWebhookRequest(
+                    url=webhook_url,
+                    eventTypes=event_types,
+                    hmac=settings.DAILY_WEBHOOK_SECRET,
                 )
-                resp.raise_for_status()
+                result = await client.create_webhook(request)
-                result = resp.json()
+
-                print(f"✓ Updated webhook {result['uuid']} (state: {result['state']})")
+                print(
-                print(f"  URL: {result['url']}")
+                    f"✓ Created replacement webhook {result.uuid} (state: {result.state})"
-                return 0
+                )
-            except httpx.HTTPStatusError as e:
+                print(f"  URL: {result.url}")
-                if e.response.status_code == 404:
+
+                webhook_uuid = result.uuid
+
+            except Exception as e:
+                if hasattr(e, "response") and e.response.status_code == 404:
                     print(f"Webhook {webhook_uuid} not found, creating new one...")
                     webhook_uuid = None  # Fall through to creation
                 else:
@@ -63,17 +67,17 @@ async def setup_webhook(webhook_url: str):
                     return 1
 
         if not webhook_uuid:
-            # Create new webhook
             print("Creating new webhook...")
-            resp = await client.post(
+            request = CreateWebhookRequest(
-                "https://api.daily.co/v1/webhooks", headers=headers, json=webhook_data
+                url=webhook_url,
+                eventTypes=event_types,
+                hmac=settings.DAILY_WEBHOOK_SECRET,
             )
-            resp.raise_for_status()
+            result = await client.create_webhook(request)
-            result = resp.json()
+            webhook_uuid = result.uuid
-            webhook_uuid = result["uuid"]
 
-            print(f"✓ Created webhook {webhook_uuid} (state: {result['state']})")
+            print(f"✓ Created webhook {webhook_uuid} (state: {result.state})")
-            print(f"  URL: {result['url']}")
+            print(f"  URL: {result.url}")
             print()
             print("=" * 60)
             print("IMPORTANT: Add this to your environment variables:")
@@ -114,7 +118,7 @@ if __name__ == "__main__":
         )
         print()
         print("Behavior:")
-        print("  - If DAILY_WEBHOOK_UUID set: Updates existing webhook")
+        print("  - If DAILY_WEBHOOK_UUID set: Deletes old webhook, creates new one")
         print(
             "  - If DAILY_WEBHOOK_UUID empty: Creates new webhook, saves UUID to .env"
         )

server/tests/conftest.py

@@ -318,6 +318,14 @@ 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

server/tests/mocks/mock_platform.py

@@ -3,9 +3,11 @@ from datetime import datetime
 from typing import Any, Dict, Literal, Optional
 
 from reflector.db.rooms import Room
+from reflector.utils.string import NonEmptyString
 from reflector.video_platforms.base import (
     ROOM_PREFIX_SEPARATOR,
     MeetingData,
+    SessionData,
     VideoPlatformClient,
     VideoPlatformConfig,
 )
@@ -49,28 +51,18 @@ class MockPlatformClient(VideoPlatformClient):
             extra_data={"mock": True},
         )
 
-    async def get_room_sessions(self, room_name: str) -> Dict[str, Any]:
+    async def get_room_sessions(self, room_name: NonEmptyString) -> list[SessionData]:
         if room_name not in self._rooms:
-            return {"error": "Room not found"}
+            return []
 
         room_data = self._rooms[room_name]
-        return {
+        return [
-            "roomName": room_name,
+            SessionData(
-            "sessions": [
+                session_id=room_data["id"],
-                {
+                started_at=datetime.utcnow(),
-                    "sessionId": room_data["id"],
+                ended_at=None if room_data["is_active"] else datetime.utcnow(),
-                    "startTime": datetime.utcnow().isoformat(),
+            )
-                    "participants": room_data["participants"],
+        ]
-                    "isActive": room_data["is_active"],
-                }
-            ],
-        }
-
-    async def delete_room(self, room_name: str) -> bool:
-        if room_name in self._rooms:
-            self._rooms[room_name]["is_active"] = False
-            return True
-        return False
 
     async def upload_logo(self, room_name: str, logo_path: str) -> bool:
         if room_name in self._rooms:

server/tests/test_daily_room_presence_polling.py

@@ -0,0 +1,466 @@
+"""Tests for Daily.co room presence polling functionality.
+
+TDD tests for Task 3.2: Room Presence Polling
+- Query Daily.co API for current room participants
+- Reconcile with DB sessions (add missing, close stale)
+- Update meeting.num_clients if different
+- Use batch operations for efficiency
+"""
+
+from datetime import datetime, timedelta, timezone
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from reflector.dailyco_api.responses import (
+    RoomPresenceParticipant,
+    RoomPresenceResponse,
+)
+from reflector.db.daily_participant_sessions import DailyParticipantSession
+from reflector.db.meetings import Meeting
+from reflector.worker.process import poll_daily_room_presence
+
+
+@pytest.fixture
+def mock_meeting():
+    """Mock meeting with Daily.co room."""
+    return Meeting(
+        id="meeting-123",
+        room_id="room-456",
+        room_name="test-room-20251118120000",
+        room_url="https://daily.co/test-room-20251118120000",
+        host_room_url="https://daily.co/test-room-20251118120000?t=host-token",
+        platform="daily",
+        num_clients=2,
+        is_active=True,
+        start_date=datetime.now(timezone.utc),
+        end_date=datetime.now(timezone.utc),
+    )
+
+
+@pytest.fixture
+def mock_api_participants():
+    """Mock Daily.co API presence response."""
+    now = datetime.now(timezone.utc)
+    return RoomPresenceResponse(
+        total_count=2,
+        data=[
+            RoomPresenceParticipant(
+                room="test-room-20251118120000",
+                id="participant-1",
+                userName="Alice",
+                userId="user-alice",
+                joinTime=(now - timedelta(minutes=10)).isoformat(),
+                duration=600,
+            ),
+            RoomPresenceParticipant(
+                room="test-room-20251118120000",
+                id="participant-2",
+                userName="Bob",
+                userId="user-bob",
+                joinTime=(now - timedelta(minutes=5)).isoformat(),
+                duration=300,
+            ),
+        ],
+    )
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.get_all_sessions_for_meeting"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_upsert_sessions"
+)
+async def test_poll_presence_adds_missing_sessions(
+    mock_batch_upsert,
+    mock_get_sessions,
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+    mock_api_participants,
+):
+    """Test that polling creates sessions for participants not in DB."""
+    mock_get_by_id.return_value = mock_meeting
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(return_value=mock_api_participants)
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    mock_get_sessions.return_value = {}
+    mock_batch_upsert.return_value = None
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+    assert mock_batch_upsert.call_count == 1
+    sessions = mock_batch_upsert.call_args.args[0]
+    assert len(sessions) == 2
+    session_ids = {s.session_id for s in sessions}
+    assert session_ids == {"participant-1", "participant-2"}
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.get_all_sessions_for_meeting"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_upsert_sessions"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_close_sessions"
+)
+async def test_poll_presence_closes_stale_sessions(
+    mock_batch_close,
+    mock_batch_upsert,
+    mock_get_sessions,
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+    mock_api_participants,
+):
+    """Test that polling closes sessions for participants no longer in room."""
+    mock_get_by_id.return_value = mock_meeting
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(return_value=mock_api_participants)
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    now = datetime.now(timezone.utc)
+    mock_get_sessions.return_value = {
+        "participant-1": DailyParticipantSession(
+            id=f"meeting-123:participant-1",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-1",
+            user_id="user-alice",
+            user_name="Alice",
+            joined_at=now,
+            left_at=None,
+        ),
+        "participant-stale": DailyParticipantSession(
+            id=f"meeting-123:participant-stale",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-stale",
+            user_id="user-stale",
+            user_name="Stale User",
+            joined_at=now - timedelta(seconds=120),  # Joined 2 minutes ago
+            left_at=None,
+        ),
+    }
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+    assert mock_batch_close.call_count == 1
+    composite_ids = mock_batch_close.call_args.args[0]
+    left_at = mock_batch_close.call_args.kwargs["left_at"]
+    assert len(composite_ids) == 1
+    assert "meeting-123:participant-stale" in composite_ids
+    assert left_at is not None
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.get_all_sessions_for_meeting"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_upsert_sessions"
+)
+@patch("reflector.worker.process.meetings_controller.update_meeting")
+async def test_poll_presence_updates_num_clients(
+    mock_update_meeting,
+    mock_batch_upsert,
+    mock_get_sessions,
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+    mock_api_participants,
+):
+    """Test that polling updates num_clients when different from API."""
+    meeting_with_wrong_count = mock_meeting
+    meeting_with_wrong_count.num_clients = 5
+    mock_get_by_id.return_value = meeting_with_wrong_count
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(return_value=mock_api_participants)
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    mock_get_sessions.return_value = {}
+    mock_batch_upsert.return_value = None
+
+    await poll_daily_room_presence(meeting_with_wrong_count.id)
+
+    assert mock_update_meeting.call_count == 1
+    assert mock_update_meeting.call_args.kwargs["num_clients"] == 2
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.get_all_sessions_for_meeting"
+)
+async def test_poll_presence_no_changes_if_synced(
+    mock_get_sessions,
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+    mock_api_participants,
+):
+    """Test that polling skips updates when DB already synced with API."""
+    mock_get_by_id.return_value = mock_meeting
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(return_value=mock_api_participants)
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    now = datetime.now(timezone.utc)
+    mock_get_sessions.return_value = {
+        "participant-1": DailyParticipantSession(
+            id=f"meeting-123:participant-1",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-1",
+            user_id="user-alice",
+            user_name="Alice",
+            joined_at=now,
+            left_at=None,
+        ),
+        "participant-2": DailyParticipantSession(
+            id=f"meeting-123:participant-2",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-2",
+            user_id="user-bob",
+            user_name="Bob",
+            joined_at=now,
+            left_at=None,
+        ),
+    }
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.get_all_sessions_for_meeting"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_upsert_sessions"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_close_sessions"
+)
+async def test_poll_presence_mixed_add_and_remove(
+    mock_batch_close,
+    mock_batch_upsert,
+    mock_get_sessions,
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+):
+    """Test that polling handles simultaneous joins and leaves in single poll."""
+    mock_get_by_id.return_value = mock_meeting
+
+    now = datetime.now(timezone.utc)
+
+    # API returns: participant-1 and participant-3 (new)
+    api_response = RoomPresenceResponse(
+        total_count=2,
+        data=[
+            RoomPresenceParticipant(
+                room="test-room-20251118120000",
+                id="participant-1",
+                userName="Alice",
+                userId="user-alice",
+                joinTime=(now - timedelta(minutes=10)).isoformat(),
+                duration=600,
+            ),
+            RoomPresenceParticipant(
+                room="test-room-20251118120000",
+                id="participant-3",
+                userName="Charlie",
+                userId="user-charlie",
+                joinTime=now.isoformat(),
+                duration=0,
+            ),
+        ],
+    )
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(return_value=api_response)
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    # DB has: participant-1 and participant-2 (left but not in API)
+    mock_get_sessions.return_value = {
+        "participant-1": DailyParticipantSession(
+            id=f"meeting-123:participant-1",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-1",
+            user_id="user-alice",
+            user_name="Alice",
+            joined_at=now - timedelta(minutes=10),
+            left_at=None,
+        ),
+        "participant-2": DailyParticipantSession(
+            id=f"meeting-123:participant-2",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-2",
+            user_id="user-bob",
+            user_name="Bob",
+            joined_at=now - timedelta(minutes=5),
+            left_at=None,
+        ),
+    }
+
+    mock_batch_upsert.return_value = None
+    mock_batch_close.return_value = None
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+    # Verify participant-3 was added (missing in DB)
+    assert mock_batch_upsert.call_count == 1
+    sessions_added = mock_batch_upsert.call_args.args[0]
+    assert len(sessions_added) == 1
+    assert sessions_added[0].session_id == "participant-3"
+    assert sessions_added[0].user_name == "Charlie"
+
+    # Verify participant-2 was closed (stale in DB)
+    assert mock_batch_close.call_count == 1
+    composite_ids = mock_batch_close.call_args.args[0]
+    assert len(composite_ids) == 1
+    assert "meeting-123:participant-2" in composite_ids
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+async def test_poll_presence_handles_api_error(
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+):
+    """Test that polling handles Daily.co API errors gracefully."""
+    mock_get_by_id.return_value = mock_meeting
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(side_effect=Exception("API error"))
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.get_all_sessions_for_meeting"
+)
+@patch(
+    "reflector.worker.process.daily_participant_sessions_controller.batch_close_sessions"
+)
+async def test_poll_presence_closes_all_when_room_empty(
+    mock_batch_close,
+    mock_get_sessions,
+    mock_create_client,
+    mock_get_by_id,
+    mock_meeting,
+):
+    """Test that polling closes all sessions when room is empty."""
+    mock_get_by_id.return_value = mock_meeting
+
+    mock_daily_client = AsyncMock()
+    mock_daily_client.get_room_presence = AsyncMock(
+        return_value=RoomPresenceResponse(total_count=0, data=[])
+    )
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    now = datetime.now(timezone.utc)
+    mock_get_sessions.return_value = {
+        "participant-1": DailyParticipantSession(
+            id=f"meeting-123:participant-1",
+            meeting_id="meeting-123",
+            room_id="room-456",
+            session_id="participant-1",
+            user_id="user-alice",
+            user_name="Alice",
+            joined_at=now
+            - timedelta(seconds=120),  # Joined 2 minutes ago (beyond grace period)
+            left_at=None,
+        ),
+    }
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+    assert mock_batch_close.call_count == 1
+    composite_ids = mock_batch_close.call_args.args[0]
+    left_at = mock_batch_close.call_args.kwargs["left_at"]
+    assert len(composite_ids) == 1
+    assert "meeting-123:participant-1" in composite_ids
+    assert left_at is not None
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.RedisAsyncLock")
+@patch("reflector.worker.process.meetings_controller.get_by_id")
+@patch("reflector.worker.process.create_platform_client")
+async def test_poll_presence_skips_if_locked(
+    mock_create_client,
+    mock_get_by_id,
+    mock_redis_lock_class,
+    mock_meeting,
+):
+    """Test that concurrent polling is prevented by Redis lock."""
+    mock_get_by_id.return_value = mock_meeting
+
+    # Mock the RedisAsyncLock to simulate lock not acquired
+    mock_lock_instance = AsyncMock()
+    mock_lock_instance.acquired = False  # Lock not acquired
+    mock_lock_instance.__aenter__ = AsyncMock(return_value=mock_lock_instance)
+    mock_lock_instance.__aexit__ = AsyncMock()
+
+    mock_redis_lock_class.return_value = mock_lock_instance
+
+    mock_daily_client = AsyncMock()
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    await poll_daily_room_presence(mock_meeting.id)
+
+    # Verify RedisAsyncLock was instantiated
+    assert mock_redis_lock_class.call_count == 1
+    # Verify get_room_presence was NOT called (lock not acquired, so function returned early)
+    assert mock_daily_client.get_room_presence.call_count == 0

server/tests/test_llm_retry.py

@@ -0,0 +1,488 @@
+"""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"

server/tests/test_pipeline_main_file.py

@@ -266,7 +266,11 @@ 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 FinalLongSummary, FinalShortSummary
+            from reflector.processors.types import (
+                ActionItems,
+                FinalLongSummary,
+                FinalShortSummary,
+            )
 
             if hasattr(mock_summary, "_callback"):
                 await mock_summary._callback(
@@ -276,12 +280,19 @@ 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):
+        def init_with_callback(
+            transcript=None, callback=None, on_short_summary=None, on_action_items=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

server/tests/test_poll_daily_recordings.py

@@ -0,0 +1,193 @@
+"""Tests for poll_daily_recordings task."""
+
+from datetime import datetime, timedelta, timezone
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from reflector.dailyco_api.responses import RecordingResponse
+from reflector.dailyco_api.webhooks import DailyTrack
+
+
+# Import the unwrapped async function for testing
+# The function is decorated with @shared_task and @asynctask,
+# but we need to test the underlying async implementation
+def _get_poll_daily_recordings_fn():
+    """Get the underlying async function without Celery/asynctask decorators."""
+    from reflector.worker import process
+
+    # Access the actual async function before decorators
+    fn = process.poll_daily_recordings
+    # Get through both decorator layers
+    if hasattr(fn, "__wrapped__"):
+        fn = fn.__wrapped__
+    if hasattr(fn, "__wrapped__"):
+        fn = fn.__wrapped__
+    return fn
+
+
+@pytest.fixture
+def mock_recording_response():
+    """Mock Daily.co API recording response with tracks."""
+    now = datetime.now(timezone.utc)
+    return [
+        RecordingResponse(
+            id="rec-123",
+            room_name="test-room-20251118120000",
+            start_ts=int((now - timedelta(hours=1)).timestamp()),
+            status="finished",
+            max_participants=2,
+            duration=3600,
+            share_token="share-token-123",
+            tracks=[
+                DailyTrack(type="audio", s3Key="track1.webm", size=1024),
+                DailyTrack(type="audio", s3Key="track2.webm", size=2048),
+            ],
+        ),
+        RecordingResponse(
+            id="rec-456",
+            room_name="test-room-20251118130000",
+            start_ts=int((now - timedelta(hours=2)).timestamp()),
+            status="finished",
+            max_participants=3,
+            duration=7200,
+            share_token="share-token-456",
+            tracks=[
+                DailyTrack(type="audio", s3Key="track1.webm", size=1024),
+            ],
+        ),
+    ]
+
+
+@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.process_multitrack_recording.delay")
+async def test_poll_daily_recordings_processes_missing_recordings(
+    mock_process_delay,
+    mock_get_recordings,
+    mock_create_client,
+    mock_settings,
+    mock_recording_response,
+):
+    """Test that poll_daily_recordings queues processing for recordings not in DB."""
+    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 = []
+
+    # Execute - call the unwrapped async function
+    poll_fn = _get_poll_daily_recordings_fn()
+    await poll_fn()
+
+    # Verify Daily.co API was called without time parameters (uses default limit=100)
+    assert mock_daily_client.list_recordings.call_count == 1
+    call_kwargs = mock_daily_client.list_recordings.call_args.kwargs
+
+    # Should not have time-based parameters (uses cursor-based pagination)
+    assert "start_time" not in call_kwargs
+    assert "end_time" not in call_kwargs
+
+    # Verify processing was queued for both missing recordings
+    assert mock_process_delay.call_count == 2
+
+    # Verify the processing calls have correct parameters
+    calls = mock_process_delay.call_args_list
+    assert calls[0].kwargs["bucket_name"] == "test-bucket"
+    assert calls[0].kwargs["recording_id"] == "rec-123"
+    assert calls[0].kwargs["daily_room_name"] == "test-room-20251118120000"
+    assert calls[0].kwargs["track_keys"] == ["track1.webm", "track2.webm"]
+
+    assert calls[1].kwargs["bucket_name"] == "test-bucket"
+    assert calls[1].kwargs["recording_id"] == "rec-456"
+    assert calls[1].kwargs["daily_room_name"] == "test-room-20251118130000"
+    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.process_multitrack_recording.delay")
+async def test_poll_daily_recordings_skips_existing_recordings(
+    mock_process_delay,
+    mock_get_recordings,
+    mock_create_client,
+    mock_settings,
+    mock_recording_response,
+):
+    """Test that poll_daily_recordings skips recordings already in DB."""
+    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 - all recordings already exist
+    from reflector.db.recordings import Recording
+
+    mock_get_recordings.return_value = [
+        Recording(
+            id="rec-123",
+            bucket_name="test-bucket",
+            object_key="",
+            recorded_at=datetime.now(timezone.utc),
+            meeting_id="meeting-1",
+        ),
+        Recording(
+            id="rec-456",
+            bucket_name="test-bucket",
+            object_key="",
+            recorded_at=datetime.now(timezone.utc),
+            meeting_id="meeting-1",
+        ),
+    ]
+
+    # 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 (all recordings already exist)
+    assert mock_process_delay.call_count == 0
+
+
+@pytest.mark.asyncio
+@patch("reflector.worker.process.settings")
+@patch("reflector.worker.process.create_platform_client")
+async def test_poll_daily_recordings_skips_when_bucket_not_configured(
+    mock_create_client,
+    mock_settings,
+):
+    """Test that poll_daily_recordings returns early when bucket is not configured."""
+    # No bucket configured
+    mock_settings.DAILYCO_STORAGE_AWS_BUCKET_NAME = None
+
+    # Mock should not be called
+    mock_daily_client = AsyncMock()
+    mock_create_client.return_value.__aenter__ = AsyncMock(
+        return_value=mock_daily_client
+    )
+    mock_create_client.return_value.__aexit__ = AsyncMock()
+
+    # Execute - call the unwrapped async function
+    poll_fn = _get_poll_daily_recordings_fn()
+    await poll_fn()
+
+    # Verify API was never called
+    mock_daily_client.list_recordings.assert_not_called()

server/tests/test_processor_transcript_segment.py

@@ -159,3 +159,78 @@ 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

server/tests/test_s3_url_parser.py

@@ -0,0 +1,136 @@
+"""Tests for S3 URL parsing functionality in reflector.tools.process"""
+
+import pytest
+
+from reflector.tools.process import parse_s3_url
+
+
+class TestParseS3URL:
+    """Test cases for parse_s3_url function"""
+
+    def test_parse_s3_protocol(self):
+        """Test parsing s3:// protocol URLs"""
+        bucket, key = parse_s3_url("s3://my-bucket/path/to/file.webm")
+        assert bucket == "my-bucket"
+        assert key == "path/to/file.webm"
+
+    def test_parse_s3_protocol_deep_path(self):
+        """Test s3:// with deeply nested paths"""
+        bucket, key = parse_s3_url("s3://bucket-name/very/deep/path/to/audio.mp4")
+        assert bucket == "bucket-name"
+        assert key == "very/deep/path/to/audio.mp4"
+
+    def test_parse_https_subdomain_format(self):
+        """Test parsing https://bucket.s3.amazonaws.com/key format"""
+        bucket, key = parse_s3_url("https://my-bucket.s3.amazonaws.com/path/file.webm")
+        assert bucket == "my-bucket"
+        assert key == "path/file.webm"
+
+    def test_parse_https_regional_subdomain(self):
+        """Test parsing regional endpoint with subdomain"""
+        bucket, key = parse_s3_url(
+            "https://my-bucket.s3.us-west-2.amazonaws.com/path/file.webm"
+        )
+        assert bucket == "my-bucket"
+        assert key == "path/file.webm"
+
+    def test_parse_https_path_style(self):
+        """Test parsing https://s3.amazonaws.com/bucket/key format"""
+        bucket, key = parse_s3_url("https://s3.amazonaws.com/my-bucket/path/file.webm")
+        assert bucket == "my-bucket"
+        assert key == "path/file.webm"
+
+    def test_parse_https_regional_path_style(self):
+        """Test parsing regional endpoint with path style"""
+        bucket, key = parse_s3_url(
+            "https://s3.us-east-1.amazonaws.com/my-bucket/path/file.webm"
+        )
+        assert bucket == "my-bucket"
+        assert key == "path/file.webm"
+
+    def test_parse_url_encoded_keys(self):
+        """Test parsing URL-encoded keys"""
+        bucket, key = parse_s3_url(
+            "s3://my-bucket/path%20with%20spaces/file%2Bname.webm"
+        )
+        assert bucket == "my-bucket"
+        assert key == "path with spaces/file+name.webm"  # Should be decoded
+
+    def test_parse_url_encoded_https(self):
+        """Test URL-encoded keys with HTTPS format"""
+        bucket, key = parse_s3_url(
+            "https://my-bucket.s3.amazonaws.com/file%20with%20spaces.webm"
+        )
+        assert bucket == "my-bucket"
+        assert key == "file with spaces.webm"
+
+    def test_invalid_url_no_scheme(self):
+        """Test that URLs without scheme raise ValueError"""
+        with pytest.raises(ValueError, match="Invalid S3 URL scheme"):
+            parse_s3_url("my-bucket/path/file.webm")
+
+    def test_invalid_url_wrong_scheme(self):
+        """Test that non-S3 schemes raise ValueError"""
+        with pytest.raises(ValueError, match="Invalid S3 URL scheme"):
+            parse_s3_url("ftp://my-bucket/path/file.webm")
+
+    def test_invalid_s3_missing_bucket(self):
+        """Test s3:// URL without bucket raises ValueError"""
+        with pytest.raises(ValueError, match="missing bucket or key"):
+            parse_s3_url("s3:///path/file.webm")
+
+    def test_invalid_s3_missing_key(self):
+        """Test s3:// URL without key raises ValueError"""
+        with pytest.raises(ValueError, match="missing bucket or key"):
+            parse_s3_url("s3://my-bucket/")
+
+    def test_invalid_s3_empty_key(self):
+        """Test s3:// URL with empty key raises ValueError"""
+        with pytest.raises(ValueError, match="missing bucket or key"):
+            parse_s3_url("s3://my-bucket")
+
+    def test_invalid_https_not_s3(self):
+        """Test HTTPS URL that's not S3 raises ValueError"""
+        with pytest.raises(ValueError, match="not recognized as S3 URL"):
+            parse_s3_url("https://example.com/path/file.webm")
+
+    def test_invalid_https_subdomain_missing_key(self):
+        """Test HTTPS subdomain format without key raises ValueError"""
+        with pytest.raises(ValueError, match="missing bucket or key"):
+            parse_s3_url("https://my-bucket.s3.amazonaws.com/")
+
+    def test_invalid_https_path_style_missing_parts(self):
+        """Test HTTPS path style with missing bucket/key raises ValueError"""
+        with pytest.raises(ValueError, match="missing bucket or key"):
+            parse_s3_url("https://s3.amazonaws.com/")
+
+    def test_bucket_with_dots(self):
+        """Test parsing bucket names with dots"""
+        bucket, key = parse_s3_url("s3://my.bucket.name/path/file.webm")
+        assert bucket == "my.bucket.name"
+        assert key == "path/file.webm"
+
+    def test_bucket_with_hyphens(self):
+        """Test parsing bucket names with hyphens"""
+        bucket, key = parse_s3_url("s3://my-bucket-name-123/path/file.webm")
+        assert bucket == "my-bucket-name-123"
+        assert key == "path/file.webm"
+
+    def test_key_with_special_chars(self):
+        """Test keys with various special characters"""
+        # Note: # is treated as URL fragment separator, not part of key
+        bucket, key = parse_s3_url("s3://bucket/2024-01-01_12:00:00/file.webm")
+        assert bucket == "bucket"
+        assert key == "2024-01-01_12:00:00/file.webm"
+
+    def test_fragment_handling(self):
+        """Test that URL fragments are properly ignored"""
+        bucket, key = parse_s3_url("s3://bucket/path/to/file.webm#fragment123")
+        assert bucket == "bucket"
+        assert key == "path/to/file.webm"  # Fragment not included
+
+    def test_http_scheme_s3_url(self):
+        """Test that HTTP (not HTTPS) S3 URLs are supported"""
+        bucket, key = parse_s3_url("http://my-bucket.s3.amazonaws.com/path/file.webm")
+        assert bucket == "my-bucket"
+        assert key == "path/file.webm"

server/tests/test_transcript_formats.py

@@ -0,0 +1,779 @@
+"""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

server/tests/test_transcripts.py

@@ -1,5 +1,8 @@
 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):
@@ -182,3 +185,51 @@ 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

server/tests/test_transcripts_process.py

@@ -1,5 +1,6 @@
 import asyncio
 import time
+from unittest.mock import patch
 
 import pytest
 from httpx import ASGITransport, AsyncClient
@@ -101,3 +102,113 @@ async def test_transcript_process(
     assert response.status_code == 200
     assert len(response.json()) == 1
     assert "Hello world. How are you today?" in response.json()[0]["transcript"]
+
+
+@pytest.mark.usefixtures("setup_database")
+@pytest.mark.asyncio
+async def test_whereby_recording_uses_file_pipeline(client):
+    """Test that Whereby recordings (bucket_name but no track_keys) use file pipeline"""
+    from datetime import datetime, timezone
+
+    from reflector.db.recordings import Recording, recordings_controller
+    from reflector.db.transcripts import transcripts_controller
+
+    # Create transcript with Whereby recording (has bucket_name, no track_keys)
+    transcript = await transcripts_controller.add(
+        "",
+        source_kind="room",
+        source_language="en",
+        target_language="en",
+        user_id="test-user",
+        share_mode="public",
+    )
+
+    recording = await recordings_controller.create(
+        Recording(
+            bucket_name="whereby-bucket",
+            object_key="test-recording.mp4",  # gitleaks:allow
+            meeting_id="test-meeting",
+            recorded_at=datetime.now(timezone.utc),
+            track_keys=None,  # Whereby recordings have no track_keys
+        )
+    )
+
+    await transcripts_controller.update(
+        transcript, {"recording_id": recording.id, "status": "uploaded"}
+    )
+
+    with (
+        patch(
+            "reflector.services.transcript_process.task_pipeline_file_process"
+        ) as mock_file_pipeline,
+        patch(
+            "reflector.services.transcript_process.task_pipeline_multitrack_process"
+        ) as mock_multitrack_pipeline,
+    ):
+        response = await client.post(f"/transcripts/{transcript.id}/process")
+
+        assert response.status_code == 200
+        assert response.json()["status"] == "ok"
+
+        # Whereby recordings should use file pipeline
+        mock_file_pipeline.delay.assert_called_once_with(transcript_id=transcript.id)
+        mock_multitrack_pipeline.delay.assert_not_called()
+
+
+@pytest.mark.usefixtures("setup_database")
+@pytest.mark.asyncio
+async def test_dailyco_recording_uses_multitrack_pipeline(client):
+    """Test that Daily.co recordings (bucket_name + track_keys) use multitrack pipeline"""
+    from datetime import datetime, timezone
+
+    from reflector.db.recordings import Recording, recordings_controller
+    from reflector.db.transcripts import transcripts_controller
+
+    # Create transcript with Daily.co multitrack recording
+    transcript = await transcripts_controller.add(
+        "",
+        source_kind="room",
+        source_language="en",
+        target_language="en",
+        user_id="test-user",
+        share_mode="public",
+    )
+
+    track_keys = [
+        "recordings/test-room/track1.webm",
+        "recordings/test-room/track2.webm",
+    ]
+    recording = await recordings_controller.create(
+        Recording(
+            bucket_name="daily-bucket",
+            object_key="recordings/test-room",
+            meeting_id="test-meeting",
+            track_keys=track_keys,
+            recorded_at=datetime.now(timezone.utc),
+        )
+    )
+
+    await transcripts_controller.update(
+        transcript, {"recording_id": recording.id, "status": "uploaded"}
+    )
+
+    with (
+        patch(
+            "reflector.services.transcript_process.task_pipeline_file_process"
+        ) as mock_file_pipeline,
+        patch(
+            "reflector.services.transcript_process.task_pipeline_multitrack_process"
+        ) as mock_multitrack_pipeline,
+    ):
+        response = await client.post(f"/transcripts/{transcript.id}/process")
+
+        assert response.status_code == 200
+        assert response.json()["status"] == "ok"
+
+        # Daily.co multitrack recordings should use multitrack pipeline
+        mock_multitrack_pipeline.delay.assert_called_once_with(
+            transcript_id=transcript.id,
+            bucket_name="daily-bucket",
+            track_keys=track_keys,
+        )
+        mock_file_pipeline.delay.assert_not_called()

server/tests/test_user_websocket_auth.py

@@ -120,7 +120,15 @@ async def test_user_ws_accepts_valid_token_and_receives_events(appserver_ws_user
     host, port = appserver_ws_user
     base_ws = f"http://{host}:{port}/v1/events"
 
-    token = _make_dummy_jwt("user-abc")
+    # Create a test user in the database
+    from reflector.db.users import user_controller
+
+    test_uid = "user-abc"
+    user = await user_controller.create_or_update(
+        id="test-user-id-abc", authentik_uid=test_uid, email="user-abc@example.com"
+    )
+
+    token = _make_dummy_jwt(test_uid)
     subprotocols = ["bearer", token]
 
     # Connect and then trigger an event via HTTP create
@@ -132,12 +140,13 @@ async def test_user_ws_accepts_valid_token_and_receives_events(appserver_ws_user
         from reflector.auth import current_user, current_user_optional
 
         # Override auth dependencies so HTTP request is performed as the same user
+        # Use the internal user.id (not the Authentik UID)
         app.dependency_overrides[current_user] = lambda: {
-            "sub": "user-abc",
+            "sub": user.id,
             "email": "user-abc@example.com",
         }
         app.dependency_overrides[current_user_optional] = lambda: {
-            "sub": "user-abc",
+            "sub": user.id,
             "email": "user-abc@example.com",
         }
 

server/tests/test_utils_daily.py

@@ -1,6 +1,6 @@
 import pytest
 
-from reflector.utils.daily import extract_base_room_name
+from reflector.utils.daily import extract_base_room_name, parse_daily_recording_filename
 
 
 @pytest.mark.parametrize(
@@ -15,3 +15,50 @@ from reflector.utils.daily import extract_base_room_name
 )
 def test_extract_base_room_name(daily_room_name, expected):
     assert extract_base_room_name(daily_room_name) == expected
+
+
+@pytest.mark.parametrize(
+    "filename,expected_recording_ts,expected_participant_id,expected_track_ts",
+    [
+        (
+            "1763152299562-12f0b87c-97d4-4dd3-a65c-cee1f854a79c-cam-audio-1763152314582",
+            1763152299562,
+            "12f0b87c-97d4-4dd3-a65c-cee1f854a79c",
+            1763152314582,
+        ),
+        (
+            "1760988935484-52f7f48b-fbab-431f-9a50-87b9abfc8255-cam-audio-1760988935922",
+            1760988935484,
+            "52f7f48b-fbab-431f-9a50-87b9abfc8255",
+            1760988935922,
+        ),
+        (
+            "1760988935484-a37c35e3-6f8e-4274-a482-e9d0f102a732-cam-audio-1760988943823",
+            1760988935484,
+            "a37c35e3-6f8e-4274-a482-e9d0f102a732",
+            1760988943823,
+        ),
+        (
+            "path/to/1763151171834-b6719a43-4481-483a-a8fc-2ae18b69283c-cam-audio-1763151180561",
+            1763151171834,
+            "b6719a43-4481-483a-a8fc-2ae18b69283c",
+            1763151180561,
+        ),
+    ],
+)
+def test_parse_daily_recording_filename(
+    filename, expected_recording_ts, expected_participant_id, expected_track_ts
+):
+    result = parse_daily_recording_filename(filename)
+
+    assert result.recording_start_ts == expected_recording_ts
+    assert result.participant_id == expected_participant_id
+    assert result.track_start_ts == expected_track_ts
+
+
+def test_parse_daily_recording_filename_invalid():
+    with pytest.raises(ValueError, match="Invalid Daily.co recording filename"):
+        parse_daily_recording_filename("invalid-filename")
+
+    with pytest.raises(ValueError, match="Invalid Daily.co recording filename"):
+        parse_daily_recording_filename("123-not-a-uuid-cam-audio-456")

server/tests/test_video_platforms_factory.py

@@ -1,58 +0,0 @@
-"""Tests for video_platforms.factory module."""
-
-from unittest.mock import patch
-
-from reflector.video_platforms.factory import get_platform
-
-
-class TestGetPlatformF:
-    """Test suite for get_platform function."""
-
-    @patch("reflector.video_platforms.factory.settings")
-    def test_with_room_platform(self, mock_settings):
-        """When room_platform provided, should return room_platform."""
-        mock_settings.DEFAULT_VIDEO_PLATFORM = "whereby"
-
-        # Should return the room's platform when provided
-        assert get_platform(room_platform="daily") == "daily"
-        assert get_platform(room_platform="whereby") == "whereby"
-
-    @patch("reflector.video_platforms.factory.settings")
-    def test_without_room_platform_uses_default(self, mock_settings):
-        """When no room_platform, should return DEFAULT_VIDEO_PLATFORM."""
-        mock_settings.DEFAULT_VIDEO_PLATFORM = "whereby"
-
-        # Should return default when room_platform is None
-        assert get_platform(room_platform=None) == "whereby"
-
-    @patch("reflector.video_platforms.factory.settings")
-    def test_with_daily_default(self, mock_settings):
-        """When DEFAULT_VIDEO_PLATFORM is 'daily', should return 'daily' when no room_platform."""
-        mock_settings.DEFAULT_VIDEO_PLATFORM = "daily"
-
-        # Should return default 'daily' when room_platform is None
-        assert get_platform(room_platform=None) == "daily"
-
-    @patch("reflector.video_platforms.factory.settings")
-    def test_no_room_id_provided(self, mock_settings):
-        """Should work correctly even when room_id is not provided."""
-        mock_settings.DEFAULT_VIDEO_PLATFORM = "whereby"
-
-        # Should use room_platform when provided
-        assert get_platform(room_platform="daily") == "daily"
-
-        # Should use default when room_platform not provided
-        assert get_platform(room_platform=None) == "whereby"
-
-    @patch("reflector.video_platforms.factory.settings")
-    def test_room_platform_always_takes_precedence(self, mock_settings):
-        """room_platform should always be used when provided."""
-        mock_settings.DEFAULT_VIDEO_PLATFORM = "whereby"
-
-        # room_platform should take precedence over default
-        assert get_platform(room_platform="daily") == "daily"
-        assert get_platform(room_platform="whereby") == "whereby"
-
-        # Different default shouldn't matter when room_platform provided
-        mock_settings.DEFAULT_VIDEO_PLATFORM = "daily"
-        assert get_platform(room_platform="whereby") == "whereby"

www/.env.example

@@ -22,6 +22,7 @@ AUTHENTIK_CLIENT_SECRET=your-client-secret-here
 
 # API URLs
 API_URL=http://127.0.0.1:1250
+SERVER_API_URL=http://server:1250
 WEBSOCKET_URL=ws://127.0.0.1:1250
 AUTH_CALLBACK_URL=http://localhost:3000/auth-callback
 

www/app/(app)/rooms/page.tsx

@@ -15,9 +15,12 @@ import {
   createListCollection,
   useDisclosure,
   Tabs,
+  Popover,
+  Text,
+  HStack,
 } from "@chakra-ui/react";
 import { useEffect, useMemo, useState } from "react";
-import { LuEye, LuEyeOff } from "react-icons/lu";
+import { LuEye, LuEyeOff, LuInfo } from "react-icons/lu";
 import useRoomList from "./useRoomList";
 import type { components } from "../../reflector-api";
 import {
@@ -67,6 +70,11 @@ const recordingTypeOptions: SelectOption[] = [
   { label: "Cloud", value: "cloud" },
 ];
 
+const platformOptions: SelectOption[] = [
+  { label: "Whereby", value: "whereby" },
+  { label: "Daily", value: "daily" },
+];
+
 const roomInitialState = {
   name: "",
   zulipAutoPost: false,
@@ -82,6 +90,8 @@ const roomInitialState = {
   icsUrl: "",
   icsEnabled: false,
   icsFetchInterval: 5,
+  platform: "whereby",
+  skipConsent: false,
 };
 
 export default function RoomsList() {
@@ -99,6 +109,11 @@ export default function RoomsList() {
   const recordingTypeCollection = createListCollection({
     items: recordingTypeOptions,
   });
+
+  const platformCollection = createListCollection({
+    items: platformOptions,
+  });
+
   const [roomInput, setRoomInput] = useState<null | typeof roomInitialState>(
     null,
   );
@@ -143,15 +158,25 @@ export default function RoomsList() {
             zulipStream: detailedEditedRoom.zulip_stream,
             zulipTopic: detailedEditedRoom.zulip_topic,
             isLocked: detailedEditedRoom.is_locked,
-            roomMode: detailedEditedRoom.room_mode,
+            roomMode:
+              detailedEditedRoom.platform === "daily"
+                ? "group"
+                : detailedEditedRoom.room_mode,
             recordingType: detailedEditedRoom.recording_type,
-            recordingTrigger: detailedEditedRoom.recording_trigger,
+            recordingTrigger:
+              detailedEditedRoom.platform === "daily"
+                ? detailedEditedRoom.recording_type === "cloud"
+                  ? "automatic-2nd-participant"
+                  : "none"
+                : 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,
+            skipConsent: detailedEditedRoom.skip_consent || false,
           }
         : null,
     [detailedEditedRoom],
@@ -277,21 +302,33 @@ 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: room.roomMode,
+        room_mode: platform === "daily" ? "group" : room.roomMode,
         recording_type: room.recordingType,
-        recording_trigger: room.recordingTrigger,
+        recording_trigger:
+          platform === "daily"
+            ? room.recordingType === "cloud"
+              ? "automatic-2nd-participant"
+              : "none"
+            : 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,
+        skip_consent: room.skipConsent,
       };
 
       if (isEditing) {
@@ -339,15 +376,22 @@ export default function RoomsList() {
       zulipStream: roomData.zulip_stream,
       zulipTopic: roomData.zulip_topic,
       isLocked: roomData.is_locked,
-      roomMode: roomData.room_mode,
+      roomMode: roomData.platform === "daily" ? "group" : roomData.room_mode, // Daily always uses 2-200
       recordingType: roomData.recording_type,
-      recordingTrigger: roomData.recording_trigger,
+      recordingTrigger:
+        roomData.platform === "daily"
+          ? roomData.recording_type === "cloud"
+            ? "automatic-2nd-participant"
+            : "none"
+          : 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,
+      skipConsent: roomData.skip_consent || false,
     });
     setEditRoomId(roomId);
     setIsEditing(true);
@@ -482,6 +526,52 @@ 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"
@@ -504,50 +594,95 @@ 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}>
-                      <Field.Label>Room size</Field.Label>
+                      <HStack gap={2} alignItems="center">
-                      <Select.Root
+                        <Field.Label>Recording type</Field.Label>
-                        value={[room.roomMode]}
+                        <Popover.Root>
-                        onValueChange={(e) =>
+                          <Popover.Trigger asChild>
-                          setRoomInput({ ...room, roomMode: e.value[0] })
+                            <IconButton
-                        }
+                              aria-label="Recording type help"
-                        collection={roomModeCollection}
+                              variant="ghost"
-                      >
+                              size="xs"
-                        <Select.HiddenSelect />
+                              colorPalette="gray"
-                        <Select.Control>
+                            >
-                          <Select.Trigger>
+                              <LuInfo />
-                            <Select.ValueText placeholder="Select room size" />
+                            </IconButton>
-                          </Select.Trigger>
+                          </Popover.Trigger>
-                          <Select.IndicatorGroup>
+                          <Popover.Positioner>
-                            <Select.Indicator />
+                            <Popover.Content>
-                          </Select.IndicatorGroup>
+                              <Popover.Arrow />
-                        </Select.Control>
+                              <Popover.Body>
-                        <Select.Positioner>
+                                <Text fontSize="sm" lineHeight="1.6">
-                          <Select.Content>
+                                  <strong>None:</strong> No recording will be
-                            {roomModeOptions.map((option) => (
+                                  created.
-                              <Select.Item key={option.value} item={option}>
+                                  <br />
-                                {option.label}
+                                  <br />
-                                <Select.ItemIndicator />
+                                  <strong>Local:</strong> Recording happens on
-                              </Select.Item>
+                                  each participant's device. Files are saved
-                            ))}
+                                  locally.
-                          </Select.Content>
+                                  <br />
-                        </Select.Positioner>
+                                  <br />
-                      </Select.Root>
+                                  <strong>Cloud:</strong> Recording happens on
-                    </Field.Root>
+                                  the platform's servers and is available after
-                    <Field.Root mt={4}>
+                                  the meeting ends.
-                      <Field.Label>Recording type</Field.Label>
+                                </Text>
+                              </Popover.Body>
+                            </Popover.Content>
+                          </Popover.Positioner>
+                        </Popover.Root>
+                      </HStack>
                       <Select.Root
                         value={[room.recordingType]}
-                        onValueChange={(e) =>
+                        onValueChange={(e) => {
-                          setRoomInput({
+                          const newRecordingType = e.value[0];
-                            ...room,
+                          const updates: Partial<typeof room> = {
-                            recordingType: e.value[0],
+                            recordingType: newRecordingType,
-                            recordingTrigger:
+                          };
-                              e.value[0] !== "cloud"
+                          if (room.platform === "daily") {
+                            updates.recordingTrigger =
+                              newRecordingType === "cloud"
+                                ? "automatic-2nd-participant"
+                                : "none";
+                          } else {
+                            updates.recordingTrigger =
+                              newRecordingType !== "cloud"
                                 ? "none"
-                                : room.recordingTrigger,
+                                : room.recordingTrigger;
-                          })
+                          }
-                        }
+                          setRoomInput({ ...room, ...updates });
+                        }}
                         collection={recordingTypeCollection}
                       >
                         <Select.HiddenSelect />
@@ -571,40 +706,77 @@ export default function RoomsList() {
                         </Select.Positioner>
                       </Select.Root>
                     </Field.Root>
-                    <Field.Root mt={4}>
+                    {room.recordingType === "cloud" &&
-                      <Field.Label>Cloud recording start trigger</Field.Label>
+                      room.platform !== "daily" && (
-                      <Select.Root
+                        <Field.Root mt={4}>
-                        value={[room.recordingTrigger]}
+                          <HStack gap={2} alignItems="center">
-                        onValueChange={(e) =>
+                            <Field.Label>Recording start trigger</Field.Label>
-                          setRoomInput({
+                            <Popover.Root>
-                            ...room,
+                              <Popover.Trigger asChild>
-                            recordingTrigger: e.value[0],
+                                <IconButton
-                          })
+                                  aria-label="Recording start trigger help"
-                        }
+                                  variant="ghost"
-                        collection={recordingTriggerCollection}
+                                  size="xs"
-                        disabled={room.recordingType !== "cloud"}
+                                  colorPalette="gray"
-                      >
+                                >
-                        <Select.HiddenSelect />
+                                  <LuInfo />
-                        <Select.Control>
+                                </IconButton>
-                          <Select.Trigger>
+                              </Popover.Trigger>
-                            <Select.ValueText placeholder="Select trigger" />
+                              <Popover.Positioner>
-                          </Select.Trigger>
+                                <Popover.Content>
-                          <Select.IndicatorGroup>
+                                  <Popover.Arrow />
-                            <Select.Indicator />
+                                  <Popover.Body>
-                          </Select.IndicatorGroup>
+                                    <Text fontSize="sm" lineHeight="1.6">
-                        </Select.Control>
+                                      <strong>None:</strong> Recording must be
-                        <Select.Positioner>
+                                      started manually by a participant.
-                          <Select.Content>
+                                      <br />
-                            {recordingTriggerOptions.map((option) => (
+                                      <br />
-                              <Select.Item key={option.value} item={option}>
+                                      <strong>Prompt:</strong> Participants will
-                                {option.label}
+                                      be prompted to start recording when they
-                                <Select.ItemIndicator />
+                                      join.
-                              </Select.Item>
+                                      <br />
-                            ))}
+                                      <br />
-                          </Select.Content>
+                                      <strong>Automatic:</strong> Recording
-                        </Select.Positioner>
+                                      starts automatically when a second
-                      </Select.Root>
+                                      participant joins.
-                    </Field.Root>
+                                    </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}>
                       <Checkbox.Root
@@ -628,6 +800,34 @@ export default function RoomsList() {
                         <Checkbox.Label>Shared room</Checkbox.Label>
                       </Checkbox.Root>
                     </Field.Root>
+                    {room.recordingType === "cloud" && (
+                      <Field.Root mt={4}>
+                        <Checkbox.Root
+                          name="skipConsent"
+                          checked={room.skipConsent}
+                          onCheckedChange={(e) => {
+                            const syntheticEvent = {
+                              target: {
+                                name: "skipConsent",
+                                type: "checkbox",
+                                checked: e.checked,
+                              },
+                            };
+                            handleRoomChange(syntheticEvent);
+                          }}
+                        >
+                          <Checkbox.HiddenInput />
+                          <Checkbox.Control>
+                            <Checkbox.Indicator />
+                          </Checkbox.Control>
+                          <Checkbox.Label>Skip consent dialog</Checkbox.Label>
+                        </Checkbox.Root>
+                        <Field.HelperText>
+                          When enabled, participants won't be asked for
+                          recording consent. Audio will be stored automatically.
+                        </Field.HelperText>
+                      </Field.Root>
+                    )}
                   </Tabs.Content>
 
                   <Tabs.Content value="share" pt={6}>

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

@@ -10,7 +10,15 @@ import FinalSummary from "./finalSummary";
 import TranscriptTitle from "../transcriptTitle";
 import Player from "../player";
 import { useRouter } from "next/navigation";
-import { Box, Flex, Grid, GridItem, Skeleton, Text } from "@chakra-ui/react";
+import {
+  Box,
+  Flex,
+  Grid,
+  GridItem,
+  Skeleton,
+  Text,
+  Spinner,
+} from "@chakra-ui/react";
 import { useTranscriptGet } from "../../../lib/apiHooks";
 import { TranscriptStatus } from "../../../lib/transcript";
 
@@ -28,6 +36,7 @@ export default function TranscriptDetails(details: TranscriptDetails) {
     "idle",
     "recording",
     "processing",
+    "uploaded",
   ] satisfies TranscriptStatus[] as TranscriptStatus[];
 
   const transcript = useTranscriptGet(transcriptId);
@@ -45,15 +54,55 @@ export default function TranscriptDetails(details: TranscriptDetails) {
     useState<HTMLDivElement | null>(null);
 
   useEffect(() => {
-    if (waiting) {
+    if (!waiting || !transcript.data) return;
-      const newUrl = "/transcripts/" + params.transcriptId + "/record";
+
+    const status = transcript.data.status;
+    let newUrl: string | null = null;
+
+    if (status === "processing" || status === "uploaded") {
+      newUrl = `/transcripts/${params.transcriptId}/processing`;
+    } else if (status === "recording") {
+      newUrl = `/transcripts/${params.transcriptId}/record`;
+    } else if (status === "idle") {
+      newUrl =
+        transcript.data.source_kind === "file"
+          ? `/transcripts/${params.transcriptId}/upload`
+          : `/transcripts/${params.transcriptId}/record`;
+    }
+
+    if (newUrl) {
       // Shallow redirection does not work on NextJS 13
       // https://github.com/vercel/next.js/discussions/48110
       // https://github.com/vercel/next.js/discussions/49540
       router.replace(newUrl);
-      // history.replaceState({}, "", newUrl);
     }
-  }, [waiting]);
+  }, [waiting, transcript.data?.status, transcript.data?.source_kind]);
+
+  if (waiting) {
+    return (
+      <Box>
+        <Box
+          w="full"
+          background="gray.bg"
+          border={"2px solid"}
+          borderColor={"gray.bg"}
+          borderRadius={8}
+          p={6}
+          minH="100%"
+          display="flex"
+          alignItems="center"
+          justifyContent="center"
+        >
+          <Flex direction="column" align="center" gap={3}>
+            <Spinner size="xl" color="blue.500" />
+            <Text color="gray.600" textAlign="center">
+              Loading transcript...
+            </Text>
+          </Flex>
+        </Box>
+      </Box>
+    );
+  }
 
   if (transcript.error || topics?.error) {
     return (
@@ -68,15 +117,6 @@ 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
@@ -98,7 +138,12 @@ export default function TranscriptDetails(details: TranscriptDetails) {
               />
             ) : !mp3.loading && (waveform.error || mp3.error) ? (
               <Box p={4} bg="red.100" borderRadius="md">
-                <Text>Error loading this recording</Text>
+                <Text>
+                  Error loading{" "}
+                  {[waveform.error && "waveform", mp3.error && "mp3"]
+                    .filter(Boolean)
+                    .join(" and ")}
+                </Text>
               </Box>
             ) : (
               <Skeleton h={14} />

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

@@ -0,0 +1,97 @@
+"use client";
+import { useEffect, use } from "react";
+import {
+  Heading,
+  Text,
+  VStack,
+  Spinner,
+  Button,
+  Center,
+} from "@chakra-ui/react";
+import { useRouter } from "next/navigation";
+import { useTranscriptGet } from "../../../../lib/apiHooks";
+
+type TranscriptProcessing = {
+  params: Promise<{
+    transcriptId: string;
+  }>;
+};
+
+export default function TranscriptProcessing(details: TranscriptProcessing) {
+  const params = use(details.params);
+  const transcriptId = params.transcriptId;
+  const router = useRouter();
+
+  const transcript = useTranscriptGet(transcriptId);
+
+  useEffect(() => {
+    const status = transcript.data?.status;
+    if (!status) return;
+
+    if (status === "ended" || status === "error") {
+      router.replace(`/transcripts/${transcriptId}`);
+    } else if (status === "recording") {
+      router.replace(`/transcripts/${transcriptId}/record`);
+    } else if (status === "idle") {
+      const dest =
+        transcript.data?.source_kind === "file"
+          ? `/transcripts/${transcriptId}/upload`
+          : `/transcripts/${transcriptId}/record`;
+      router.replace(dest);
+    }
+  }, [
+    transcript.data?.status,
+    transcript.data?.source_kind,
+    router,
+    transcriptId,
+  ]);
+
+  if (transcript.isLoading) {
+    return (
+      <VStack align="center" py={8}>
+        <Heading size="lg">Loading transcript...</Heading>
+      </VStack>
+    );
+  }
+
+  if (transcript.error) {
+    return (
+      <VStack align="center" py={8}>
+        <Heading size="lg">Transcript not found</Heading>
+        <Text>We couldn't load this transcript.</Text>
+      </VStack>
+    );
+  }
+
+  return (
+    <>
+      <VStack
+        align={"left"}
+        minH="100vh"
+        pt={4}
+        mx="auto"
+        w={{ base: "full", md: "container.xl" }}
+      >
+        <Center h={"full"} w="full">
+          <VStack gap={10} bg="gray.100" p={10} borderRadius="md" maxW="500px">
+            <Spinner size="xl" color="blue.500" />
+            <Heading size={"md"} textAlign="center">
+              Processing recording
+            </Heading>
+            <Text color="gray.600" textAlign="center">
+              You can safely return to the library while your recording is being
+              processed.
+            </Text>
+            <Button
+              onClick={() => {
+                router.push("/browse");
+              }}
+            >
+              Browse
+            </Button>
+          </VStack>
+        </Center>
+      </VStack>
+    </>
+  );
+}

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

@@ -4,7 +4,7 @@ import { useWebSockets } from "../../useWebSockets";
 import { lockWakeState, releaseWakeState } from "../../../../lib/wakeLock";
 import { useRouter } from "next/navigation";
 import useMp3 from "../../useMp3";
-import { Center, VStack, Text, Heading, Button } from "@chakra-ui/react";
+import { Center, VStack, Text, Heading } from "@chakra-ui/react";
 import FileUploadButton from "../../fileUploadButton";
 import { useTranscriptGet } from "../../../../lib/apiHooks";
 
@@ -53,6 +53,12 @@ const TranscriptUpload = (details: TranscriptUpload) => {
 
       const newUrl = "/transcripts/" + params.transcriptId;
       router.replace(newUrl);
+    } else if (
+      newStatus &&
+      (newStatus == "uploaded" || newStatus == "processing")
+    ) {
+      // After upload finishes (or if already processing), redirect to the unified processing page
+      router.replace(`/transcripts/${params.transcriptId}/processing`);
     }
   }, [webSockets.status?.value, transcript.data?.status]);
 
@@ -71,7 +77,7 @@ const TranscriptUpload = (details: TranscriptUpload) => {
     <>
       <VStack
         align={"left"}
-        h="full"
+        minH="100vh"
         pt={4}
         mx="auto"
         w={{ base: "full", md: "container.xl" }}
@@ -79,34 +85,16 @@ const TranscriptUpload = (details: TranscriptUpload) => {
         <Heading size={"lg"}>Upload meeting</Heading>
         <Center h={"full"} w="full">
           <VStack gap={10} bg="gray.100" p={10} borderRadius="md" maxW="500px">
-            {status && status == "idle" && (
+            <Text>
-              <>
+              Please select the file, supported formats: .mp3, m4a, .wav, .mp4,
-                <Text>
+              .mov or .webm
-                  Please select the file, supported formats: .mp3, m4a, .wav,
+            </Text>
-                  .mp4, .mov or .webm
+            <FileUploadButton
-                </Text>
+              transcriptId={params.transcriptId}
-                <FileUploadButton transcriptId={params.transcriptId} />
+              onUploadComplete={() =>
-              </>
+                router.replace(`/transcripts/${params.transcriptId}/processing`)
-            )}
+              }
-            {status && status == "uploaded" && (
+            />
-              <Text>File is uploaded, processing...</Text>
-            )}
-            {(status == "recording" || status == "processing") && (
-              <>
-                <Heading size={"lg"}>Processing your recording...</Heading>
-                <Text>
-                  You can safely return to the library while your file is being
-                  processed.
-                </Text>
-                <Button
-                  onClick={() => {
-                    router.push("/browse");
-                  }}
-                >
-                  Browse
-                </Button>
-              </>
-            )}
           </VStack>
         </Center>
       </VStack>

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

@@ -0,0 +1,60 @@
+import type { components } from "../../reflector-api";
+import { formatTime } from "../../lib/time";
+
+type GetTranscriptTopic = components["schemas"]["GetTranscriptTopic"];
+type Participant = components["schemas"]["Participant"];
+
+function getSpeakerName(
+  speakerNumber: number,
+  participants?: Participant[] | null,
+): string {
+  const name = participants?.find((p) => p.speaker === speakerNumber)?.name;
+  return name && name.trim().length > 0 ? name : `Speaker ${speakerNumber}`;
+}
+
+export function buildTranscriptWithTopics(
+  topics: GetTranscriptTopic[],
+  participants?: Participant[] | null,
+  transcriptTitle?: string | null,
+): string {
+  const blocks: string[] = [];
+
+  if (transcriptTitle && transcriptTitle.trim()) {
+    blocks.push(`# ${transcriptTitle.trim()}`);
+    blocks.push("");
+  }
+
+  for (const topic of topics) {
+    // Topic header
+    const topicTime = formatTime(Math.floor(topic.timestamp || 0));
+    const title = topic.title?.trim() || "Untitled Topic";
+    blocks.push(`## ${title} [${topicTime}]`);
+
+    if (topic.segments && topic.segments.length > 0) {
+      for (const seg of topic.segments) {
+        const ts = formatTime(Math.floor(seg.start || 0));
+        const speaker = getSpeakerName(seg.speaker as number, participants);
+        const text = (seg.text || "").replace(/\s+/g, " ").trim();
+        if (text) {
+          blocks.push(`[${ts}] ${speaker}: ${text}`);
+        }
+      }
+    } else if (topic.transcript) {
+      // Fallback: plain transcript when segments are not present
+      const text = topic.transcript.replace(/\s+/g, " ").trim();
+      if (text) {
+        blocks.push(text);
+      }
+    }
+
+    // Blank line between topics
+    blocks.push("");
+  }
+
+  // Trim trailing blank line
+  while (blocks.length > 0 && blocks[blocks.length - 1] === "") {
+    blocks.pop();
+  }
+
+  return blocks.join("\n");
+}

www/app/(app)/transcripts/fileUploadButton.tsx

@@ -5,6 +5,7 @@ import { useError } from "../../(errors)/errorContext";
 
 type FileUploadButton = {
   transcriptId: string;
+  onUploadComplete?: () => void;
 };
 
 export default function FileUploadButton(props: FileUploadButton) {
@@ -31,6 +32,7 @@ export default function FileUploadButton(props: FileUploadButton) {
       const uploadNextChunk = async () => {
         if (chunkNumber == totalChunks) {
           setProgress(0);
+          props.onUploadComplete?.();
           return;
         }
 

www/app/(app)/transcripts/shareCopy.tsx

@@ -1,12 +1,16 @@
 import { useState } from "react";
-import type { components } from "../../reflector-api";
+import type { components, operations } from "../../reflector-api";
-type GetTranscript = components["schemas"]["GetTranscript"];
+type GetTranscriptWithParticipants =
+  components["schemas"]["GetTranscriptWithParticipants"];
 type GetTranscriptTopic = components["schemas"]["GetTranscriptTopic"];
-import { Button, BoxProps, Box } from "@chakra-ui/react";
+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";
 
 type ShareCopyProps = {
   finalSummaryElement: HTMLDivElement | null;
-  transcript: GetTranscript;
+  transcript: GetTranscriptWithParticipants;
   topics: GetTranscriptTopic[];
 };
 
@@ -18,10 +22,33 @@ 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 onCopySummaryClick = () => {
     const text_to_copy = finalSummaryElement?.innerText;
-
     if (text_to_copy) {
       navigator.clipboard.writeText(text_to_copy).then(() => {
         setIsCopiedSummary(true);
@@ -31,27 +58,91 @@ export default function ShareCopy({
     }
   };
 
-  const onCopyTranscriptClick = () => {
+  const onCopyTranscriptFormatClick = async (format: TranscriptFormat) => {
-    let text_to_copy =
+    try {
-      topics
+      setIsCopying(true);
-        ?.map((topic) => topic.transcript)
+      const { data, error } = await client.GET(
-        .join("\n\n")
+        "/v1/transcripts/{transcript_id}",
-        .replace(/ +/g, " ")
+        {
-        .trim() || "";
+          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;
+      }
 
-    text_to_copy &&
+      const copiedText =
-      navigator.clipboard.writeText(text_to_copy).then(() => {
+        format === "json"
+          ? JSON.stringify(data?.transcript ?? {}, null, 2)
+          : String(data?.transcript ?? "");
+
+      if (copiedText) {
+        await navigator.clipboard.writeText(copiedText);
         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}>
-      <Button onClick={onCopyTranscriptClick} mr={2} variant="subtle">
+      <Menu.Root
-        {isCopiedTranscript ? "Copied!" : "Copy Transcript"}
+        closeOnSelect={true}
-      </Button>
+        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={onCopySummaryClick} variant="subtle">
         {isCopiedSummary ? "Copied!" : "Copy Summary"}
       </Button>

www/app/(app)/transcripts/transcriptTitle.tsx

@@ -4,10 +4,15 @@ import type { components } from "../../reflector-api";
 type UpdateTranscript = components["schemas"]["UpdateTranscript"];
 type GetTranscript = components["schemas"]["GetTranscript"];
 type GetTranscriptTopic = components["schemas"]["GetTranscriptTopic"];
-import { useTranscriptUpdate } from "../../lib/apiHooks";
+import {
+  useTranscriptUpdate,
+  useTranscriptParticipants,
+} from "../../lib/apiHooks";
 import { Heading, IconButton, Input, Flex, Spacer } from "@chakra-ui/react";
-import { LuPen } from "react-icons/lu";
+import { LuPen, LuCopy, LuCheck } from "react-icons/lu";
 import ShareAndPrivacy from "./shareAndPrivacy";
+import { buildTranscriptWithTopics } from "./buildTranscriptWithTopics";
+import { toaster } from "../../components/ui/toaster";
 
 type TranscriptTitle = {
   title: string;
@@ -25,6 +30,9 @@ const TranscriptTitle = (props: TranscriptTitle) => {
   const [preEditTitle, setPreEditTitle] = useState(props.title);
   const [isEditing, setIsEditing] = useState(false);
   const updateTranscriptMutation = useTranscriptUpdate();
+  const participantsQuery = useTranscriptParticipants(
+    props.transcript?.id || null,
+  );
 
   const updateTitle = async (newTitle: string, transcriptId: string) => {
     try {
@@ -118,11 +126,57 @@ const TranscriptTitle = (props: TranscriptTitle) => {
             <LuPen />
           </IconButton>
           {props.transcript && props.topics && (
-            <ShareAndPrivacy
+            <>
-              finalSummaryElement={props.finalSummaryElement}
+              <IconButton
-              transcript={props.transcript}
+                aria-label="Copy Transcript"
-              topics={props.topics}
+                size="sm"
-            />
+                variant="subtle"
+                onClick={() => {
+                  const text = buildTranscriptWithTopics(
+                    props.topics || [],
+                    participantsQuery?.data || null,
+                    props.transcript?.title || null,
+                  );
+                  if (!text) return;
+                  navigator.clipboard
+                    .writeText(text)
+                    .then(() => {
+                      toaster
+                        .create({
+                          placement: "top",
+                          duration: 2500,
+                          render: () => (
+                            <div className="chakra-ui-light">
+                              <div
+                                style={{
+                                  background: "#38A169",
+                                  color: "white",
+                                  padding: "8px 12px",
+                                  borderRadius: 6,
+                                  display: "flex",
+                                  alignItems: "center",
+                                  gap: 8,
+                                  boxShadow: "rgba(0,0,0,0.25) 0px 4px 12px",
+                                }}
+                              >
+                                <LuCheck /> Transcript copied
+                              </div>
+                            </div>
+                          ),
+                        })
+                        .then(() => {});
+                    })
+                    .catch(() => {});
+                }}
+              >
+                <LuCopy />
+              </IconButton>
+              <ShareAndPrivacy
+                finalSummaryElement={props.finalSummaryElement}
+                transcript={props.transcript}
+                topics={props.topics}
+              />
+            </>
           )}
         </Flex>
       )}

www/app/(auth)/userInfo.tsx

@@ -13,9 +13,12 @@ export default function UserInfo() {
     <Spinner size="xs" className="mx-3" />
   ) : !isAuthenticated && !isRefreshing ? (
     <Link
-      href="/"
+      href="#"
       className="font-light px-2"
-      onClick={() => auth.signIn("authentik")}
+      onClick={(e) => {
+        e.preventDefault();
+        auth.signIn("authentik");
+      }}
     >
       Log in
     </Link>

www/app/[roomName]/MeetingSelection.tsx

@@ -26,6 +26,7 @@ import { useRouter } from "next/navigation";
 import { formatDateTime, formatStartedAgo } from "../lib/timeUtils";
 import MeetingMinimalHeader from "../components/MeetingMinimalHeader";
 import { NonEmptyString } from "../lib/utils";
+import { MeetingId } from "../lib/types";
 
 type Meeting = components["schemas"]["Meeting"];
 
@@ -98,7 +99,7 @@ export default function MeetingSelection({
     onMeetingSelect(meeting);
   };
 
-  const handleEndMeeting = async (meetingId: string) => {
+  const handleEndMeeting = async (meetingId: MeetingId) => {
     try {
       await deactivateMeetingMutation.mutateAsync({
         params: {

www/app/[roomName]/components/DailyRoom.tsx

@@ -1,82 +1,318 @@
 "use client";
 
-import { useCallback, useEffect, useRef } from "react";
+import {
-import { Box } from "@chakra-ui/react";
+  RefObject,
-import { useRouter } from "next/navigation";
+  useCallback,
-import DailyIframe, { DailyCall } from "@daily-co/daily-js";
+  useEffect,
+  useMemo,
+  useRef,
+  useState,
+} from "react";
+import { Box, Spinner, Center, Text } from "@chakra-ui/react";
+import { useRouter, useParams } from "next/navigation";
+import DailyIframe, {
+  DailyCall,
+  DailyCallOptions,
+  DailyCustomTrayButton,
+  DailyCustomTrayButtons,
+  DailyEventObjectCustomButtonClick,
+  DailyFactoryOptions,
+  DailyParticipantsObject,
+} from "@daily-co/daily-js";
 import type { components } from "../../reflector-api";
 import { useAuth } from "../../lib/AuthProvider";
-import {
+import { useConsentDialog } from "../../lib/consent";
-  ConsentDialogButton,
+import { useRoomJoinMeeting } from "../../lib/apiHooks";
-  recordingTypeRequiresConsent,
+import { omit } from "remeda";
-} from "../../lib/consent";
+import { assertExists } from "../../lib/utils";
+import { assertMeetingId } from "../../lib/types";
+
+const CONSENT_BUTTON_ID = "recording-consent";
+const RECORDING_INDICATOR_ID = "recording-indicator";
 
 type Meeting = components["schemas"]["Meeting"];
+type Room = components["schemas"]["RoomDetails"];
 
-interface DailyRoomProps {
+type DailyRoomProps = {
   meeting: Meeting;
-}
+  room: Room;
+};
 
-export default function DailyRoom({ meeting }: DailyRoomProps) {
+const useCustomTrayButtons = (
+  frame: {
+    updateCustomTrayButtons: (
+      customTrayButtons: DailyCustomTrayButtons,
+    ) => void;
+    joined: boolean;
+  } | null,
+) => {
+  const [, setCustomTrayButtons] = useState<DailyCustomTrayButtons>({});
+  return useCallback(
+    (id: string, button: DailyCustomTrayButton | null) => {
+      setCustomTrayButtons((prev) => {
+        // would blink state when frame blinks but it's ok here
+        const state =
+          button === null ? omit(prev, [id]) : { ...prev, [id]: button };
+        if (frame !== null && frame.joined)
+          frame.updateCustomTrayButtons(state);
+        return state;
+      });
+    },
+    [setCustomTrayButtons, frame],
+  );
+};
+
+const USE_FRAME_INIT_STATE = {
+  frame: null as DailyCall | null,
+  joined: false as boolean,
+} as const;
+
+// Daily js and not Daily react used right now because daily-js allows for prebuild interface vs. -react is customizable but has no nice defaults
+const useFrame = (
+  container: HTMLDivElement | null,
+  cbs: {
+    onLeftMeeting: () => void;
+    onCustomButtonClick: (ev: DailyEventObjectCustomButtonClick) => void;
+    onJoinMeeting: (
+      startRecording: (args: { type: "raw-tracks" }) => void,
+    ) => void;
+  },
+) => {
+  const [{ frame, joined }, setState] = useState(USE_FRAME_INIT_STATE);
+  const setJoined = useCallback(
+    (joined: boolean) => setState((prev) => ({ ...prev, joined })),
+    [setState],
+  );
+  const setFrame = useCallback(
+    (frame: DailyCall | null) => setState((prev) => ({ ...prev, frame })),
+    [setState],
+  );
+  useEffect(() => {
+    if (!container) return;
+    const init = async () => {
+      const existingFrame = DailyIframe.getCallInstance();
+      if (existingFrame) {
+        console.error("existing daily frame present");
+        await existingFrame.destroy();
+      }
+      const frameOptions: DailyFactoryOptions = {
+        iframeStyle: {
+          width: "100vw",
+          height: "100vh",
+          border: "none",
+        },
+        showLeaveButton: true,
+        showFullscreenButton: true,
+      };
+      const frame = DailyIframe.createFrame(container, frameOptions);
+      setFrame(frame);
+    };
+    init().catch(
+      console.error.bind(console, "Failed to initialize daily frame:"),
+    );
+    return () => {
+      frame
+        ?.destroy()
+        .catch(console.error.bind(console, "Failed to destroy daily frame:"));
+      setState(USE_FRAME_INIT_STATE);
+    };
+  }, [container]);
+  useEffect(() => {
+    if (!frame) return;
+    frame.on("left-meeting", cbs.onLeftMeeting);
+    frame.on("custom-button-click", cbs.onCustomButtonClick);
+    const joinCb = () => {
+      if (!frame) {
+        console.error("frame is null in joined-meeting callback");
+        return;
+      }
+      cbs.onJoinMeeting(frame.startRecording.bind(frame));
+    };
+    frame.on("joined-meeting", joinCb);
+    return () => {
+      frame.off("left-meeting", cbs.onLeftMeeting);
+      frame.off("custom-button-click", cbs.onCustomButtonClick);
+      frame.off("joined-meeting", joinCb);
+    };
+  }, [frame, cbs]);
+  const frame_ = useMemo(() => {
+    if (frame === null) return frame;
+    return {
+      join: async (
+        properties?: DailyCallOptions,
+      ): Promise<DailyParticipantsObject | void> => {
+        await frame.join(properties);
+        setJoined(!frame.isDestroyed());
+      },
+      updateCustomTrayButtons: (
+        customTrayButtons: DailyCustomTrayButtons,
+      ): DailyCall => frame.updateCustomTrayButtons(customTrayButtons),
+    };
+  }, [frame]);
+  const setCustomTrayButton = useCustomTrayButtons(
+    useMemo(() => {
+      if (frame_ === null) return null;
+      return {
+        updateCustomTrayButtons: frame_.updateCustomTrayButtons,
+        joined,
+      };
+    }, [frame_, joined]),
+  );
+  return [
+    frame_,
+    {
+      setCustomTrayButton,
+    },
+  ] as const;
+};
+
+export default function DailyRoom({ meeting, room }: DailyRoomProps) {
   const router = useRouter();
+  const params = useParams();
   const auth = useAuth();
-  const status = auth.status;
+  const authLastUserId = auth.lastUserId;
-  const containerRef = useRef<HTMLDivElement>(null);
+  const [container, setContainer] = useState<HTMLDivElement | null>(null);
+  const joinMutation = useRoomJoinMeeting();
+  const [joinedMeeting, setJoinedMeeting] = useState<Meeting | null>(null);
 
-  const roomUrl = meeting?.host_room_url || meeting?.room_url;
+  const roomName = params?.roomName as string;
 
-  const isLoading = status === "loading";
+  const {
+    showConsentModal,
+    showRecordingIndicator: showRecordingInTray,
+    showConsentButton,
+  } = useConsentDialog({
+    meetingId: assertMeetingId(meeting.id),
+    recordingType: meeting.recording_type,
+    skipConsent: room.skip_consent,
+  });
+  const showConsentModalRef = useRef(showConsentModal);
+  showConsentModalRef.current = showConsentModal;
+
+  useEffect(() => {
+    if (authLastUserId === undefined || !meeting?.id || !roomName) return;
+
+    const join = async () => {
+      try {
+        const result = await joinMutation.mutateAsync({
+          params: {
+            path: {
+              room_name: roomName,
+              meeting_id: meeting.id,
+            },
+          },
+        });
+        setJoinedMeeting(result);
+      } catch (error) {
+        console.error("Failed to join meeting:", error);
+      }
+    };
+
+    join().catch(console.error.bind(console, "Failed to join meeting:"));
+  }, [meeting?.id, roomName, authLastUserId]);
+
+  const roomUrl = joinedMeeting?.room_url;
 
   const handleLeave = useCallback(() => {
     router.push("/browse");
   }, [router]);
 
-  useEffect(() => {
+  const handleCustomButtonClick = useCallback(
-    if (isLoading || !roomUrl || !containerRef.current) return;
+    (ev: DailyEventObjectCustomButtonClick) => {
+      if (ev.button_id === CONSENT_BUTTON_ID) {
+        showConsentModalRef.current();
+      }
+    },
+    [
+      /*keep static; iframe recreation depends on it*/
+    ],
+  );
 
-    let frame: DailyCall | null = null;
+  const handleFrameJoinMeeting = useCallback(
-    let destroyed = false;
+    (startRecording: (args: { type: "raw-tracks" }) => void) => {
-
-    const createAndJoin = async () => {
       try {
-        const existingFrame = DailyIframe.getCallInstance();
+        if (meeting.recording_type === "cloud") {
-        if (existingFrame) {
+          console.log("Starting cloud recording");
-          await existingFrame.destroy();
+          startRecording({ type: "raw-tracks" });
         }
-
-        frame = DailyIframe.createFrame(containerRef.current!, {
-          iframeStyle: {
-            width: "100vw",
-            height: "100vh",
-            border: "none",
-          },
-          showLeaveButton: true,
-          showFullscreenButton: true,
-        });
-
-        if (destroyed) {
-          await frame.destroy();
-          return;
-        }
-
-        frame.on("left-meeting", handleLeave);
-        await frame.join({ url: roomUrl });
       } catch (error) {
-        console.error("Error creating Daily frame:", error);
+        console.error("Failed to start recording:", error);
       }
-    };
+    },
+    [meeting.recording_type],
+  );
 
-    createAndJoin();
+  const recordingIconUrl = useMemo(
+    () => new URL("/recording-icon.svg", window.location.origin),
+    [],
+  );
 
-    return () => {
+  const [frame, { setCustomTrayButton }] = useFrame(container, {
-      destroyed = true;
+    onLeftMeeting: handleLeave,
-      if (frame) {
+    onCustomButtonClick: handleCustomButtonClick,
-        frame.destroy().catch((e) => {
+    onJoinMeeting: handleFrameJoinMeeting,
-          console.error("Error destroying frame:", e);
+  });
-        });
+
-      }
+  useEffect(() => {
-    };
+    if (!frame || !roomUrl) return;
-  }, [roomUrl, isLoading, handleLeave]);
+    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
+        },
+      })
+      .catch(console.error.bind(console, "Failed to join daily room:"));
+  }, [frame, roomUrl]);
+
+  useEffect(() => {
+    setCustomTrayButton(
+      RECORDING_INDICATOR_ID,
+      showRecordingInTray
+        ? {
+            iconPath: recordingIconUrl.href,
+            label: "Recording",
+            tooltip: "Recording in progress",
+          }
+        : null,
+    );
+  }, [showRecordingInTray, recordingIconUrl, setCustomTrayButton]);
+
+  useEffect(() => {
+    setCustomTrayButton(
+      CONSENT_BUTTON_ID,
+      showConsentButton
+        ? {
+            iconPath: recordingIconUrl.href,
+            label: "Recording (click to consent)",
+            tooltip: "Recording (click to consent)",
+          }
+        : null,
+    );
+  }, [showConsentButton, recordingIconUrl, setCustomTrayButton]);
+
+  if (authLastUserId === undefined) {
+    return (
+      <Center width="100vw" height="100vh">
+        <Spinner size="xl" />
+      </Center>
+    );
+  }
+
+  if (joinMutation.isError) {
+    return (
+      <Center width="100vw" height="100vh">
+        <Text color="red.500">Failed to join meeting. Please try again.</Text>
+      </Center>
+    );
+  }
 
   if (!roomUrl) {
     return null;
@@ -84,10 +320,7 @@ export default function DailyRoom({ meeting }: DailyRoomProps) {
 
   return (
     <Box position="relative" width="100vw" height="100vh">
-      <div ref={containerRef} style={{ width: "100%", height: "100%" }} />
+      <div ref={setContainer} style={{ width: "100%", height: "100%" }} />
-      {meeting.recording_type &&
-        recordingTypeRequiresConsent(meeting.recording_type) &&
-        meeting.id && <ConsentDialogButton meetingId={meeting.id} />}
     </Box>
   );
 }

www/app/[roomName]/components/RoomContainer.tsx

@@ -18,6 +18,7 @@ import { useAuth } from "../../lib/AuthProvider";
 import { useError } from "../../(errors)/errorContext";
 import { parseNonEmptyString } from "../../lib/utils";
 import { printApiError } from "../../api/_error";
+import { assertMeetingId } from "../../lib/types";
 
 type Meeting = components["schemas"]["Meeting"];
 
@@ -67,7 +68,10 @@ export default function RoomContainer(details: RoomDetails) {
     room && !room.ics_enabled && !pageMeetingId ? roomName : null,
   );
 
-  const explicitMeeting = useRoomGetMeeting(roomName, pageMeetingId || null);
+  const explicitMeeting = useRoomGetMeeting(
+    roomName,
+    pageMeetingId ? assertMeetingId(pageMeetingId) : null,
+  );
 
   const meeting = explicitMeeting.data || defaultMeeting.response;
 
@@ -192,9 +196,9 @@ export default function RoomContainer(details: RoomDetails) {
 
   switch (platform) {
     case "daily":
-      return <DailyRoom meeting={meeting} />;
+      return <DailyRoom meeting={meeting} room={room} />;
     case "whereby":
-      return <WherebyRoom meeting={meeting} />;
+      return <WherebyRoom meeting={meeting} room={room} />;
     default: {
       const _exhaustive: never = platform;
       return (

www/app/[roomName]/components/WherebyRoom.tsx

@@ -5,24 +5,29 @@ import { useRouter } from "next/navigation";
 import type { components } from "../../reflector-api";
 import { useAuth } from "../../lib/AuthProvider";
 import { getWherebyUrl, useWhereby } from "../../lib/wherebyClient";
-import { assertExistsAndNonEmptyString, NonEmptyString } from "../../lib/utils";
 import {
   ConsentDialogButton as BaseConsentDialogButton,
   useConsentDialog,
-  recordingTypeRequiresConsent,
 } from "../../lib/consent";
+import { assertMeetingId, MeetingId } from "../../lib/types";
 
 type Meeting = components["schemas"]["Meeting"];
+type Room = components["schemas"]["RoomDetails"];
 
 interface WherebyRoomProps {
   meeting: Meeting;
+  room: Room;
 }
 
 function WherebyConsentDialogButton({
   meetingId,
+  recordingType,
+  skipConsent,
   wherebyRef,
 }: {
-  meetingId: NonEmptyString;
+  meetingId: MeetingId;
+  recordingType: Meeting["recording_type"];
+  skipConsent: boolean;
   wherebyRef: React.RefObject<HTMLElement>;
 }) {
   const previousFocusRef = useRef<HTMLElement | null>(null);
@@ -45,10 +50,16 @@ function WherebyConsentDialogButton({
     };
   }, [wherebyRef]);
 
-  return <BaseConsentDialogButton meetingId={meetingId} />;
+  return (
+    <BaseConsentDialogButton
+      meetingId={meetingId}
+      recordingType={recordingType}
+      skipConsent={skipConsent}
+    />
+  );
 }
 
-export default function WherebyRoom({ meeting }: WherebyRoomProps) {
+export default function WherebyRoom({ meeting, room }: WherebyRoomProps) {
   const wherebyLoaded = useWhereby();
   const wherebyRef = useRef<HTMLElement>(null);
   const router = useRouter();
@@ -57,9 +68,14 @@ export default function WherebyRoom({ meeting }: WherebyRoomProps) {
   const isAuthenticated = status === "authenticated";
 
   const wherebyRoomUrl = getWherebyUrl(meeting);
-  const recordingType = meeting.recording_type;
   const meetingId = meeting.id;
 
+  const { showConsentButton } = useConsentDialog({
+    meetingId: assertMeetingId(meetingId),
+    recordingType: meeting.recording_type,
+    skipConsent: room.skip_consent,
+  });
+
   const isLoading = status === "loading";
 
   const handleLeave = useCallback(() => {
@@ -88,14 +104,14 @@ export default function WherebyRoom({ meeting }: WherebyRoomProps) {
         room={wherebyRoomUrl}
         style={{ width: "100vw", height: "100vh" }}
       />
-      {recordingType &&
+      {showConsentButton && (
-        recordingTypeRequiresConsent(recordingType) &&
+        <WherebyConsentDialogButton
-        meetingId && (
+          meetingId={assertMeetingId(meetingId)}
-          <WherebyConsentDialogButton
+          recordingType={meeting.recording_type}
-            meetingId={assertExistsAndNonEmptyString(meetingId)}
+          skipConsent={room.skip_consent}
-            wherebyRef={wherebyRef}
+          wherebyRef={wherebyRef}
-          />
+        />
-        )}
+      )}
     </>
   );
 }

www/app/[roomName]/room.tsx

@@ -6,7 +6,6 @@ import {
   useEffect,
   useRef,
   useState,
-  useContext,
   RefObject,
   use,
 } from "react";
@@ -25,8 +24,6 @@ import { useRecordingConsent } from "../recordingConsentContext";
 import {
   useMeetingAudioConsent,
   useRoomGetByName,
-  useRoomActiveMeetings,
-  useRoomUpcomingMeetings,
   useRoomsCreateMeeting,
   useRoomGetMeeting,
 } from "../lib/apiHooks";
@@ -39,12 +36,9 @@ import { FaBars } from "react-icons/fa6";
 import { useAuth } from "../lib/AuthProvider";
 import { getWherebyUrl, useWhereby } from "../lib/wherebyClient";
 import { useError } from "../(errors)/errorContext";
-import {
+import { parseNonEmptyString } from "../lib/utils";
-  assertExistsAndNonEmptyString,
-  NonEmptyString,
-  parseNonEmptyString,
-} from "../lib/utils";
 import { printApiError } from "../api/_error";
+import { assertMeetingId, MeetingId } from "../lib/types";
 
 export type RoomDetails = {
   params: Promise<{
@@ -92,16 +86,16 @@ const useConsentWherebyFocusManagement = (
 };
 
 const useConsentDialog = (
-  meetingId: string,
+  meetingId: MeetingId,
   wherebyRef: RefObject<HTMLElement> /*accessibility*/,
 ) => {
-  const { state: consentState, touch, hasConsent } = useRecordingConsent();
+  const { state: consentState, touch, hasAnswered } = useRecordingConsent();
   // toast would open duplicates, even with using "id=" prop
   const [modalOpen, setModalOpen] = useState(false);
   const audioConsentMutation = useMeetingAudioConsent();
 
   const handleConsent = useCallback(
-    async (meetingId: string, given: boolean) => {
+    async (meetingId: MeetingId, given: boolean) => {
       try {
         await audioConsentMutation.mutateAsync({
           params: {
@@ -114,7 +108,7 @@ const useConsentDialog = (
           },
         });
 
-        touch(meetingId);
+        touch(meetingId, given);
       } catch (error) {
         console.error("Error submitting consent:", error);
       }
@@ -216,7 +210,7 @@ const useConsentDialog = (
   return {
     showConsentModal,
     consentState,
-    hasConsent,
+    hasAnswered,
     consentLoading: audioConsentMutation.isPending,
   };
 };
@@ -225,13 +219,13 @@ function ConsentDialogButton({
   meetingId,
   wherebyRef,
 }: {
-  meetingId: NonEmptyString;
+  meetingId: MeetingId;
   wherebyRef: React.RefObject<HTMLElement>;
 }) {
-  const { showConsentModal, consentState, hasConsent, consentLoading } =
+  const { showConsentModal, consentState, hasAnswered, consentLoading } =
     useConsentDialog(meetingId, wherebyRef);
 
-  if (!consentState.ready || hasConsent(meetingId) || consentLoading) {
+  if (!consentState.ready || hasAnswered(meetingId) || consentLoading) {
     return null;
   }
 
@@ -284,7 +278,10 @@ export default function Room(details: RoomDetails) {
     room && !room.ics_enabled && !pageMeetingId ? roomName : null,
   );
 
-  const explicitMeeting = useRoomGetMeeting(roomName, pageMeetingId || null);
+  const explicitMeeting = useRoomGetMeeting(
+    roomName,
+    pageMeetingId ? assertMeetingId(pageMeetingId) : null,
+  );
   const wherebyRoomUrl = explicitMeeting.data
     ? getWherebyUrl(explicitMeeting.data)
     : defaultMeeting.response
@@ -437,7 +434,7 @@ export default function Room(details: RoomDetails) {
             recordingTypeRequiresConsent(recordingType) &&
             meetingId && (
               <ConsentDialogButton
-                meetingId={assertExistsAndNonEmptyString(meetingId)}
+                meetingId={assertMeetingId(meetingId)}
                 wherebyRef={wherebyRef}
               />
             )}

www/app/lib/AuthProvider.tsx

@@ -1,6 +1,6 @@
 "use client";
 
-import { createContext, useContext } from "react";
+import { createContext, useContext, useRef } from "react";
 import { useSession as useNextAuthSession } from "next-auth/react";
 import { signOut, signIn } from "next-auth/react";
 import { configureApiAuth } from "./apiClient";
@@ -25,6 +25,9 @@ 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);
@@ -41,10 +44,15 @@ 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
     ? {
@@ -73,11 +81,16 @@ 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,
@@ -92,6 +105,8 @@ export function AuthProvider({ children }: { children: React.ReactNode }) {
               }
             }
             case "unauthenticated": {
+              // warning: call order-dependent
+              lastUserId.current = null;
               return { status: "unauthenticated" as const };
             }
             default: {
@@ -103,6 +118,8 @@ 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;
 

www/app/lib/apiHooks.ts

@@ -5,6 +5,7 @@ import { useError } from "../(errors)/errorContext";
 import { QueryClient, useQueryClient } from "@tanstack/react-query";
 import type { components } from "../reflector-api";
 import { useAuth } from "./AuthProvider";
+import { MeetingId } from "./types";
 
 /*
  * XXX error types returned from the hooks are not always correct; declared types are ValidationError but real type could be string or any other
@@ -718,7 +719,7 @@ export function useRoomActiveMeetings(roomName: string | null) {
 
 export function useRoomGetMeeting(
   roomName: string | null,
-  meetingId: string | null,
+  meetingId: MeetingId | null,
 ) {
   return $api.useQuery(
     "get",