chore(main): release 0.39.0 (#913)

* test: full integration tests

* fix: add env vars as secrets in CI

.github/workflows/integration_tests.yml

@@ -0,0 +1,139 @@
+name: Integration Tests
+
+on:
+  workflow_dispatch:
+    inputs:
+      llm_model:
+        description: "LLM model name (overrides LLM_MODEL secret)"
+        required: false
+        default: ""
+        type: string
+
+jobs:
+  integration:
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Start infrastructure services
+        working-directory: server/tests
+        env:
+          LLM_URL: ${{ secrets.LLM_URL }}
+          LLM_MODEL: ${{ inputs.llm_model || secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          docker compose -f docker-compose.integration.yml up -d --build postgres redis garage hatchet mock-daily
+
+      - name: Set up Garage bucket and keys
+        working-directory: server/tests
+        run: |
+          GARAGE="docker compose -f docker-compose.integration.yml exec -T garage /garage"
+          GARAGE_KEY_ID="GK0123456789abcdef01234567" # gitleaks:allow
+          GARAGE_KEY_SECRET="0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef" # gitleaks:allow
+
+          echo "Waiting for Garage to be healthy..."
+          for i in $(seq 1 60); do
+            if $GARAGE stats &>/dev/null; then break; fi
+            sleep 2
+          done
+
+          echo "Setting up Garage..."
+          NODE_ID=$($GARAGE node id -q 2>&1 | tr -d '[:space:]')
+          LAYOUT_STATUS=$($GARAGE layout show 2>&1 || true)
+          if echo "$LAYOUT_STATUS" | grep -q "No nodes"; then
+            $GARAGE layout assign "$NODE_ID" -c 1G -z dc1
+            $GARAGE layout apply --version 1
+          fi
+
+          $GARAGE bucket info reflector-media &>/dev/null || $GARAGE bucket create reflector-media
+          if ! $GARAGE key info reflector-test &>/dev/null; then
+            $GARAGE key import --yes "$GARAGE_KEY_ID" "$GARAGE_KEY_SECRET"
+            $GARAGE key rename "$GARAGE_KEY_ID" reflector-test
+          fi
+          $GARAGE bucket allow reflector-media --read --write --key reflector-test
+
+      - name: Wait for Hatchet and generate API token
+        working-directory: server/tests
+        run: |
+          echo "Waiting for Hatchet to be healthy..."
+          for i in $(seq 1 90); do
+            if docker compose -f docker-compose.integration.yml exec -T hatchet curl -sf http://localhost:8888/api/live &>/dev/null; then
+              echo "Hatchet is ready."
+              break
+            fi
+            sleep 2
+          done
+
+          echo "Generating Hatchet API token..."
+          HATCHET_OUTPUT=$(docker compose -f docker-compose.integration.yml exec -T hatchet \
+            /hatchet-admin token create --config /config --name integration-test 2>&1)
+          HATCHET_TOKEN=$(echo "$HATCHET_OUTPUT" | grep -o 'eyJ[A-Za-z0-9_.\-]*')
+          if [ -z "$HATCHET_TOKEN" ]; then
+            echo "ERROR: Failed to extract Hatchet JWT token"
+            exit 1
+          fi
+          echo "HATCHET_CLIENT_TOKEN=${HATCHET_TOKEN}" >> $GITHUB_ENV
+
+      - name: Start backend services
+        working-directory: server/tests
+        env:
+          LLM_URL: ${{ secrets.LLM_URL }}
+          LLM_MODEL: ${{ inputs.llm_model || secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          # Export garage and hatchet credentials for backend services
+          export GARAGE_KEY_ID="${{ env.GARAGE_KEY_ID }}"
+          export GARAGE_KEY_SECRET="${{ env.GARAGE_KEY_SECRET }}"
+          export HATCHET_CLIENT_TOKEN="${{ env.HATCHET_CLIENT_TOKEN }}"
+
+          docker compose -f docker-compose.integration.yml up -d \
+            server worker hatchet-worker-cpu hatchet-worker-llm test-runner
+
+      - name: Wait for server health check
+        working-directory: server/tests
+        run: |
+          echo "Waiting for server to be healthy..."
+          for i in $(seq 1 60); do
+            if docker compose -f docker-compose.integration.yml exec -T test-runner \
+              curl -sf http://server:1250/health &>/dev/null; then
+              echo "Server is ready."
+              break
+            fi
+            sleep 3
+          done
+
+      - name: Run DB migrations
+        working-directory: server/tests
+        run: |
+          docker compose -f docker-compose.integration.yml exec -T server \
+            uv run alembic upgrade head
+
+      - name: Run integration tests
+        working-directory: server/tests
+        run: |
+          docker compose -f docker-compose.integration.yml exec -T test-runner \
+            uv run pytest tests/integration/ -v -x
+
+      - name: Collect logs on failure
+        if: failure()
+        working-directory: server/tests
+        run: |
+          docker compose -f docker-compose.integration.yml logs --tail=500 > integration-logs.txt 2>&1
+
+      - name: Upload logs artifact
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: integration-logs
+          path: server/tests/integration-logs.txt
+          retention-days: 7
+
+      - name: Teardown
+        if: always()
+        working-directory: server/tests
+        run: |
+          docker compose -f docker-compose.integration.yml down -v --remove-orphans

.gitignore

@@ -25,3 +25,4 @@ www/.env.production
 opencode.json
 
 vibedocs/
+server/tests/integration/logs/

.pre-commit-config.yaml

@@ -1,5 +1,6 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
+exclude: '(^uv\.lock$|pnpm-lock\.yaml$)'
 repos:
   - repo: local
     hooks:

CHANGELOG.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## [0.39.0](https://github.com/GreyhavenHQ/reflector/compare/v0.38.2...v0.39.0) (2026-03-18)
+
+
+### Features
+
+* migrate file and live post-processing pipelines from Celery to Hatchet workflow engine ([#911](https://github.com/GreyhavenHQ/reflector/issues/911)) ([37a1f01](https://github.com/GreyhavenHQ/reflector/commit/37a1f0185057dd43b68df2b12bb08d3b18e28d34))
+
+
+### Bug Fixes
+
+* integration tests runner in CI ([#919](https://github.com/GreyhavenHQ/reflector/issues/919)) ([1e396ca](https://github.com/GreyhavenHQ/reflector/commit/1e396ca0ca91bc9d2645ddfc63a1576469491faa))
+* latest vulns ([#915](https://github.com/GreyhavenHQ/reflector/issues/915)) ([a9200d3](https://github.com/GreyhavenHQ/reflector/commit/a9200d35bf856f65f24a4f34931ebe0d75ad0382))
+
 ## [0.38.2](https://github.com/GreyhavenHQ/reflector/compare/v0.38.1...v0.38.2) (2026-03-12)
 
 

CLAUDE.md

@@ -160,6 +160,21 @@ All endpoints prefixed `/v1/`:
 - **Frontend**: No current test suite - opportunities for Jest/React Testing Library
 - **Coverage**: Backend maintains test coverage reports in `htmlcov/`
 
+### Integration Tests (DO NOT run unless explicitly asked)
+
+There are end-to-end integration tests in `server/tests/integration/` that spin up the full stack (PostgreSQL, Redis, Hatchet, Garage, mock-daily, server, workers) via Docker Compose and exercise real processing pipelines. These tests are:
+
+- `test_file_pipeline.py` — File upload → FilePipeline
+- `test_live_pipeline.py` — WebRTC stream → LivePostPipeline
+- `test_multitrack_pipeline.py` — Multitrack → DailyMultitrackPipeline
+
+**Important:**
+- These tests are **excluded** from normal `uv run pytest` runs via `--ignore=tests/integration` in pyproject.toml.
+- Do **NOT** run them as part of verification, code review, or general testing unless the user explicitly asks.
+- They require Docker, external LLM credentials, and HuggingFace token — they cannot run in a regular test environment.
+- To run locally: `./scripts/run-integration-tests.sh` (requires env vars: `LLM_URL`, `LLM_API_KEY`, `HF_TOKEN`).
+- In CI: triggered manually via the "Integration Tests" GitHub Actions workflow (`workflow_dispatch`).
+
 ## GPU Processing
 
 Modal.com integration for scalable ML processing:

docker-compose.selfhosted.yml

@@ -51,6 +51,9 @@ services:
       HF_TOKEN: ${HF_TOKEN:-}
       # WebRTC: fixed UDP port range for ICE candidates (mapped above)
       WEBRTC_PORT_RANGE: "51000-51100"
+      # Hatchet workflow engine (always-on for processing pipelines)
+      HATCHET_CLIENT_SERVER_URL: ${HATCHET_CLIENT_SERVER_URL:-http://hatchet:8888}
+      HATCHET_CLIENT_HOST_PORT: ${HATCHET_CLIENT_HOST_PORT:-hatchet:7077}
     depends_on:
       postgres:
         condition: service_healthy
@@ -75,6 +78,9 @@ services:
       CELERY_RESULT_BACKEND: redis://redis:6379/1
       # ML backend config comes from env_file (server/.env), set per-mode by setup script
       HF_TOKEN: ${HF_TOKEN:-}
+      # Hatchet workflow engine (always-on for processing pipelines)
+      HATCHET_CLIENT_SERVER_URL: ${HATCHET_CLIENT_SERVER_URL:-http://hatchet:8888}
+      HATCHET_CLIENT_HOST_PORT: ${HATCHET_CLIENT_HOST_PORT:-hatchet:7077}
     depends_on:
       postgres:
         condition: service_healthy
@@ -126,6 +132,8 @@ services:
   redis:
     image: redis:7.2-alpine
     restart: unless-stopped
+    ports:
+      - "6379:6379"
     healthcheck:
       test: ["CMD", "redis-cli", "ping"]
       interval: 30s
@@ -301,20 +309,20 @@ services:
       - server
 
   # ===========================================================
-  # Hatchet + Daily.co workers (optional — for Daily.co multitrack processing)
-  # Auto-enabled when DAILY_API_KEY is configured in server/r
+  # Hatchet workflow engine + workers
+  # Required for all processing pipelines (file, live, Daily.co multitrack).
+  # Always-on — every selfhosted deployment needs Hatchet.
   # ===========================================================
 
   hatchet:
     image: ghcr.io/hatchet-dev/hatchet/hatchet-lite:latest
-    profiles: [dailyco]
     restart: on-failure
     depends_on:
       postgres:
         condition: service_healthy
     ports:
-      - "8888:8888"
-      - "7078:7077"
+      - "127.0.0.1:8888:8888"
+      - "127.0.0.1:7078:7077"
     env_file:
       - ./.env.hatchet
     environment:
@@ -363,7 +371,6 @@ services:
       context: ./server
       dockerfile: Dockerfile
     image: monadicalsas/reflector-backend:latest
-    profiles: [dailyco]
     restart: unless-stopped
     env_file:
       - ./server/.env

scripts/run-integration-tests.sh

@@ -0,0 +1,156 @@
+#!/usr/bin/env bash
+#
+# Run integration tests locally.
+#
+# Spins up the full stack via Docker Compose, runs the three integration tests,
+# and tears everything down afterward.
+#
+# Required environment variables:
+#   LLM_URL      — OpenAI-compatible LLM endpoint (e.g. https://api.openai.com/v1)
+#   LLM_API_KEY  — API key for the LLM endpoint
+#   HF_TOKEN     — HuggingFace token for pyannote gated models
+#
+# Optional:
+#   LLM_MODEL    — Model name (default: qwen2.5:14b)
+#
+# Usage:
+#   export LLM_URL="https://api.openai.com/v1"
+#   export LLM_API_KEY="sk-..."
+#   export HF_TOKEN="hf_..."
+#   ./scripts/run-integration-tests.sh
+#
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+COMPOSE_DIR="$REPO_ROOT/server/tests"
+COMPOSE_FILE="$COMPOSE_DIR/docker-compose.integration.yml"
+COMPOSE="docker compose -f $COMPOSE_FILE"
+
+# ── Validate required env vars ──────────────────────────────────────────────
+for var in LLM_URL LLM_API_KEY HF_TOKEN; do
+    if [[ -z "${!var:-}" ]]; then
+        echo "ERROR: $var is not set. See script header for required env vars."
+        exit 1
+    fi
+done
+
+export LLM_MODEL="${LLM_MODEL:-qwen2.5:14b}"
+
+# ── Helpers ─────────────────────────────────────────────────────────────────
+info()  { echo -e "\n\033[1;34m▸ $*\033[0m"; }
+ok()    { echo -e "\033[1;32m  ✓ $*\033[0m"; }
+fail()  { echo -e "\033[1;31m  ✗ $*\033[0m"; }
+
+wait_for() {
+    local desc="$1" cmd="$2" max="${3:-60}"
+    info "Waiting for $desc (up to ${max}s)..."
+    for i in $(seq 1 "$max"); do
+        if eval "$cmd" &>/dev/null; then
+            ok "$desc is ready"
+            return 0
+        fi
+        sleep 2
+    done
+    fail "$desc did not become ready within ${max}s"
+    return 1
+}
+
+cleanup() {
+    info "Tearing down..."
+    $COMPOSE down -v --remove-orphans 2>/dev/null || true
+}
+
+# Always tear down on exit
+trap cleanup EXIT
+
+# ── Step 1: Build and start infrastructure ──────────────────────────────────
+info "Building and starting infrastructure services..."
+$COMPOSE up -d --build postgres redis garage hatchet mock-daily
+
+# ── Step 2: Set up Garage (S3 bucket + keys) ───────────────────────────────
+wait_for "Garage" "$COMPOSE exec -T garage /garage stats" 60
+
+info "Setting up Garage bucket and keys..."
+GARAGE="$COMPOSE exec -T garage /garage"
+
+# Hardcoded test credentials — ephemeral containers, destroyed after tests
+export GARAGE_KEY_ID="GK0123456789abcdef01234567" # gitleaks:allow
+export GARAGE_KEY_SECRET="0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef" # gitleaks:allow
+
+# Layout
+NODE_ID=$($GARAGE node id -q 2>&1 | tr -d '[:space:]')
+LAYOUT_STATUS=$($GARAGE layout show 2>&1 || true)
+if echo "$LAYOUT_STATUS" | grep -q "No nodes"; then
+    $GARAGE layout assign "$NODE_ID" -c 1G -z dc1
+    $GARAGE layout apply --version 1
+fi
+
+# Bucket
+$GARAGE bucket info reflector-media >/dev/null 2>&1 || $GARAGE bucket create reflector-media
+
+# Import key with known credentials
+if ! $GARAGE key info reflector-test >/dev/null 2>&1; then
+    $GARAGE key import --yes "$GARAGE_KEY_ID" "$GARAGE_KEY_SECRET"
+    $GARAGE key rename "$GARAGE_KEY_ID" reflector-test
+fi
+
+# Permissions
+$GARAGE bucket allow reflector-media --read --write --key reflector-test
+
+ok "Garage ready with hardcoded test credentials"
+
+# ── Step 3: Generate Hatchet API token ──────────────────────────────────────
+wait_for "Hatchet" "$COMPOSE exec -T hatchet curl -sf http://localhost:8888/api/live" 90
+
+info "Generating Hatchet API token..."
+HATCHET_TOKEN_OUTPUT=$($COMPOSE exec -T hatchet /hatchet-admin token create --config /config --name local-test 2>&1)
+export HATCHET_CLIENT_TOKEN=$(echo "$HATCHET_TOKEN_OUTPUT" | grep -o 'eyJ[A-Za-z0-9_.\-]*')
+
+if [[ -z "$HATCHET_CLIENT_TOKEN" ]]; then
+    fail "Failed to extract Hatchet token (JWT not found in output)"
+    echo "  Output was: $HATCHET_TOKEN_OUTPUT"
+    exit 1
+fi
+ok "Hatchet token generated"
+
+# ── Step 4: Start backend services ──────────────────────────────────────────
+info "Starting backend services..."
+$COMPOSE up -d server worker hatchet-worker-cpu hatchet-worker-llm test-runner
+
+# ── Step 5: Wait for server + run migrations ────────────────────────────────
+wait_for "Server" "$COMPOSE exec -T test-runner curl -sf http://server:1250/health" 60
+
+info "Running database migrations..."
+$COMPOSE exec -T server uv run alembic upgrade head
+ok "Migrations applied"
+
+# ── Step 6: Run integration tests ───────────────────────────────────────────
+info "Running integration tests..."
+echo ""
+
+LOGS_DIR="$COMPOSE_DIR/integration/logs"
+mkdir -p "$LOGS_DIR"
+RUN_TIMESTAMP=$(date +%Y%m%d-%H%M%S)
+TEST_LOG="$LOGS_DIR/$RUN_TIMESTAMP.txt"
+
+if $COMPOSE exec -T test-runner uv run pytest tests/integration/ -v -x 2>&1 | tee "$TEST_LOG.pytest"; then
+    echo ""
+    ok "All integration tests passed!"
+    EXIT_CODE=0
+else
+    echo ""
+    fail "Integration tests failed!"
+    EXIT_CODE=1
+fi
+
+# Always collect service logs + test output into a single file
+info "Collecting logs..."
+$COMPOSE logs --tail=500 > "$TEST_LOG" 2>&1
+echo -e "\n\n=== PYTEST OUTPUT ===\n" >> "$TEST_LOG"
+cat "$TEST_LOG.pytest" >> "$TEST_LOG" 2>/dev/null
+rm -f "$TEST_LOG.pytest"
+echo "  Logs saved to: server/tests/integration/logs/$RUN_TIMESTAMP.txt"
+
+# cleanup runs via trap
+exit $EXIT_CODE

scripts/setup-selfhosted.sh

@@ -261,9 +261,11 @@ if [[ -z "$MODEL_MODE" ]]; then
 fi
 
 # Build profiles list — one profile per feature
-# Only --gpu needs a compose profile; --cpu and --hosted use in-process/remote backends
+# Hatchet + hatchet-worker-llm are always-on (no profile needed).
+# gpu/cpu profiles only control the ML container (transcription service).
 COMPOSE_PROFILES=()
 [[ "$MODEL_MODE" == "gpu" ]] && COMPOSE_PROFILES+=("gpu")
+[[ "$MODEL_MODE" == "cpu" ]] && COMPOSE_PROFILES+=("cpu")
 [[ -n "$OLLAMA_MODE" ]] && COMPOSE_PROFILES+=("$OLLAMA_MODE")
 [[ "$USE_GARAGE" == "true" ]] && COMPOSE_PROFILES+=("garage")
 [[ "$USE_CADDY" == "true" ]] && COMPOSE_PROFILES+=("caddy")
@@ -557,12 +559,10 @@ step_server_env() {
         ok "CPU mode — file processing timeouts set to 3600s (1 hour)"
     fi
 
-    # If Daily.co is manually configured, ensure Hatchet connectivity vars are set
-    if env_has_key "$SERVER_ENV" "DAILY_API_KEY" && [[ -n "$(env_get "$SERVER_ENV" "DAILY_API_KEY")" ]]; then
-        env_set "$SERVER_ENV" "HATCHET_CLIENT_SERVER_URL" "http://hatchet:8888"
-        env_set "$SERVER_ENV" "HATCHET_CLIENT_HOST_PORT" "hatchet:7077"
-        ok "Daily.co detected — Hatchet connectivity configured"
-    fi
+    # Hatchet is always required (file, live, and multitrack pipelines all use it)
+    env_set "$SERVER_ENV" "HATCHET_CLIENT_SERVER_URL" "http://hatchet:8888"
+    env_set "$SERVER_ENV" "HATCHET_CLIENT_HOST_PORT" "hatchet:7077"
+    ok "Hatchet connectivity configured (workflow engine for processing pipelines)"
 
     ok "server/.env ready"
 }
@@ -886,15 +886,22 @@ step_services() {
         compose_cmd pull server web || warn "Pull failed — using cached images"
     fi
 
-    # Build hatchet workers if Daily.co is configured (same backend image)
-    if [[ "$DAILY_DETECTED" == "true" ]] && [[ "$BUILD_IMAGES" == "true" ]]; then
+    # Hatchet is always needed (all processing pipelines use it)
+    local NEEDS_HATCHET=true
+
+    # Build hatchet workers if Hatchet is needed (same backend image)
+    if [[ "$NEEDS_HATCHET" == "true" ]] && [[ "$BUILD_IMAGES" == "true" ]]; then
         info "Building Hatchet worker images..."
-        compose_cmd build hatchet-worker-cpu hatchet-worker-llm
+        if [[ "$DAILY_DETECTED" == "true" ]]; then
+            compose_cmd build hatchet-worker-cpu hatchet-worker-llm
+        else
+            compose_cmd build hatchet-worker-llm
+        fi
         ok "Hatchet worker images built"
     fi
 
     # Ensure hatchet database exists before starting hatchet (init-hatchet-db.sql only runs on fresh postgres volumes)
-    if [[ "$DAILY_DETECTED" == "true" ]]; then
+    if [[ "$NEEDS_HATCHET" == "true" ]]; then
         info "Ensuring postgres is running for Hatchet database setup..."
         compose_cmd up -d postgres
         local pg_ready=false
@@ -1049,24 +1056,22 @@ step_health() {
         fi
     fi
 
-    # Hatchet (if Daily.co detected)
-    if [[ "$DAILY_DETECTED" == "true" ]]; then
-        info "Waiting for Hatchet workflow engine..."
-        local hatchet_ok=false
-        for i in $(seq 1 60); do
-            if curl -sf http://localhost:8888/api/live > /dev/null 2>&1; then
-                hatchet_ok=true
-                break
-            fi
-            echo -ne "\r  Waiting for Hatchet... ($i/60)"
-            sleep 3
-        done
-        echo ""
-        if [[ "$hatchet_ok" == "true" ]]; then
-            ok "Hatchet workflow engine healthy"
-        else
-            warn "Hatchet not ready yet. Check: docker compose logs hatchet"
+    # Hatchet (always-on)
+    info "Waiting for Hatchet workflow engine..."
+    local hatchet_ok=false
+    for i in $(seq 1 60); do
+        if curl -sf http://localhost:8888/api/live > /dev/null 2>&1; then
+            hatchet_ok=true
+            break
         fi
+        echo -ne "\r  Waiting for Hatchet... ($i/60)"
+        sleep 3
+    done
+    echo ""
+    if [[ "$hatchet_ok" == "true" ]]; then
+        ok "Hatchet workflow engine healthy"
+    else
+        warn "Hatchet not ready yet. Check: docker compose logs hatchet"
     fi
 
     # LLM warning for non-Ollama modes
@@ -1087,12 +1092,10 @@ step_health() {
 }
 
 # =========================================================
-# Step 8: Hatchet token generation (Daily.co only)
+# Step 8: Hatchet token generation (gpu/cpu/Daily.co)
 # =========================================================
 step_hatchet_token() {
-    if [[ "$DAILY_DETECTED" != "true" ]]; then
-        return
-    fi
+    # Hatchet is always required — no gating needed
 
     # Skip if token already set
     if env_has_key "$SERVER_ENV" "HATCHET_CLIENT_TOKEN" && [[ -n "$(env_get "$SERVER_ENV" "HATCHET_CLIENT_TOKEN")" ]]; then
@@ -1147,7 +1150,9 @@ step_hatchet_token() {
 
     # Restart services that need the token
     info "Restarting services with new Hatchet token..."
-    compose_cmd restart server worker hatchet-worker-cpu hatchet-worker-llm
+    local restart_services="server worker hatchet-worker-llm"
+    [[ "$DAILY_DETECTED" == "true" ]] && restart_services="$restart_services hatchet-worker-cpu"
+    compose_cmd restart $restart_services
     ok "Services restarted with Hatchet token"
 }
 
@@ -1216,28 +1221,23 @@ main() {
         ok "Daily.co detected — enabling Hatchet workflow services"
     fi
 
-    # Generate .env.hatchet for hatchet dashboard config
-    if [[ "$DAILY_DETECTED" == "true" ]]; then
-        local hatchet_server_url hatchet_cookie_domain
-        if [[ -n "$CUSTOM_DOMAIN" ]]; then
-            hatchet_server_url="https://${CUSTOM_DOMAIN}:8888"
-            hatchet_cookie_domain="$CUSTOM_DOMAIN"
-        elif [[ -n "$PRIMARY_IP" ]]; then
-            hatchet_server_url="http://${PRIMARY_IP}:8888"
-            hatchet_cookie_domain="$PRIMARY_IP"
-        else
-            hatchet_server_url="http://localhost:8888"
-            hatchet_cookie_domain="localhost"
-        fi
-        cat > "$ROOT_DIR/.env.hatchet" << EOF
+    # Generate .env.hatchet for hatchet dashboard config (always needed)
+    local hatchet_server_url hatchet_cookie_domain
+    if [[ -n "$CUSTOM_DOMAIN" ]]; then
+        hatchet_server_url="https://${CUSTOM_DOMAIN}:8888"
+        hatchet_cookie_domain="$CUSTOM_DOMAIN"
+    elif [[ -n "$PRIMARY_IP" ]]; then
+        hatchet_server_url="http://${PRIMARY_IP}:8888"
+        hatchet_cookie_domain="$PRIMARY_IP"
+    else
+        hatchet_server_url="http://localhost:8888"
+        hatchet_cookie_domain="localhost"
+    fi
+    cat > "$ROOT_DIR/.env.hatchet" << EOF
 SERVER_URL=$hatchet_server_url
 SERVER_AUTH_COOKIE_DOMAIN=$hatchet_cookie_domain
 EOF
-        ok "Generated .env.hatchet (dashboard URL=$hatchet_server_url)"
-    else
-        # Create empty .env.hatchet so compose doesn't fail if dailyco profile is ever activated manually
-        touch "$ROOT_DIR/.env.hatchet"
-    fi
+    ok "Generated .env.hatchet (dashboard URL=$hatchet_server_url)"
 
     step_www_env
     echo ""

server/pyproject.toml

@@ -116,9 +116,10 @@ source = ["reflector"]
 ENVIRONMENT = "pytest"
 DATABASE_URL = "postgresql://test_user:test_password@localhost:15432/reflector_test"
 AUTH_BACKEND = "jwt"
+HATCHET_CLIENT_TOKEN = "test-dummy-token"
 
 [tool.pytest.ini_options]
-addopts = "-ra -q --disable-pytest-warnings --cov --cov-report html -v"
+addopts = "-ra -q --disable-pytest-warnings --cov --cov-report html -v --ignore=tests/integration"
 testpaths = ["tests"]
 asyncio_mode = "auto"
 markers = [

server/reflector/hatchet/constants.py

@@ -26,6 +26,21 @@ class TaskName(StrEnum):
     DETECT_CHUNK_TOPIC = "detect_chunk_topic"
     GENERATE_DETAILED_SUMMARY = "generate_detailed_summary"
 
+    # File pipeline tasks
+    EXTRACT_AUDIO = "extract_audio"
+    UPLOAD_AUDIO = "upload_audio"
+    TRANSCRIBE = "transcribe"
+    DIARIZE = "diarize"
+    ASSEMBLE_TRANSCRIPT = "assemble_transcript"
+    GENERATE_SUMMARIES = "generate_summaries"
+
+    # Live post-processing pipeline tasks
+    WAVEFORM = "waveform"
+    CONVERT_MP3 = "convert_mp3"
+    UPLOAD_MP3 = "upload_mp3"
+    REMOVE_UPLOAD = "remove_upload"
+    FINAL_SUMMARIES = "final_summaries"
+
 
 # Rate limit key for LLM API calls (shared across all LLM-calling tasks)
 LLM_RATE_LIMIT_KEY = "llm"

server/reflector/hatchet/run_workers_llm.py

@@ -10,6 +10,8 @@ from reflector.hatchet.client import HatchetClientManager
 from reflector.hatchet.workflows.daily_multitrack_pipeline import (
     daily_multitrack_pipeline,
 )
+from reflector.hatchet.workflows.file_pipeline import file_pipeline
+from reflector.hatchet.workflows.live_post_pipeline import live_post_pipeline
 from reflector.hatchet.workflows.subject_processing import subject_workflow
 from reflector.hatchet.workflows.topic_chunk_processing import topic_chunk_workflow
 from reflector.hatchet.workflows.track_processing import track_workflow
@@ -47,6 +49,8 @@ def main():
         },
         workflows=[
             daily_multitrack_pipeline,
+            file_pipeline,
+            live_post_pipeline,
             topic_chunk_workflow,
             subject_workflow,
             track_workflow,

server/reflector/hatchet/workflows/daily_multitrack_pipeline.py

@@ -307,7 +307,9 @@ async def get_recording(input: PipelineInput, ctx: Context) -> RecordingResult:
     ctx.log(
         f"get_recording: calling Daily.co API for recording_id={input.recording_id}..."
     )
-    async with DailyApiClient(api_key=settings.DAILY_API_KEY) as client:
+    async with DailyApiClient(
+        api_key=settings.DAILY_API_KEY, base_url=settings.DAILY_API_URL
+    ) as client:
         recording = await client.get_recording(input.recording_id)
     ctx.log(f"get_recording: Daily.co API returned successfully")
 
@@ -374,7 +376,9 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
             settings.DAILY_API_KEY, "DAILY_API_KEY is required"
         )
 
-        async with DailyApiClient(api_key=daily_api_key) as client:
+        async with DailyApiClient(
+            api_key=daily_api_key, base_url=settings.DAILY_API_URL
+        ) as client:
             participants = await client.get_meeting_participants(mtg_session_id)
 
         id_to_name = {}

server/reflector/hatchet/workflows/file_pipeline.py

@@ -0,0 +1,885 @@
+"""
+Hatchet workflow: FilePipeline
+
+Processing pipeline for file uploads and Whereby recordings.
+Orchestrates: extract audio → upload → transcribe/diarize/waveform (parallel)
+→ assemble → detect topics → title/summaries (parallel) → finalize
+→ cleanup consent → post zulip / send webhook.
+
+Note: This file uses deferred imports (inside functions/tasks) intentionally.
+Hatchet workers run in forked processes; fresh imports per task ensure DB connections
+are not shared across forks, avoiding connection pooling issues.
+"""
+
+import json
+from datetime import timedelta
+from pathlib import Path
+
+from hatchet_sdk import Context
+from pydantic import BaseModel
+
+from reflector.hatchet.broadcast import (
+    append_event_and_broadcast,
+    set_status_and_broadcast,
+)
+from reflector.hatchet.client import HatchetClientManager
+from reflector.hatchet.constants import (
+    TIMEOUT_HEAVY,
+    TIMEOUT_MEDIUM,
+    TIMEOUT_SHORT,
+    TIMEOUT_TITLE,
+    TaskName,
+)
+from reflector.hatchet.workflows.daily_multitrack_pipeline import (
+    fresh_db_connection,
+    set_workflow_error_status,
+    with_error_handling,
+)
+from reflector.hatchet.workflows.models import (
+    ConsentResult,
+    TitleResult,
+    TopicsResult,
+    WaveformResult,
+    WebhookResult,
+    ZulipResult,
+)
+from reflector.logger import logger
+from reflector.pipelines import topic_processing
+from reflector.settings import settings
+from reflector.utils.audio_constants import WAVEFORM_SEGMENTS
+from reflector.utils.audio_waveform import get_audio_waveform
+
+
+class FilePipelineInput(BaseModel):
+    transcript_id: str
+    room_id: str | None = None
+
+
+# --- Result models specific to file pipeline ---
+
+
+class ExtractAudioResult(BaseModel):
+    audio_path: str
+    duration_ms: float = 0.0
+
+
+class UploadAudioResult(BaseModel):
+    audio_url: str
+    audio_path: str
+
+
+class TranscribeResult(BaseModel):
+    words: list[dict]
+    translation: str | None = None
+
+
+class DiarizeResult(BaseModel):
+    diarization: list[dict] | None = None
+
+
+class AssembleTranscriptResult(BaseModel):
+    assembled: bool
+
+
+class SummariesResult(BaseModel):
+    generated: bool
+
+
+class FinalizeResult(BaseModel):
+    status: str
+
+
+hatchet = HatchetClientManager.get_client()
+
+file_pipeline = hatchet.workflow(name="FilePipeline", input_validator=FilePipelineInput)
+
+
+@file_pipeline.task(
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.EXTRACT_AUDIO)
+async def extract_audio(input: FilePipelineInput, ctx: Context) -> ExtractAudioResult:
+    """Extract audio from upload file, convert to MP3."""
+    ctx.log(f"extract_audio: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+
+        await set_status_and_broadcast(input.transcript_id, "processing", logger=logger)
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            raise ValueError(f"Transcript {input.transcript_id} not found")
+
+        # Clear transcript as we're going to regenerate everything
+        await transcripts_controller.update(
+            transcript,
+            {
+                "events": [],
+                "topics": [],
+            },
+        )
+
+        # Find upload file
+        audio_file = next(transcript.data_path.glob("upload.*"), None)
+        if not audio_file:
+            audio_file = next(transcript.data_path.glob("audio.*"), None)
+        if not audio_file:
+            raise ValueError("No audio file found to process")
+
+        ctx.log(f"extract_audio: processing {audio_file}")
+
+        # Extract audio and write as MP3
+        import av  # noqa: PLC0415
+
+        from reflector.processors import AudioFileWriterProcessor  # noqa: PLC0415
+
+        duration_ms_container = [0.0]
+
+        async def capture_duration(d):
+            duration_ms_container[0] = d
+
+        mp3_writer = AudioFileWriterProcessor(
+            path=transcript.audio_mp3_filename,
+            on_duration=capture_duration,
+        )
+        input_container = av.open(str(audio_file))
+        for frame in input_container.decode(audio=0):
+            await mp3_writer.push(frame)
+        await mp3_writer.flush()
+        input_container.close()
+
+        duration_ms = duration_ms_container[0]
+        audio_path = str(transcript.audio_mp3_filename)
+
+        # Persist duration to database and broadcast to websocket clients
+        from reflector.db.transcripts import TranscriptDuration  # noqa: PLC0415
+        from reflector.db.transcripts import transcripts_controller as tc
+
+        await tc.update(transcript, {"duration": duration_ms})
+        await append_event_and_broadcast(
+            input.transcript_id,
+            transcript,
+            "DURATION",
+            TranscriptDuration(duration=duration_ms),
+            logger=logger,
+        )
+
+    ctx.log(f"extract_audio complete: {audio_path}, duration={duration_ms}ms")
+    return ExtractAudioResult(audio_path=audio_path, duration_ms=duration_ms)
+
+
+@file_pipeline.task(
+    parents=[extract_audio],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.UPLOAD_AUDIO)
+async def upload_audio(input: FilePipelineInput, ctx: Context) -> UploadAudioResult:
+    """Upload audio to S3/storage, return audio_url."""
+    ctx.log(f"upload_audio: starting for transcript_id={input.transcript_id}")
+
+    extract_result = ctx.task_output(extract_audio)
+    audio_path = extract_result.audio_path
+
+    from reflector.storage import get_transcripts_storage  # noqa: PLC0415
+
+    storage = get_transcripts_storage()
+    if not storage:
+        raise ValueError(
+            "Storage backend required for file processing. "
+            "Configure TRANSCRIPT_STORAGE_* settings."
+        )
+
+    with open(audio_path, "rb") as f:
+        audio_data = f.read()
+
+    storage_path = f"file_pipeline/{input.transcript_id}/audio.mp3"
+    await storage.put_file(storage_path, audio_data)
+    audio_url = await storage.get_file_url(storage_path)
+
+    ctx.log(f"upload_audio complete: {audio_url}")
+    return UploadAudioResult(audio_url=audio_url, audio_path=audio_path)
+
+
+@file_pipeline.task(
+    parents=[upload_audio],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+@with_error_handling(TaskName.TRANSCRIBE)
+async def transcribe(input: FilePipelineInput, ctx: Context) -> TranscribeResult:
+    """Transcribe the audio file using the configured backend."""
+    ctx.log(f"transcribe: starting for transcript_id={input.transcript_id}")
+
+    upload_result = ctx.task_output(upload_audio)
+    audio_url = upload_result.audio_url
+
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            raise ValueError(f"Transcript {input.transcript_id} not found")
+        source_language = transcript.source_language
+
+    from reflector.pipelines.transcription_helpers import (  # noqa: PLC0415
+        transcribe_file_with_processor,
+    )
+
+    result = await transcribe_file_with_processor(audio_url, source_language)
+
+    ctx.log(f"transcribe complete: {len(result.words)} words")
+    return TranscribeResult(
+        words=[w.model_dump() for w in result.words],
+        translation=result.translation,
+    )
+
+
+@file_pipeline.task(
+    parents=[upload_audio],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+@with_error_handling(TaskName.DIARIZE)
+async def diarize(input: FilePipelineInput, ctx: Context) -> DiarizeResult:
+    """Diarize the audio file (speaker identification)."""
+    ctx.log(f"diarize: starting for transcript_id={input.transcript_id}")
+
+    if not settings.DIARIZATION_BACKEND:
+        ctx.log("diarize: diarization disabled, skipping")
+        return DiarizeResult(diarization=None)
+
+    upload_result = ctx.task_output(upload_audio)
+    audio_url = upload_result.audio_url
+
+    from reflector.processors.file_diarization import (  # noqa: PLC0415
+        FileDiarizationInput,
+    )
+    from reflector.processors.file_diarization_auto import (  # noqa: PLC0415
+        FileDiarizationAutoProcessor,
+    )
+
+    processor = FileDiarizationAutoProcessor()
+    input_data = FileDiarizationInput(audio_url=audio_url)
+
+    result = None
+
+    async def capture_result(diarization_output):
+        nonlocal result
+        result = diarization_output.diarization
+
+    try:
+        processor.on(capture_result)
+        await processor.push(input_data)
+        await processor.flush()
+    except Exception as e:
+        logger.error(f"Diarization failed: {e}")
+        return DiarizeResult(diarization=None)
+
+    ctx.log(f"diarize complete: {len(result) if result else 0} segments")
+    return DiarizeResult(diarization=list(result) if result else None)
+
+
+@file_pipeline.task(
+    parents=[upload_audio],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.GENERATE_WAVEFORM)
+async def generate_waveform(input: FilePipelineInput, ctx: Context) -> WaveformResult:
+    """Generate audio waveform visualization."""
+    ctx.log(f"generate_waveform: starting for transcript_id={input.transcript_id}")
+
+    upload_result = ctx.task_output(upload_audio)
+    audio_path = upload_result.audio_path
+
+    from reflector.db.transcripts import (  # noqa: PLC0415
+        TranscriptWaveform,
+        transcripts_controller,
+    )
+
+    waveform = get_audio_waveform(
+        path=Path(audio_path), segments_count=WAVEFORM_SEGMENTS
+    )
+
+    async with fresh_db_connection():
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript:
+            transcript.data_path.mkdir(parents=True, exist_ok=True)
+            with open(transcript.audio_waveform_filename, "w") as f:
+                json.dump(waveform, f)
+
+            waveform_data = TranscriptWaveform(waveform=waveform)
+            await append_event_and_broadcast(
+                input.transcript_id,
+                transcript,
+                "WAVEFORM",
+                waveform_data,
+                logger=logger,
+            )
+
+    ctx.log("generate_waveform complete")
+    return WaveformResult(waveform_generated=True)
+
+
+@file_pipeline.task(
+    parents=[transcribe, diarize, generate_waveform],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.ASSEMBLE_TRANSCRIPT)
+async def assemble_transcript(
+    input: FilePipelineInput, ctx: Context
+) -> AssembleTranscriptResult:
+    """Merge transcription + diarization results."""
+    ctx.log(f"assemble_transcript: starting for transcript_id={input.transcript_id}")
+
+    transcribe_result = ctx.task_output(transcribe)
+    diarize_result = ctx.task_output(diarize)
+
+    from reflector.processors.transcript_diarization_assembler import (  # noqa: PLC0415
+        TranscriptDiarizationAssemblerInput,
+        TranscriptDiarizationAssemblerProcessor,
+    )
+    from reflector.processors.types import (  # noqa: PLC0415
+        DiarizationSegment,
+        Word,
+    )
+    from reflector.processors.types import (  # noqa: PLC0415
+        Transcript as TranscriptType,
+    )
+
+    words = [Word(**w) for w in transcribe_result.words]
+    transcript_data = TranscriptType(
+        words=words, translation=transcribe_result.translation
+    )
+
+    diarization = None
+    if diarize_result.diarization:
+        diarization = [DiarizationSegment(**s) for s in diarize_result.diarization]
+
+    processor = TranscriptDiarizationAssemblerProcessor()
+    assembler_input = TranscriptDiarizationAssemblerInput(
+        transcript=transcript_data, diarization=diarization or []
+    )
+
+    diarized_transcript = None
+
+    async def capture_result(transcript):
+        nonlocal diarized_transcript
+        diarized_transcript = transcript
+
+    processor.on(capture_result)
+    await processor.push(assembler_input)
+    await processor.flush()
+
+    if not diarized_transcript:
+        raise ValueError("No diarized transcript captured")
+
+    # Save the assembled transcript events to the database
+    async with fresh_db_connection():
+        from reflector.db.transcripts import (  # noqa: PLC0415
+            TranscriptText,
+            transcripts_controller,
+        )
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript:
+            assembled_text = diarized_transcript.text if diarized_transcript else ""
+            assembled_translation = (
+                diarized_transcript.translation if diarized_transcript else None
+            )
+            await append_event_and_broadcast(
+                input.transcript_id,
+                transcript,
+                "TRANSCRIPT",
+                TranscriptText(text=assembled_text, translation=assembled_translation),
+                logger=logger,
+            )
+
+    ctx.log("assemble_transcript complete")
+    return AssembleTranscriptResult(assembled=True)
+
+
+@file_pipeline.task(
+    parents=[assemble_transcript],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+@with_error_handling(TaskName.DETECT_TOPICS)
+async def detect_topics(input: FilePipelineInput, ctx: Context) -> TopicsResult:
+    """Detect topics from the assembled transcript."""
+    ctx.log(f"detect_topics: starting for transcript_id={input.transcript_id}")
+
+    # Re-read the transcript to get the diarized words
+    transcribe_result = ctx.task_output(transcribe)
+    diarize_result = ctx.task_output(diarize)
+
+    from reflector.db.transcripts import (  # noqa: PLC0415
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.transcript_diarization_assembler import (  # noqa: PLC0415
+        TranscriptDiarizationAssemblerInput,
+        TranscriptDiarizationAssemblerProcessor,
+    )
+    from reflector.processors.types import (  # noqa: PLC0415
+        DiarizationSegment,
+        Word,
+    )
+    from reflector.processors.types import (  # noqa: PLC0415
+        Transcript as TranscriptType,
+    )
+
+    words = [Word(**w) for w in transcribe_result.words]
+    transcript_data = TranscriptType(
+        words=words, translation=transcribe_result.translation
+    )
+
+    diarization = None
+    if diarize_result.diarization:
+        diarization = [DiarizationSegment(**s) for s in diarize_result.diarization]
+
+    # Re-assemble to get the diarized transcript for topic detection
+    processor = TranscriptDiarizationAssemblerProcessor()
+    assembler_input = TranscriptDiarizationAssemblerInput(
+        transcript=transcript_data, diarization=diarization or []
+    )
+
+    diarized_transcript = None
+
+    async def capture_result(transcript):
+        nonlocal diarized_transcript
+        diarized_transcript = transcript
+
+    processor.on(capture_result)
+    await processor.push(assembler_input)
+    await processor.flush()
+
+    if not diarized_transcript:
+        raise ValueError("No diarized transcript for topic detection")
+
+    async with fresh_db_connection():
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            raise ValueError(f"Transcript {input.transcript_id} not found")
+        target_language = transcript.target_language
+
+        empty_pipeline = topic_processing.EmptyPipeline(logger=logger)
+
+        async def on_topic_callback(data):
+            topic = TranscriptTopic(
+                title=data.title,
+                summary=data.summary,
+                timestamp=data.timestamp,
+                transcript=data.transcript.text
+                if hasattr(data.transcript, "text")
+                else "",
+                words=data.transcript.words
+                if hasattr(data.transcript, "words")
+                else [],
+            )
+            await transcripts_controller.upsert_topic(transcript, topic)
+            await append_event_and_broadcast(
+                input.transcript_id, transcript, "TOPIC", topic, logger=logger
+            )
+
+        topics = await topic_processing.detect_topics(
+            diarized_transcript,
+            target_language,
+            on_topic_callback=on_topic_callback,
+            empty_pipeline=empty_pipeline,
+        )
+
+    ctx.log(f"detect_topics complete: {len(topics)} topics")
+    return TopicsResult(topics=topics)
+
+
+@file_pipeline.task(
+    parents=[detect_topics],
+    execution_timeout=timedelta(seconds=TIMEOUT_TITLE),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
+)
+@with_error_handling(TaskName.GENERATE_TITLE)
+async def generate_title(input: FilePipelineInput, ctx: Context) -> TitleResult:
+    """Generate meeting title using LLM."""
+    ctx.log(f"generate_title: starting for transcript_id={input.transcript_id}")
+
+    topics_result = ctx.task_output(detect_topics)
+    topics = topics_result.topics
+
+    from reflector.db.transcripts import (  # noqa: PLC0415
+        TranscriptFinalTitle,
+        transcripts_controller,
+    )
+
+    empty_pipeline = topic_processing.EmptyPipeline(logger=logger)
+    title_result = None
+
+    async with fresh_db_connection():
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            raise ValueError(f"Transcript {input.transcript_id} not found")
+
+        async def on_title_callback(data):
+            nonlocal title_result
+            title_result = data.title
+            final_title = TranscriptFinalTitle(title=data.title)
+            if not transcript.title:
+                await transcripts_controller.update(
+                    transcript, {"title": final_title.title}
+                )
+            await append_event_and_broadcast(
+                input.transcript_id,
+                transcript,
+                "FINAL_TITLE",
+                final_title,
+                logger=logger,
+            )
+
+        await topic_processing.generate_title(
+            topics,
+            on_title_callback=on_title_callback,
+            empty_pipeline=empty_pipeline,
+            logger=logger,
+        )
+
+    ctx.log(f"generate_title complete: '{title_result}'")
+    return TitleResult(title=title_result)
+
+
+@file_pipeline.task(
+    parents=[detect_topics],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+@with_error_handling(TaskName.GENERATE_SUMMARIES)
+async def generate_summaries(input: FilePipelineInput, ctx: Context) -> SummariesResult:
+    """Generate long/short summaries and action items."""
+    ctx.log(f"generate_summaries: starting for transcript_id={input.transcript_id}")
+
+    topics_result = ctx.task_output(detect_topics)
+    topics = topics_result.topics
+
+    from reflector.db.transcripts import (  # noqa: PLC0415
+        TranscriptActionItems,
+        TranscriptFinalLongSummary,
+        TranscriptFinalShortSummary,
+        transcripts_controller,
+    )
+
+    empty_pipeline = topic_processing.EmptyPipeline(logger=logger)
+
+    async with fresh_db_connection():
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            raise ValueError(f"Transcript {input.transcript_id} not found")
+
+        async def on_long_summary_callback(data):
+            final_long = TranscriptFinalLongSummary(long_summary=data.long_summary)
+            await transcripts_controller.update(
+                transcript, {"long_summary": final_long.long_summary}
+            )
+            await append_event_and_broadcast(
+                input.transcript_id,
+                transcript,
+                "FINAL_LONG_SUMMARY",
+                final_long,
+                logger=logger,
+            )
+
+        async def on_short_summary_callback(data):
+            final_short = TranscriptFinalShortSummary(short_summary=data.short_summary)
+            await transcripts_controller.update(
+                transcript, {"short_summary": final_short.short_summary}
+            )
+            await append_event_and_broadcast(
+                input.transcript_id,
+                transcript,
+                "FINAL_SHORT_SUMMARY",
+                final_short,
+                logger=logger,
+            )
+
+        async def on_action_items_callback(data):
+            action_items = TranscriptActionItems(action_items=data.action_items)
+            await transcripts_controller.update(
+                transcript, {"action_items": action_items.action_items}
+            )
+            await append_event_and_broadcast(
+                input.transcript_id,
+                transcript,
+                "ACTION_ITEMS",
+                action_items,
+                logger=logger,
+            )
+
+        await topic_processing.generate_summaries(
+            topics,
+            transcript,
+            on_long_summary_callback=on_long_summary_callback,
+            on_short_summary_callback=on_short_summary_callback,
+            on_action_items_callback=on_action_items_callback,
+            empty_pipeline=empty_pipeline,
+            logger=logger,
+        )
+
+    ctx.log("generate_summaries complete")
+    return SummariesResult(generated=True)
+
+
+@file_pipeline.task(
+    parents=[generate_title, generate_summaries],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=5,
+)
+@with_error_handling(TaskName.FINALIZE)
+async def finalize(input: FilePipelineInput, ctx: Context) -> FinalizeResult:
+    """Set transcript status to 'ended' and broadcast."""
+    ctx.log("finalize: setting status to 'ended'")
+
+    async with fresh_db_connection():
+        await set_status_and_broadcast(input.transcript_id, "ended", logger=logger)
+
+    ctx.log("finalize complete")
+    return FinalizeResult(status="COMPLETED")
+
+
+@file_pipeline.task(
+    parents=[finalize],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.CLEANUP_CONSENT, set_error_status=False)
+async def cleanup_consent(input: FilePipelineInput, ctx: Context) -> ConsentResult:
+    """Check consent and delete audio files if any participant denied."""
+    ctx.log(f"cleanup_consent: transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.db.meetings import (  # noqa: PLC0415
+            meeting_consent_controller,
+            meetings_controller,
+        )
+        from reflector.db.recordings import recordings_controller  # noqa: PLC0415
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+        from reflector.storage import get_transcripts_storage  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            ctx.log("cleanup_consent: transcript not found")
+            return ConsentResult()
+
+        consent_denied = False
+        recording = None
+        if transcript.recording_id:
+            recording = await recordings_controller.get_by_id(transcript.recording_id)
+            if recording and recording.meeting_id:
+                meeting = await meetings_controller.get_by_id(recording.meeting_id)
+                if meeting:
+                    consent_denied = await meeting_consent_controller.has_any_denial(
+                        meeting.id
+                    )
+
+        if not consent_denied:
+            ctx.log("cleanup_consent: consent approved, keeping all files")
+            return ConsentResult()
+
+        ctx.log("cleanup_consent: consent denied, deleting audio files")
+
+        deletion_errors = []
+        if recording and recording.bucket_name:
+            keys_to_delete = []
+            if recording.track_keys:
+                keys_to_delete = recording.track_keys
+            elif recording.object_key:
+                keys_to_delete = [recording.object_key]
+
+            master_storage = get_transcripts_storage()
+            for key in keys_to_delete:
+                try:
+                    await master_storage.delete_file(key, bucket=recording.bucket_name)
+                    ctx.log(f"Deleted recording file: {recording.bucket_name}/{key}")
+                except Exception as e:
+                    error_msg = f"Failed to delete {key}: {e}"
+                    logger.error(error_msg, exc_info=True)
+                    deletion_errors.append(error_msg)
+
+        if transcript.audio_location == "storage":
+            storage = get_transcripts_storage()
+            try:
+                await storage.delete_file(transcript.storage_audio_path)
+                ctx.log(f"Deleted processed audio: {transcript.storage_audio_path}")
+            except Exception as e:
+                error_msg = f"Failed to delete processed audio: {e}"
+                logger.error(error_msg, exc_info=True)
+                deletion_errors.append(error_msg)
+
+        try:
+            if (
+                hasattr(transcript, "audio_mp3_filename")
+                and transcript.audio_mp3_filename
+            ):
+                transcript.audio_mp3_filename.unlink(missing_ok=True)
+            if (
+                hasattr(transcript, "audio_wav_filename")
+                and transcript.audio_wav_filename
+            ):
+                transcript.audio_wav_filename.unlink(missing_ok=True)
+        except Exception as e:
+            error_msg = f"Failed to delete local audio files: {e}"
+            logger.error(error_msg, exc_info=True)
+            deletion_errors.append(error_msg)
+
+        if deletion_errors:
+            logger.warning(
+                "[Hatchet] cleanup_consent completed with errors",
+                transcript_id=input.transcript_id,
+                error_count=len(deletion_errors),
+            )
+        else:
+            await transcripts_controller.update(transcript, {"audio_deleted": True})
+            ctx.log("cleanup_consent: all audio deleted successfully")
+
+    return ConsentResult()
+
+
+@file_pipeline.task(
+    parents=[cleanup_consent],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
+)
+@with_error_handling(TaskName.POST_ZULIP, set_error_status=False)
+async def post_zulip(input: FilePipelineInput, ctx: Context) -> ZulipResult:
+    """Post notification to Zulip."""
+    ctx.log(f"post_zulip: transcript_id={input.transcript_id}")
+
+    if not settings.ZULIP_REALM:
+        ctx.log("post_zulip skipped (Zulip not configured)")
+        return ZulipResult(zulip_message_id=None, skipped=True)
+
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+        from reflector.zulip import post_transcript_notification  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript:
+            message_id = await post_transcript_notification(transcript)
+            ctx.log(f"post_zulip complete: zulip_message_id={message_id}")
+        else:
+            message_id = None
+
+    return ZulipResult(zulip_message_id=message_id)
+
+
+@file_pipeline.task(
+    parents=[cleanup_consent],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
+)
+@with_error_handling(TaskName.SEND_WEBHOOK, set_error_status=False)
+async def send_webhook(input: FilePipelineInput, ctx: Context) -> WebhookResult:
+    """Send completion webhook to external service."""
+    ctx.log(f"send_webhook: transcript_id={input.transcript_id}")
+
+    if not input.room_id:
+        ctx.log("send_webhook skipped (no room_id)")
+        return WebhookResult(webhook_sent=False, skipped=True)
+
+    async with fresh_db_connection():
+        from reflector.db.rooms import rooms_controller  # noqa: PLC0415
+        from reflector.utils.webhook import (  # noqa: PLC0415
+            fetch_transcript_webhook_payload,
+            send_webhook_request,
+        )
+
+        room = await rooms_controller.get_by_id(input.room_id)
+        if not room or not room.webhook_url:
+            ctx.log("send_webhook skipped (no webhook_url configured)")
+            return WebhookResult(webhook_sent=False, skipped=True)
+
+        payload = await fetch_transcript_webhook_payload(
+            transcript_id=input.transcript_id,
+            room_id=input.room_id,
+        )
+
+        if isinstance(payload, str):
+            ctx.log(f"send_webhook skipped (could not build payload): {payload}")
+            return WebhookResult(webhook_sent=False, skipped=True)
+
+        import httpx  # noqa: PLC0415
+
+        try:
+            response = await send_webhook_request(
+                url=room.webhook_url,
+                payload=payload,
+                event_type="transcript.completed",
+                webhook_secret=room.webhook_secret,
+                timeout=30.0,
+            )
+            ctx.log(f"send_webhook complete: status_code={response.status_code}")
+            return WebhookResult(webhook_sent=True, response_code=response.status_code)
+        except httpx.HTTPStatusError as e:
+            ctx.log(f"send_webhook failed (HTTP {e.response.status_code}), continuing")
+            return WebhookResult(
+                webhook_sent=False, response_code=e.response.status_code
+            )
+        except (httpx.ConnectError, httpx.TimeoutException) as e:
+            ctx.log(f"send_webhook failed ({e}), continuing")
+            return WebhookResult(webhook_sent=False)
+        except Exception as e:
+            ctx.log(f"send_webhook unexpected error: {e}")
+            return WebhookResult(webhook_sent=False)
+
+
+# --- On failure handler ---
+
+
+async def on_workflow_failure(input: FilePipelineInput, ctx: Context) -> None:
+    """Set transcript status to 'error' only if not already 'ended'."""
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript and transcript.status == "ended":
+            logger.info(
+                "[Hatchet] FilePipeline on_workflow_failure: transcript already ended, skipping error status",
+                transcript_id=input.transcript_id,
+            )
+            ctx.log(
+                "on_workflow_failure: transcript already ended, skipping error status"
+            )
+            return
+    await set_workflow_error_status(input.transcript_id)
+
+
+@file_pipeline.on_failure_task()
+async def _register_on_workflow_failure(input: FilePipelineInput, ctx: Context) -> None:
+    await on_workflow_failure(input, ctx)

server/reflector/hatchet/workflows/live_post_pipeline.py

@@ -0,0 +1,389 @@
+"""
+Hatchet workflow: LivePostProcessingPipeline
+
+Post-processing pipeline for live WebRTC meetings.
+Triggered after a live meeting ends. Orchestrates:
+  Left branch:  waveform → convert_mp3 → upload_mp3 → remove_upload → diarize → cleanup_consent
+  Right branch: generate_title (parallel with left branch)
+  Fan-in:       final_summaries → post_zulip → send_webhook
+
+Note: This file uses deferred imports (inside functions/tasks) intentionally.
+Hatchet workers run in forked processes; fresh imports per task ensure DB connections
+are not shared across forks, avoiding connection pooling issues.
+"""
+
+from datetime import timedelta
+
+from hatchet_sdk import Context
+from pydantic import BaseModel
+
+from reflector.hatchet.client import HatchetClientManager
+from reflector.hatchet.constants import (
+    TIMEOUT_HEAVY,
+    TIMEOUT_MEDIUM,
+    TIMEOUT_SHORT,
+    TIMEOUT_TITLE,
+    TaskName,
+)
+from reflector.hatchet.workflows.daily_multitrack_pipeline import (
+    fresh_db_connection,
+    set_workflow_error_status,
+    with_error_handling,
+)
+from reflector.hatchet.workflows.models import (
+    ConsentResult,
+    TitleResult,
+    WaveformResult,
+    WebhookResult,
+    ZulipResult,
+)
+from reflector.logger import logger
+from reflector.settings import settings
+
+
+class LivePostPipelineInput(BaseModel):
+    transcript_id: str
+    room_id: str | None = None
+
+
+# --- Result models specific to live post pipeline ---
+
+
+class ConvertMp3Result(BaseModel):
+    converted: bool
+
+
+class UploadMp3Result(BaseModel):
+    uploaded: bool
+
+
+class RemoveUploadResult(BaseModel):
+    removed: bool
+
+
+class DiarizeResult(BaseModel):
+    diarized: bool
+
+
+class FinalSummariesResult(BaseModel):
+    generated: bool
+
+
+hatchet = HatchetClientManager.get_client()
+
+live_post_pipeline = hatchet.workflow(
+    name="LivePostProcessingPipeline", input_validator=LivePostPipelineInput
+)
+
+
+@live_post_pipeline.task(
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.WAVEFORM)
+async def waveform(input: LivePostPipelineInput, ctx: Context) -> WaveformResult:
+    """Generate waveform visualization from recorded audio."""
+    ctx.log(f"waveform: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            PipelineMainWaveform,
+        )
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if not transcript:
+            raise ValueError(f"Transcript {input.transcript_id} not found")
+
+        runner = PipelineMainWaveform(transcript_id=transcript.id)
+        await runner.run()
+
+    ctx.log("waveform complete")
+    return WaveformResult(waveform_generated=True)
+
+
+@live_post_pipeline.task(
+    execution_timeout=timedelta(seconds=TIMEOUT_TITLE),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
+)
+@with_error_handling(TaskName.GENERATE_TITLE)
+async def generate_title(input: LivePostPipelineInput, ctx: Context) -> TitleResult:
+    """Generate meeting title from topics (runs in parallel with audio chain)."""
+    ctx.log(f"generate_title: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            PipelineMainTitle,
+        )
+
+        runner = PipelineMainTitle(transcript_id=input.transcript_id)
+        await runner.run()
+
+    ctx.log("generate_title complete")
+    return TitleResult(title=None)
+
+
+@live_post_pipeline.task(
+    parents=[waveform],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.CONVERT_MP3)
+async def convert_mp3(input: LivePostPipelineInput, ctx: Context) -> ConvertMp3Result:
+    """Convert WAV recording to MP3."""
+    ctx.log(f"convert_mp3: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            pipeline_convert_to_mp3,
+        )
+
+        await pipeline_convert_to_mp3(transcript_id=input.transcript_id)
+
+    ctx.log("convert_mp3 complete")
+    return ConvertMp3Result(converted=True)
+
+
+@live_post_pipeline.task(
+    parents=[convert_mp3],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.UPLOAD_MP3)
+async def upload_mp3(input: LivePostPipelineInput, ctx: Context) -> UploadMp3Result:
+    """Upload MP3 to external storage."""
+    ctx.log(f"upload_mp3: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            pipeline_upload_mp3,
+        )
+
+        await pipeline_upload_mp3(transcript_id=input.transcript_id)
+
+    ctx.log("upload_mp3 complete")
+    return UploadMp3Result(uploaded=True)
+
+
+@live_post_pipeline.task(
+    parents=[upload_mp3],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=5,
+)
+@with_error_handling(TaskName.REMOVE_UPLOAD)
+async def remove_upload(
+    input: LivePostPipelineInput, ctx: Context
+) -> RemoveUploadResult:
+    """Remove the original upload file."""
+    ctx.log(f"remove_upload: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            pipeline_remove_upload,
+        )
+
+        await pipeline_remove_upload(transcript_id=input.transcript_id)
+
+    ctx.log("remove_upload complete")
+    return RemoveUploadResult(removed=True)
+
+
+@live_post_pipeline.task(
+    parents=[remove_upload],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+@with_error_handling(TaskName.DIARIZE)
+async def diarize(input: LivePostPipelineInput, ctx: Context) -> DiarizeResult:
+    """Run diarization on the recorded audio."""
+    ctx.log(f"diarize: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            pipeline_diarization,
+        )
+
+        await pipeline_diarization(transcript_id=input.transcript_id)
+
+    ctx.log("diarize complete")
+    return DiarizeResult(diarized=True)
+
+
+@live_post_pipeline.task(
+    parents=[diarize],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
+)
+@with_error_handling(TaskName.CLEANUP_CONSENT, set_error_status=False)
+async def cleanup_consent(input: LivePostPipelineInput, ctx: Context) -> ConsentResult:
+    """Check consent and delete audio files if any participant denied."""
+    ctx.log(f"cleanup_consent: transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            cleanup_consent as _cleanup_consent,
+        )
+
+        await _cleanup_consent(transcript_id=input.transcript_id)
+
+    ctx.log("cleanup_consent complete")
+    return ConsentResult()
+
+
+@live_post_pipeline.task(
+    parents=[cleanup_consent, generate_title],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+@with_error_handling(TaskName.FINAL_SUMMARIES)
+async def final_summaries(
+    input: LivePostPipelineInput, ctx: Context
+) -> FinalSummariesResult:
+    """Generate final summaries (fan-in after audio chain + title)."""
+    ctx.log(f"final_summaries: starting for transcript_id={input.transcript_id}")
+
+    async with fresh_db_connection():
+        from reflector.pipelines.main_live_pipeline import (  # noqa: PLC0415
+            pipeline_summaries,
+        )
+
+        await pipeline_summaries(transcript_id=input.transcript_id)
+
+    ctx.log("final_summaries complete")
+    return FinalSummariesResult(generated=True)
+
+
+@live_post_pipeline.task(
+    parents=[final_summaries],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
+)
+@with_error_handling(TaskName.POST_ZULIP, set_error_status=False)
+async def post_zulip(input: LivePostPipelineInput, ctx: Context) -> ZulipResult:
+    """Post notification to Zulip."""
+    ctx.log(f"post_zulip: transcript_id={input.transcript_id}")
+
+    if not settings.ZULIP_REALM:
+        ctx.log("post_zulip skipped (Zulip not configured)")
+        return ZulipResult(zulip_message_id=None, skipped=True)
+
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+        from reflector.zulip import post_transcript_notification  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript:
+            message_id = await post_transcript_notification(transcript)
+            ctx.log(f"post_zulip complete: zulip_message_id={message_id}")
+        else:
+            message_id = None
+
+    return ZulipResult(zulip_message_id=message_id)
+
+
+@live_post_pipeline.task(
+    parents=[final_summaries],
+    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
+)
+@with_error_handling(TaskName.SEND_WEBHOOK, set_error_status=False)
+async def send_webhook(input: LivePostPipelineInput, ctx: Context) -> WebhookResult:
+    """Send completion webhook to external service."""
+    ctx.log(f"send_webhook: transcript_id={input.transcript_id}")
+
+    if not input.room_id:
+        ctx.log("send_webhook skipped (no room_id)")
+        return WebhookResult(webhook_sent=False, skipped=True)
+
+    async with fresh_db_connection():
+        from reflector.db.rooms import rooms_controller  # noqa: PLC0415
+        from reflector.utils.webhook import (  # noqa: PLC0415
+            fetch_transcript_webhook_payload,
+            send_webhook_request,
+        )
+
+        room = await rooms_controller.get_by_id(input.room_id)
+        if not room or not room.webhook_url:
+            ctx.log("send_webhook skipped (no webhook_url configured)")
+            return WebhookResult(webhook_sent=False, skipped=True)
+
+        payload = await fetch_transcript_webhook_payload(
+            transcript_id=input.transcript_id,
+            room_id=input.room_id,
+        )
+
+        if isinstance(payload, str):
+            ctx.log(f"send_webhook skipped (could not build payload): {payload}")
+            return WebhookResult(webhook_sent=False, skipped=True)
+
+        import httpx  # noqa: PLC0415
+
+        try:
+            response = await send_webhook_request(
+                url=room.webhook_url,
+                payload=payload,
+                event_type="transcript.completed",
+                webhook_secret=room.webhook_secret,
+                timeout=30.0,
+            )
+            ctx.log(f"send_webhook complete: status_code={response.status_code}")
+            return WebhookResult(webhook_sent=True, response_code=response.status_code)
+        except httpx.HTTPStatusError as e:
+            ctx.log(f"send_webhook failed (HTTP {e.response.status_code}), continuing")
+            return WebhookResult(
+                webhook_sent=False, response_code=e.response.status_code
+            )
+        except (httpx.ConnectError, httpx.TimeoutException) as e:
+            ctx.log(f"send_webhook failed ({e}), continuing")
+            return WebhookResult(webhook_sent=False)
+        except Exception as e:
+            ctx.log(f"send_webhook unexpected error: {e}")
+            return WebhookResult(webhook_sent=False)
+
+
+# --- On failure handler ---
+
+
+async def on_workflow_failure(input: LivePostPipelineInput, ctx: Context) -> None:
+    """Set transcript status to 'error' only if not already 'ended'."""
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript and transcript.status == "ended":
+            logger.info(
+                "[Hatchet] LivePostProcessingPipeline on_workflow_failure: transcript already ended",
+                transcript_id=input.transcript_id,
+            )
+            ctx.log(
+                "on_workflow_failure: transcript already ended, skipping error status"
+            )
+            return
+    await set_workflow_error_status(input.transcript_id)
+
+
+@live_post_pipeline.on_failure_task()
+async def _register_on_workflow_failure(
+    input: LivePostPipelineInput, ctx: Context
+) -> None:
+    await on_workflow_failure(input, ctx)

server/reflector/pipelines/main_live_pipeline.py

@@ -17,7 +17,7 @@ from contextlib import asynccontextmanager
 from typing import Generic
 
 import av
-from celery import chord, current_task, group, shared_task
+from celery import current_task, shared_task
 from pydantic import BaseModel
 from structlog import BoundLogger as Logger
 
@@ -397,7 +397,9 @@ class PipelineMainLive(PipelineMainBase):
         # when the pipeline ends, connect to the post pipeline
         logger.info("Pipeline main live ended", transcript_id=self.transcript_id)
         logger.info("Scheduling pipeline main post", transcript_id=self.transcript_id)
-        pipeline_post(transcript_id=self.transcript_id)
+        transcript = await transcripts_controller.get_by_id(self.transcript_id)
+        room_id = transcript.room_id if transcript else None
+        await pipeline_post(transcript_id=self.transcript_id, room_id=room_id)
 
 
 class PipelineMainDiarization(PipelineMainBase[AudioDiarizationInput]):
@@ -792,29 +794,20 @@ async def task_pipeline_post_to_zulip(*, transcript_id: str):
     await pipeline_post_to_zulip(transcript_id=transcript_id)
 
 
-def pipeline_post(*, transcript_id: str):
+async def pipeline_post(*, transcript_id: str, room_id: str | None = None):
     """
-    Run the post pipeline
+    Run the post pipeline via Hatchet.
     """
-    chain_mp3_and_diarize = (
-        task_pipeline_waveform.si(transcript_id=transcript_id)
-        | task_pipeline_convert_to_mp3.si(transcript_id=transcript_id)
-        | task_pipeline_upload_mp3.si(transcript_id=transcript_id)
-        | task_pipeline_remove_upload.si(transcript_id=transcript_id)
-        | task_pipeline_diarization.si(transcript_id=transcript_id)
-        | task_cleanup_consent.si(transcript_id=transcript_id)
-    )
-    chain_title_preview = task_pipeline_title.si(transcript_id=transcript_id)
-    chain_final_summaries = task_pipeline_final_summaries.si(
-        transcript_id=transcript_id
-    )
+    from reflector.hatchet.client import HatchetClientManager  # noqa: PLC0415
 
-    chain = chord(
-        group(chain_mp3_and_diarize, chain_title_preview),
-        chain_final_summaries,
-    ) | task_pipeline_post_to_zulip.si(transcript_id=transcript_id)
-
-    return chain.delay()
+    await HatchetClientManager.start_workflow(
+        "LivePostProcessingPipeline",
+        {
+            "transcript_id": str(transcript_id),
+            "room_id": str(room_id) if room_id else None,
+        },
+        additional_metadata={"transcript_id": str(transcript_id)},
+    )
 
 
 @get_transcript

server/reflector/services/transcript_process.py

@@ -10,7 +10,6 @@ from dataclasses import dataclass
 from typing import Literal, Union, assert_never
 
 import celery
-from celery.result import AsyncResult
 from hatchet_sdk.clients.rest.exceptions import ApiException, NotFoundException
 from hatchet_sdk.clients.rest.models import V1TaskStatus
 
@@ -18,7 +17,6 @@ from reflector.db.recordings import recordings_controller
 from reflector.db.transcripts import Transcript, transcripts_controller
 from reflector.hatchet.client import HatchetClientManager
 from reflector.logger import logger
-from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
 from reflector.utils.string import NonEmptyString
 
 
@@ -105,11 +103,8 @@ async def validate_transcript_for_processing(
     ):
         return ValidationNotReady(detail="Recording is not ready for processing")
 
-    # Check Celery tasks
+    # Check Celery tasks (multitrack still uses Celery for some paths)
     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,
     ):
@@ -175,11 +170,8 @@ async def prepare_transcript_processing(validation: ValidationOk) -> PrepareResu
 
 async def dispatch_transcript_processing(
     config: ProcessingConfig, force: bool = False
-) -> AsyncResult | None:
-    """Dispatch transcript processing to appropriate backend (Hatchet or Celery).
-
-    Returns AsyncResult for Celery tasks, None for Hatchet workflows.
-    """
+) -> None:
+    """Dispatch transcript processing to Hatchet workflow engine."""
     if isinstance(config, MultitrackProcessingConfig):
         # Multitrack processing always uses Hatchet (no Celery fallback)
         # First check if we can replay (outside transaction since it's read-only)
@@ -275,7 +267,21 @@ async def dispatch_transcript_processing(
         return None
 
     elif isinstance(config, FileProcessingConfig):
-        return task_pipeline_file_process.delay(transcript_id=config.transcript_id)
+        # File processing uses Hatchet workflow
+        workflow_id = await HatchetClientManager.start_workflow(
+            workflow_name="FilePipeline",
+            input_data={"transcript_id": config.transcript_id},
+            additional_metadata={"transcript_id": config.transcript_id},
+        )
+
+        transcript = await transcripts_controller.get_by_id(config.transcript_id)
+        if transcript:
+            await transcripts_controller.update(
+                transcript, {"workflow_run_id": workflow_id}
+            )
+
+        logger.info("File pipeline dispatched via Hatchet", workflow_id=workflow_id)
+        return None
     else:
         assert_never(config)
 

server/reflector/settings.py

@@ -180,6 +180,7 @@ class Settings(BaseSettings):
     )
 
     # Daily.co integration
+    DAILY_API_URL: str = "https://api.daily.co/v1"
     DAILY_API_KEY: str | None = None
     DAILY_WEBHOOK_SECRET: str | None = None
     DAILY_SUBDOMAIN: str | None = None

server/reflector/tools/process.py

@@ -7,7 +7,6 @@ import asyncio
 import json
 import shutil
 import sys
-import time
 from pathlib import Path
 from typing import Any, Dict, List, Literal, Tuple
 from urllib.parse import unquote, urlparse
@@ -15,10 +14,8 @@ from urllib.parse import unquote, urlparse
 from botocore.exceptions import BotoCoreError, ClientError, NoCredentialsError
 
 from reflector.db.transcripts import SourceKind, TranscriptTopic, transcripts_controller
+from reflector.hatchet.client import HatchetClientManager
 from reflector.logger import logger
-from reflector.pipelines.main_file_pipeline import (
-    task_pipeline_file_process as task_pipeline_file_process,
-)
 from reflector.pipelines.main_live_pipeline import pipeline_post as live_pipeline_post
 from reflector.pipelines.main_live_pipeline import (
     pipeline_process as live_pipeline_process,
@@ -237,29 +234,22 @@ async def process_live_pipeline(
     # assert documented behaviour: after process, the pipeline isn't ended. this is the reason of calling pipeline_post
     assert pre_final_transcript.status != "ended"
 
-    # at this point, diarization is running but we have no access to it. run diarization in parallel - one will hopefully win after polling
-    result = live_pipeline_post(transcript_id=transcript_id)
-
-    # result.ready() blocks even without await; it mutates result also
-    while not result.ready():
-        print(f"Status: {result.state}")
-        time.sleep(2)
+    # Trigger post-processing via Hatchet (fire-and-forget)
+    await live_pipeline_post(transcript_id=transcript_id)
+    print("Live post-processing pipeline triggered via Hatchet", file=sys.stderr)
 
 
 async def process_file_pipeline(
     transcript_id: TranscriptId,
 ):
-    """Process audio/video file using the optimized file pipeline"""
+    """Process audio/video file using the optimized file pipeline via Hatchet"""
 
-    # task_pipeline_file_process is a Celery task, need to use .delay() for async execution
-    result = task_pipeline_file_process.delay(transcript_id=transcript_id)
-
-    # Wait for the Celery task to complete
-    while not result.ready():
-        print(f"File pipeline status: {result.state}", file=sys.stderr)
-        time.sleep(2)
-
-    logger.info("File pipeline processing complete")
+    await HatchetClientManager.start_workflow(
+        "FilePipeline",
+        {"transcript_id": str(transcript_id)},
+        additional_metadata={"transcript_id": str(transcript_id)},
+    )
+    print("File pipeline triggered via Hatchet", file=sys.stderr)
 
 
 async def process(
@@ -293,7 +283,16 @@ async def process(
 
         await handler(transcript_id)
 
-        await extract_result_from_entry(transcript_id, output_path)
+        if pipeline == "file":
+            # File pipeline is async via Hatchet — results not available immediately.
+            # Use reflector.tools.process_transcript with --sync for polling.
+            print(
+                f"File pipeline dispatched for transcript {transcript_id}. "
+                f"Results will be available once the Hatchet workflow completes.",
+                file=sys.stderr,
+            )
+        else:
+            await extract_result_from_entry(transcript_id, output_path)
     finally:
         await database.disconnect()
 

server/reflector/tools/process_transcript.py

@@ -11,10 +11,8 @@ Usage:
 import argparse
 import asyncio
 import sys
-import time
 from typing import Callable
 
-from celery.result import AsyncResult
 from hatchet_sdk.clients.rest.models import V1TaskStatus
 
 import reflector._warnings_filter  # noqa: F401 -- side effect: suppress pydantic validate_default warning
@@ -39,7 +37,7 @@ async def process_transcript_inner(
     on_validation: Callable[[ValidationResult], None],
     on_preprocess: Callable[[PrepareResult], None],
     force: bool = False,
-) -> AsyncResult | None:
+) -> None:
     validation = await validate_transcript_for_processing(transcript)
     on_validation(validation)
     config = await prepare_transcript_processing(validation)
@@ -87,56 +85,39 @@ async def process_transcript(
             elif isinstance(config, FileProcessingConfig):
                 print(f"Dispatching file pipeline", file=sys.stderr)
 
-        result = await process_transcript_inner(
+        await process_transcript_inner(
             transcript,
             on_validation=on_validation,
             on_preprocess=on_preprocess,
             force=force,
         )
 
-        if result is None:
-            # Hatchet workflow dispatched
-            if sync:
-                # Re-fetch transcript to get workflow_run_id
-                transcript = await transcripts_controller.get_by_id(transcript_id)
-                if not transcript or not transcript.workflow_run_id:
-                    print("Error: workflow_run_id not found", file=sys.stderr)
+        if sync:
+            # Re-fetch transcript to get workflow_run_id
+            transcript = await transcripts_controller.get_by_id(transcript_id)
+            if not transcript or not transcript.workflow_run_id:
+                print("Error: workflow_run_id not found", file=sys.stderr)
+                sys.exit(1)
+
+            print("Waiting for Hatchet workflow...", file=sys.stderr)
+            while True:
+                status = await HatchetClientManager.get_workflow_run_status(
+                    transcript.workflow_run_id
+                )
+                print(f"  Status: {status.value}", file=sys.stderr)
+
+                if status == V1TaskStatus.COMPLETED:
+                    print("Workflow completed successfully", file=sys.stderr)
+                    break
+                elif status in (V1TaskStatus.FAILED, V1TaskStatus.CANCELLED):
+                    print(f"Workflow failed: {status}", file=sys.stderr)
                     sys.exit(1)
 
-                print("Waiting for Hatchet workflow...", file=sys.stderr)
-                while True:
-                    status = await HatchetClientManager.get_workflow_run_status(
-                        transcript.workflow_run_id
-                    )
-                    print(f"  Status: {status.value}", file=sys.stderr)
-
-                    if status == V1TaskStatus.COMPLETED:
-                        print("Workflow completed successfully", file=sys.stderr)
-                        break
-                    elif status in (V1TaskStatus.FAILED, V1TaskStatus.CANCELLED):
-                        print(f"Workflow failed: {status}", file=sys.stderr)
-                        sys.exit(1)
-
-                    await asyncio.sleep(5)
-            else:
-                print(
-                    "Task dispatched (use --sync to wait for completion)",
-                    file=sys.stderr,
-                )
-        elif 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)
+                await asyncio.sleep(5)
         else:
             print(
-                "Task dispatched (use --sync to wait for completion)", file=sys.stderr
+                "Task dispatched (use --sync to wait for completion)",
+                file=sys.stderr,
             )
 
     finally:

server/reflector/views/transcripts_process.py

@@ -52,8 +52,5 @@ async def transcript_process(
     if isinstance(config, ProcessError):
         raise HTTPException(status_code=500, detail=config.detail)
     else:
-        # When transcript is in error state, force a new workflow instead of replaying
-        # (replay would re-run from failure point with same conditions and likely fail again)
-        force = transcript.status == "error"
-        await dispatch_transcript_processing(config, force=force)
+        await dispatch_transcript_processing(config, force=True)
         return ProcessStatus(status="ok")

server/reflector/views/transcripts_upload.py

@@ -6,7 +6,7 @@ from pydantic import BaseModel
 
 import reflector.auth as auth
 from reflector.db.transcripts import SourceKind, transcripts_controller
-from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
+from reflector.hatchet.client import HatchetClientManager
 
 router = APIRouter()
 
@@ -95,7 +95,14 @@ async def transcript_record_upload(
         transcript, {"status": "uploaded", "source_kind": SourceKind.FILE}
     )
 
-    # launch a background task to process the file
-    task_pipeline_file_process.delay(transcript_id=transcript_id)
+    # launch Hatchet workflow to process the file
+    workflow_id = await HatchetClientManager.start_workflow(
+        "FilePipeline",
+        {"transcript_id": str(transcript_id)},
+        additional_metadata={"transcript_id": str(transcript_id)},
+    )
+
+    # Save workflow_run_id for duplicate detection and status polling
+    await transcripts_controller.update(transcript, {"workflow_run_id": workflow_id})
 
     return UploadStatus(status="ok")

server/reflector/worker/process.py

@@ -25,7 +25,6 @@ from reflector.db.transcripts import (
     transcripts_controller,
 )
 from reflector.hatchet.client import HatchetClientManager
-from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
 from reflector.pipelines.main_live_pipeline import asynctask
 from reflector.pipelines.topic_processing import EmptyPipeline
 from reflector.processors import AudioFileWriterProcessor
@@ -163,7 +162,14 @@ async def process_recording(bucket_name: str, object_key: str):
 
     await transcripts_controller.update(transcript, {"status": "uploaded"})
 
-    task_pipeline_file_process.delay(transcript_id=transcript.id)
+    await HatchetClientManager.start_workflow(
+        "FilePipeline",
+        {
+            "transcript_id": str(transcript.id),
+            "room_id": str(room.id) if room else None,
+        },
+        additional_metadata={"transcript_id": str(transcript.id)},
+    )
 
 
 @shared_task

server/tests/conftest.py

@@ -1,6 +1,6 @@
 import os
 from contextlib import asynccontextmanager
-from unittest.mock import patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
@@ -538,18 +538,59 @@ def fake_mp3_upload():
 
 
 @pytest.fixture(autouse=True)
-def reset_hatchet_client():
-    """Reset HatchetClientManager singleton before and after each test.
+def mock_hatchet_client():
+    """Mock HatchetClientManager for all tests.
 
-    This ensures test isolation - each test starts with a fresh client state.
-    The fixture is autouse=True so it applies to all tests automatically.
+    Prevents tests from connecting to a real Hatchet server. The dummy token
+    in [tool.pytest_env] prevents the import-time ValueError, but the SDK
+    would still try to connect when get_client() is called. This fixture
+    mocks get_client to return a MagicMock and start_workflow to return a
+    dummy workflow ID.
     """
     from reflector.hatchet.client import HatchetClientManager
 
-    # Reset before test
     HatchetClientManager.reset()
-    yield
-    # Reset after test to clean up
+
+    mock_client = MagicMock()
+    mock_client.workflow.return_value = MagicMock()
+
+    with (
+        patch.object(
+            HatchetClientManager,
+            "get_client",
+            return_value=mock_client,
+        ),
+        patch.object(
+            HatchetClientManager,
+            "start_workflow",
+            new_callable=AsyncMock,
+            return_value="mock-workflow-id",
+        ),
+        patch.object(
+            HatchetClientManager,
+            "get_workflow_run_status",
+            new_callable=AsyncMock,
+            return_value=None,
+        ),
+        patch.object(
+            HatchetClientManager,
+            "can_replay",
+            new_callable=AsyncMock,
+            return_value=False,
+        ),
+        patch.object(
+            HatchetClientManager,
+            "cancel_workflow",
+            new_callable=AsyncMock,
+        ),
+        patch.object(
+            HatchetClientManager,
+            "replay_workflow",
+            new_callable=AsyncMock,
+        ),
+    ):
+        yield mock_client
+
     HatchetClientManager.reset()
 
 

server/tests/docker-compose.integration.yml

@@ -0,0 +1,218 @@
+# Integration test stack — full pipeline end-to-end.
+#
+# Usage:
+#   docker compose -f server/tests/docker-compose.integration.yml up -d --build
+#
+# Requires .env.integration in the repo root (generated by CI workflow).
+
+x-backend-env: &backend-env
+  DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+  REDIS_HOST: redis
+  CELERY_BROKER_URL: redis://redis:6379/1
+  CELERY_RESULT_BACKEND: redis://redis:6379/1
+  HATCHET_CLIENT_TOKEN: ${HATCHET_CLIENT_TOKEN:-}
+  HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+  HATCHET_CLIENT_HOST_PORT: hatchet:7077
+  HATCHET_CLIENT_TLS_STRATEGY: none
+  # ML backends — CPU-only, no external services
+  TRANSCRIPT_BACKEND: whisper
+  WHISPER_CHUNK_MODEL: tiny
+  WHISPER_FILE_MODEL: tiny
+  DIARIZATION_BACKEND: pyannote
+  TRANSLATION_BACKEND: passthrough
+  # Storage — local Garage S3
+  TRANSCRIPT_STORAGE_BACKEND: aws
+  TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL: http://garage:3900
+  TRANSCRIPT_STORAGE_AWS_BUCKET_NAME: reflector-media
+  TRANSCRIPT_STORAGE_AWS_REGION: garage
+  # Daily mock
+  DAILY_API_URL: http://mock-daily:8080/v1
+  DAILY_API_KEY: fake-daily-key
+  # Auth
+  PUBLIC_MODE: "true"
+  AUTH_BACKEND: none
+  # LLM (injected from CI)
+  LLM_URL: ${LLM_URL:-}
+  LLM_API_KEY: ${LLM_API_KEY:-}
+  LLM_MODEL: ${LLM_MODEL:-gpt-4o-mini}
+  # HuggingFace (for pyannote gated models)
+  HF_TOKEN: ${HF_TOKEN:-}
+  # Garage S3 credentials — hardcoded test keys, containers are ephemeral
+  TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID: GK0123456789abcdef01234567 # gitleaks:allow
+  TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY: "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef" # gitleaks:allow
+  # NOTE: DAILYCO_STORAGE_AWS_* intentionally NOT set — forces fallback to
+  # get_transcripts_storage() which has ENDPOINT_URL pointing at Garage.
+  # Setting them would bypass the endpoint and generate presigned URLs for AWS.
+
+services:
+  postgres:
+    image: postgres:17-alpine
+    command: ["postgres", "-c", "max_connections=200"]
+    environment:
+      POSTGRES_USER: reflector
+      POSTGRES_PASSWORD: reflector
+      POSTGRES_DB: reflector
+    volumes:
+      - ../../server/docker/init-hatchet-db.sql:/docker-entrypoint-initdb.d/init-hatchet-db.sql:ro
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U reflector"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+
+  redis:
+    image: redis:7.2-alpine
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 5s
+      timeout: 3s
+      retries: 5
+
+  hatchet:
+    image: ghcr.io/hatchet-dev/hatchet/hatchet-lite:latest
+    depends_on:
+      postgres:
+        condition: service_healthy
+    environment:
+      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable&connect_timeout=30"
+      SERVER_AUTH_COOKIE_INSECURE: "t"
+      SERVER_AUTH_COOKIE_DOMAIN: "localhost"
+      SERVER_GRPC_BIND_ADDRESS: "0.0.0.0"
+      SERVER_GRPC_INSECURE: "t"
+      SERVER_GRPC_BROADCAST_ADDRESS: hatchet:7077
+      SERVER_GRPC_PORT: "7077"
+      SERVER_AUTH_SET_EMAIL_VERIFIED: "t"
+      SERVER_INTERNAL_CLIENT_INTERNAL_GRPC_BROADCAST_ADDRESS: hatchet:7077
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8888/api/live"]
+      interval: 10s
+      timeout: 5s
+      retries: 15
+      start_period: 30s
+
+  garage:
+    image: dxflrs/garage:v1.1.0
+    volumes:
+      - ./integration/garage.toml:/etc/garage.toml:ro
+    healthcheck:
+      test: ["CMD", "/garage", "stats"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+      start_period: 5s
+
+  mock-daily:
+    build:
+      context: .
+      dockerfile: integration/Dockerfile.mock-daily
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8080/v1/recordings/test')"]
+      interval: 5s
+      timeout: 3s
+      retries: 5
+
+  server:
+    build:
+      context: ../../server
+      dockerfile: Dockerfile
+    environment:
+      <<: *backend-env
+      ENTRYPOINT: server
+      WEBRTC_HOST: server
+      WEBRTC_PORT_RANGE: "52000-52100"
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+      hatchet:
+        condition: service_healthy
+      garage:
+        condition: service_healthy
+      mock-daily:
+        condition: service_healthy
+    volumes:
+      - server_data:/app/data
+
+  worker:
+    build:
+      context: ../../server
+      dockerfile: Dockerfile
+    environment:
+      <<: *backend-env
+      ENTRYPOINT: worker
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    volumes:
+      - server_data:/app/data
+
+  hatchet-worker-cpu:
+    build:
+      context: ../../server
+      dockerfile: Dockerfile
+    environment:
+      <<: *backend-env
+      ENTRYPOINT: hatchet-worker-cpu
+    depends_on:
+      hatchet:
+        condition: service_healthy
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    volumes:
+      - server_data:/app/data
+
+  hatchet-worker-llm:
+    build:
+      context: ../../server
+      dockerfile: Dockerfile
+    environment:
+      <<: *backend-env
+      ENTRYPOINT: hatchet-worker-llm
+    depends_on:
+      hatchet:
+        condition: service_healthy
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    volumes:
+      - server_data:/app/data
+
+  test-runner:
+    build:
+      context: ../../server
+      dockerfile: Dockerfile
+    environment:
+      <<: *backend-env
+      # Override DATABASE_URL for sync driver (used by direct DB access in tests)
+      DATABASE_URL_ASYNC: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      SERVER_URL: http://server:1250
+      GARAGE_ENDPOINT: http://garage:3900
+    depends_on:
+      server:
+        condition: service_started
+      worker:
+        condition: service_started
+      hatchet-worker-cpu:
+        condition: service_started
+      hatchet-worker-llm:
+        condition: service_started
+    volumes:
+      - server_data:/app/data
+      # Mount test files into the container
+      - ./records:/app/tests/records:ro
+      - ./integration:/app/tests/integration:ro
+    entrypoint: ["sleep", "infinity"]
+
+volumes:
+  server_data:
+
+networks:
+  default:
+    attachable: true

server/tests/integration/Dockerfile.mock-daily

@@ -0,0 +1,9 @@
+FROM python:3.12-slim
+
+RUN pip install --no-cache-dir fastapi uvicorn[standard]
+
+WORKDIR /app
+COPY integration/mock_daily_server.py /app/mock_daily_server.py
+
+EXPOSE 8080
+CMD ["uvicorn", "mock_daily_server:app", "--host", "0.0.0.0", "--port", "8080"]

server/tests/integration/conftest.py

@@ -0,0 +1,116 @@
+"""
+Integration test fixtures — no mocks, real services.
+
+All services (PostgreSQL, Redis, Hatchet, Garage, server, workers) are
+expected to be running via docker-compose.integration.yml.
+"""
+
+import asyncio
+import os
+from pathlib import Path
+
+import boto3
+import httpx
+import pytest
+import pytest_asyncio
+from sqlalchemy.ext.asyncio import create_async_engine
+
+SERVER_URL = os.environ.get("SERVER_URL", "http://server:1250")
+GARAGE_ENDPOINT = os.environ.get("GARAGE_ENDPOINT", "http://garage:3900")
+DATABASE_URL = os.environ.get(
+    "DATABASE_URL_ASYNC",
+    os.environ.get(
+        "DATABASE_URL",
+        "postgresql+asyncpg://reflector:reflector@postgres:5432/reflector",
+    ),
+)
+GARAGE_KEY_ID = os.environ.get("TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID", "")
+GARAGE_KEY_SECRET = os.environ.get("TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY", "")
+BUCKET_NAME = "reflector-media"
+
+
+@pytest_asyncio.fixture
+async def api_client():
+    """HTTP client pointed at the running server."""
+    async with httpx.AsyncClient(
+        base_url=f"{SERVER_URL}/v1",
+        timeout=httpx.Timeout(30.0),
+    ) as client:
+        yield client
+
+
+@pytest.fixture(scope="session")
+def s3_client():
+    """Boto3 S3 client pointed at Garage."""
+    return boto3.client(
+        "s3",
+        endpoint_url=GARAGE_ENDPOINT,
+        aws_access_key_id=GARAGE_KEY_ID,
+        aws_secret_access_key=GARAGE_KEY_SECRET,
+        region_name="garage",
+    )
+
+
+@pytest_asyncio.fixture
+async def db_engine():
+    """SQLAlchemy async engine for direct DB operations."""
+    engine = create_async_engine(DATABASE_URL)
+    yield engine
+    await engine.dispose()
+
+
+@pytest.fixture(scope="session")
+def test_records_dir():
+    """Path to the test audio files directory."""
+    return Path(__file__).parent.parent / "records"
+
+
+@pytest.fixture(scope="session")
+def bucket_name():
+    """S3 bucket name used for integration tests."""
+    return BUCKET_NAME
+
+
+async def _poll_transcript_status(
+    client: httpx.AsyncClient,
+    transcript_id: str,
+    target: str | tuple[str, ...],
+    error: str = "error",
+    max_wait: int = 300,
+    interval: int = 3,
+) -> dict:
+    """
+    Poll GET /transcripts/{id} until status matches target or error.
+
+    target can be a single status string or a tuple of acceptable statuses.
+    Returns the transcript dict on success, raises on timeout or error status.
+    """
+    targets = (target,) if isinstance(target, str) else target
+    elapsed = 0
+    status = None
+    while elapsed < max_wait:
+        resp = await client.get(f"/transcripts/{transcript_id}")
+        resp.raise_for_status()
+        data = resp.json()
+        status = data.get("status")
+
+        if status in targets:
+            return data
+        if status == error:
+            raise AssertionError(
+                f"Transcript {transcript_id} reached error status: {data}"
+            )
+
+        await asyncio.sleep(interval)
+        elapsed += interval
+
+    raise TimeoutError(
+        f"Transcript {transcript_id} did not reach status '{target}' "
+        f"within {max_wait}s (last status: {status})"
+    )
+
+
+@pytest_asyncio.fixture
+def poll_transcript_status():
+    """Returns the poll_transcript_status async helper function."""
+    return _poll_transcript_status

server/tests/integration/garage.toml

@@ -0,0 +1,14 @@
+metadata_dir = "/var/lib/garage/meta"
+data_dir = "/var/lib/garage/data"
+replication_factor = 1
+
+rpc_secret = "abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789" # gitleaks:allow
+rpc_bind_addr = "[::]:3901"
+
+[s3_api]
+api_bind_addr = "[::]:3900"
+s3_region = "garage"
+root_domain = ".s3.garage.localhost"
+
+[admin]
+api_bind_addr = "[::]:3903"

server/tests/integration/garage_setup.sh

@@ -0,0 +1,62 @@
+#!/bin/sh
+#
+# Initialize Garage bucket and keys for integration tests.
+# Run inside the Garage container after it's healthy.
+#
+# Outputs KEY_ID and KEY_SECRET to stdout (last two lines).
+#
+# Note: uses /bin/sh (not bash) since the Garage container is minimal.
+#
+set -eu
+
+echo "Waiting for Garage to be ready..."
+i=0
+while [ "$i" -lt 30 ]; do
+    if /garage stats >/dev/null 2>&1; then
+        break
+    fi
+    sleep 1
+    i=$((i + 1))
+done
+
+# Layout setup
+NODE_ID=$(/garage node id -q | tr -d '[:space:]')
+LAYOUT_STATUS=$(/garage layout show 2>&1 || true)
+if echo "$LAYOUT_STATUS" | grep -q "No nodes"; then
+    /garage layout assign "$NODE_ID" -c 1G -z dc1
+    /garage layout apply --version 1
+    echo "Layout applied."
+else
+    echo "Layout already configured."
+fi
+
+# Bucket
+if ! /garage bucket info reflector-media >/dev/null 2>&1; then
+    /garage bucket create reflector-media
+    echo "Bucket 'reflector-media' created."
+else
+    echo "Bucket 'reflector-media' already exists."
+fi
+
+# Key
+if /garage key info reflector-test >/dev/null 2>&1; then
+    echo "Key 'reflector-test' already exists."
+    KEY_OUTPUT=$(/garage key info reflector-test 2>&1)
+else
+    KEY_OUTPUT=$(/garage key create reflector-test 2>&1)
+    echo "Key 'reflector-test' created."
+fi
+
+# Permissions
+/garage bucket allow reflector-media --read --write --key reflector-test
+
+# Extract key ID and secret from output using POSIX-compatible parsing
+# garage key output format:
+#   Key name: reflector-test
+#   Key ID: GK...
+#   Secret key: ...
+KEY_ID=$(echo "$KEY_OUTPUT" | grep "Key ID" | sed 's/.*Key ID: *//')
+KEY_SECRET=$(echo "$KEY_OUTPUT" | grep "Secret key" | sed 's/.*Secret key: *//')
+
+echo "GARAGE_KEY_ID=${KEY_ID}"
+echo "GARAGE_KEY_SECRET=${KEY_SECRET}"

server/tests/integration/mock_daily_server.py

@@ -0,0 +1,75 @@
+"""
+Minimal FastAPI mock for Daily.co API.
+
+Serves canned responses for:
+- GET /v1/recordings/{recording_id}
+- GET /v1/meetings/{meeting_id}/participants
+"""
+
+from fastapi import FastAPI
+
+app = FastAPI(title="Mock Daily API")
+
+
+# Participant UUIDs must be 36-char hex UUIDs to match Daily's filename format
+PARTICIPANT_A_ID = "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
+PARTICIPANT_B_ID = "bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb"
+
+# Daily-format track keys: {recording_start_ts}-{participant_id}-cam-audio-{track_start_ts}
+TRACK_KEYS = [
+    f"1700000000000-{PARTICIPANT_A_ID}-cam-audio-1700000001000",
+    f"1700000000000-{PARTICIPANT_B_ID}-cam-audio-1700000001000",
+]
+
+
+@app.get("/v1/recordings/{recording_id}")
+async def get_recording(recording_id: str):
+    return {
+        "id": recording_id,
+        "room_name": "integration-test-room",
+        "start_ts": 1700000000,
+        "type": "raw-tracks",
+        "status": "finished",
+        "max_participants": 2,
+        "duration": 5,
+        "share_token": None,
+        "s3": {
+            "bucket_name": "reflector-media",
+            "bucket_region": "garage",
+            "key": None,
+            "endpoint": None,
+        },
+        "s3key": None,
+        "tracks": [
+            {"type": "audio", "s3Key": key, "size": 100000} for key in TRACK_KEYS
+        ],
+        "mtgSessionId": "mock-mtg-session-id",
+    }
+
+
+@app.get("/v1/meetings/{meeting_id}/participants")
+async def get_meeting_participants(meeting_id: str):
+    return {
+        "data": [
+            {
+                "user_id": "user-a",
+                "participant_id": PARTICIPANT_A_ID,
+                "user_name": "Speaker A",
+                "join_time": 1700000000,
+                "duration": 300,
+            },
+            {
+                "user_id": "user-b",
+                "participant_id": PARTICIPANT_B_ID,
+                "user_name": "Speaker B",
+                "join_time": 1700000010,
+                "duration": 290,
+            },
+        ]
+    }
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=8080)

server/tests/integration/test_file_pipeline.py

@@ -0,0 +1,61 @@
+"""
+Integration test: File upload → FilePipeline → full processing.
+
+Exercises: upload endpoint → Hatchet FilePipeline → whisper transcription →
+pyannote diarization → LLM summarization/topics → status "ended".
+"""
+
+import pytest
+
+
+@pytest.mark.asyncio
+async def test_file_pipeline_end_to_end(
+    api_client, test_records_dir, poll_transcript_status
+):
+    """Upload a WAV file and verify the full pipeline completes."""
+    # 1. Create transcript
+    resp = await api_client.post(
+        "/transcripts",
+        json={"name": "integration-file-test", "source_kind": "file"},
+    )
+    assert resp.status_code == 200, f"Failed to create transcript: {resp.text}"
+    transcript = resp.json()
+    transcript_id = transcript["id"]
+
+    # 2. Upload audio file (single chunk)
+    audio_path = test_records_dir / "test_short.wav"
+    assert audio_path.exists(), f"Test audio file not found: {audio_path}"
+
+    with open(audio_path, "rb") as f:
+        resp = await api_client.post(
+            f"/transcripts/{transcript_id}/record/upload",
+            params={"chunk_number": 0, "total_chunks": 1},
+            files={"chunk": ("test_short.wav", f, "audio/wav")},
+        )
+    assert resp.status_code == 200, f"Upload failed: {resp.text}"
+
+    # 3. Poll until pipeline completes
+    data = await poll_transcript_status(
+        api_client, transcript_id, target="ended", max_wait=300
+    )
+
+    # 4. Assertions
+    assert data["status"] == "ended"
+    assert data.get("title") and len(data["title"]) > 0, "Title should be non-empty"
+    assert (
+        data.get("long_summary") and len(data["long_summary"]) > 0
+    ), "Long summary should be non-empty"
+    assert (
+        data.get("short_summary") and len(data["short_summary"]) > 0
+    ), "Short summary should be non-empty"
+
+    # Topics are served from a separate endpoint
+    topics_resp = await api_client.get(f"/transcripts/{transcript_id}/topics")
+    assert topics_resp.status_code == 200, f"Failed to get topics: {topics_resp.text}"
+    topics = topics_resp.json()
+    assert len(topics) >= 1, "Should have at least 1 topic"
+    for topic in topics:
+        assert topic.get("title"), "Each topic should have a title"
+        assert topic.get("summary"), "Each topic should have a summary"
+
+    assert data.get("duration", 0) > 0, "Duration should be positive"

server/tests/integration/test_live_pipeline.py

@@ -0,0 +1,109 @@
+"""
+Integration test: WebRTC stream → LivePostProcessingPipeline → full processing.
+
+Exercises: WebRTC SDP exchange → live audio streaming → connection close →
+Hatchet LivePostPipeline → whisper transcription → LLM summarization/topics → status "ended".
+"""
+
+import asyncio
+import json
+import os
+
+import httpx
+import pytest
+from aiortc import RTCPeerConnection, RTCSessionDescription
+from aiortc.contrib.media import MediaPlayer
+
+SERVER_URL = os.environ.get("SERVER_URL", "http://server:1250")
+
+
+@pytest.mark.asyncio
+async def test_live_pipeline_end_to_end(
+    api_client, test_records_dir, poll_transcript_status
+):
+    """Stream audio via WebRTC and verify the full post-processing pipeline completes."""
+    # 1. Create transcript
+    resp = await api_client.post(
+        "/transcripts",
+        json={"name": "integration-live-test"},
+    )
+    assert resp.status_code == 200, f"Failed to create transcript: {resp.text}"
+    transcript = resp.json()
+    transcript_id = transcript["id"]
+
+    # 2. Set up WebRTC peer connection with audio from test file
+    audio_path = test_records_dir / "test_short.wav"
+    assert audio_path.exists(), f"Test audio file not found: {audio_path}"
+
+    pc = RTCPeerConnection()
+    player = MediaPlayer(audio_path.as_posix())
+
+    # Add audio track
+    audio_track = player.audio
+    pc.addTrack(audio_track)
+
+    # Create data channel (server expects this for STOP command)
+    channel = pc.createDataChannel("data-channel")
+
+    # 3. Generate SDP offer
+    offer = await pc.createOffer()
+    await pc.setLocalDescription(offer)
+
+    sdp_payload = {
+        "sdp": pc.localDescription.sdp,
+        "type": pc.localDescription.type,
+    }
+
+    # 4. Send offer to server and get answer
+    webrtc_url = f"{SERVER_URL}/v1/transcripts/{transcript_id}/record/webrtc"
+    async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
+        resp = await client.post(webrtc_url, json=sdp_payload)
+    assert resp.status_code == 200, f"WebRTC offer failed: {resp.text}"
+
+    answer_data = resp.json()
+    answer = RTCSessionDescription(sdp=answer_data["sdp"], type=answer_data["type"])
+    await pc.setRemoteDescription(answer)
+
+    # 5. Wait for audio playback to finish
+    max_stream_wait = 60
+    elapsed = 0
+    while elapsed < max_stream_wait:
+        if audio_track.readyState == "ended":
+            break
+        await asyncio.sleep(0.5)
+        elapsed += 0.5
+
+    # 6. Send STOP command and close connection
+    try:
+        channel.send(json.dumps({"cmd": "STOP"}))
+        await asyncio.sleep(1)
+    except Exception:
+        pass  # Channel may not be open if track ended quickly
+
+    await pc.close()
+
+    # 7. Poll until post-processing pipeline completes
+    data = await poll_transcript_status(
+        api_client, transcript_id, target="ended", max_wait=300
+    )
+
+    # 8. Assertions
+    assert data["status"] == "ended"
+    assert data.get("title") and len(data["title"]) > 0, "Title should be non-empty"
+    assert (
+        data.get("long_summary") and len(data["long_summary"]) > 0
+    ), "Long summary should be non-empty"
+    assert (
+        data.get("short_summary") and len(data["short_summary"]) > 0
+    ), "Short summary should be non-empty"
+
+    # Topics are served from a separate endpoint
+    topics_resp = await api_client.get(f"/transcripts/{transcript_id}/topics")
+    assert topics_resp.status_code == 200, f"Failed to get topics: {topics_resp.text}"
+    topics = topics_resp.json()
+    assert len(topics) >= 1, "Should have at least 1 topic"
+    for topic in topics:
+        assert topic.get("title"), "Each topic should have a title"
+        assert topic.get("summary"), "Each topic should have a summary"
+
+    assert data.get("duration", 0) > 0, "Duration should be positive"

server/tests/integration/test_multitrack_pipeline.py

@@ -0,0 +1,129 @@
+"""
+Integration test: Multitrack → DailyMultitrackPipeline → full processing.
+
+Exercises: S3 upload → DB recording setup → process endpoint →
+Hatchet DiarizationPipeline → mock Daily API → whisper per-track transcription →
+diarization → mixdown → LLM summarization/topics → status "ended".
+"""
+
+import json
+from datetime import datetime, timezone
+
+import pytest
+from sqlalchemy import text
+
+# Must match Daily's filename format: {recording_start_ts}-{participant_uuid}-cam-audio-{track_start_ts}
+# These UUIDs must match mock_daily_server.py participant IDs
+PARTICIPANT_A_ID = "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
+PARTICIPANT_B_ID = "bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb"
+TRACK_KEYS = [
+    f"1700000000000-{PARTICIPANT_A_ID}-cam-audio-1700000001000",
+    f"1700000000000-{PARTICIPANT_B_ID}-cam-audio-1700000001000",
+]
+
+
+@pytest.mark.asyncio
+async def test_multitrack_pipeline_end_to_end(
+    api_client,
+    s3_client,
+    db_engine,
+    test_records_dir,
+    bucket_name,
+    poll_transcript_status,
+):
+    """Set up multitrack recording in S3/DB and verify the full pipeline completes."""
+    # 1. Upload test audio as two separate tracks to Garage S3
+    audio_path = test_records_dir / "test_short.wav"
+    assert audio_path.exists(), f"Test audio file not found: {audio_path}"
+
+    for track_key in TRACK_KEYS:
+        s3_client.upload_file(
+            str(audio_path),
+            bucket_name,
+            track_key,
+        )
+
+    # 2. Create transcript via API
+    resp = await api_client.post(
+        "/transcripts",
+        json={"name": "integration-multitrack-test"},
+    )
+    assert resp.status_code == 200, f"Failed to create transcript: {resp.text}"
+    transcript = resp.json()
+    transcript_id = transcript["id"]
+
+    # 3. Insert Recording row and link to transcript via direct DB access
+    recording_id = f"rec-integration-{transcript_id[:8]}"
+    now = datetime.now(timezone.utc)
+
+    async with db_engine.begin() as conn:
+        # Insert recording with track_keys
+        await conn.execute(
+            text("""
+                INSERT INTO recording (id, bucket_name, object_key, recorded_at, status, track_keys)
+                VALUES (:id, :bucket_name, :object_key, :recorded_at, :status, CAST(:track_keys AS json))
+            """),
+            {
+                "id": recording_id,
+                "bucket_name": bucket_name,
+                "object_key": TRACK_KEYS[0],
+                "recorded_at": now,
+                "status": "completed",
+                "track_keys": json.dumps(TRACK_KEYS),
+            },
+        )
+
+        # Link recording to transcript and set status to uploaded
+        await conn.execute(
+            text("""
+                UPDATE transcript
+                SET recording_id = :recording_id, status = 'uploaded'
+                WHERE id = :transcript_id
+            """),
+            {
+                "recording_id": recording_id,
+                "transcript_id": transcript_id,
+            },
+        )
+
+    # 4. Trigger processing via process endpoint
+    resp = await api_client.post(f"/transcripts/{transcript_id}/process")
+    assert resp.status_code == 200, f"Process trigger failed: {resp.text}"
+
+    # 5. Poll until pipeline completes
+    # The pipeline will call mock-daily for get_recording and get_participants
+    # Accept "error" too — non-critical steps like action_items may fail due to
+    # LLM parsing flakiness while core results (transcript, summaries) still exist.
+    data = await poll_transcript_status(
+        api_client, transcript_id, target=("ended", "error"), max_wait=300
+    )
+
+    # 6. Assertions — verify core pipeline results regardless of final status
+    assert data.get("title") and len(data["title"]) > 0, "Title should be non-empty"
+    assert (
+        data.get("long_summary") and len(data["long_summary"]) > 0
+    ), "Long summary should be non-empty"
+    assert (
+        data.get("short_summary") and len(data["short_summary"]) > 0
+    ), "Short summary should be non-empty"
+
+    # Topics are served from a separate endpoint
+    topics_resp = await api_client.get(f"/transcripts/{transcript_id}/topics")
+    assert topics_resp.status_code == 200, f"Failed to get topics: {topics_resp.text}"
+    topics = topics_resp.json()
+    assert len(topics) >= 1, "Should have at least 1 topic"
+    for topic in topics:
+        assert topic.get("title"), "Each topic should have a title"
+        assert topic.get("summary"), "Each topic should have a summary"
+
+    # Participants are served from a separate endpoint
+    participants_resp = await api_client.get(
+        f"/transcripts/{transcript_id}/participants"
+    )
+    assert (
+        participants_resp.status_code == 200
+    ), f"Failed to get participants: {participants_resp.text}"
+    participants = participants_resp.json()
+    assert (
+        len(participants) >= 2
+    ), f"Expected at least 2 speakers for multitrack, got {len(participants)}"

server/tests/test_hatchet_client.py

@@ -37,18 +37,3 @@ async def test_hatchet_client_can_replay_handles_exception():
 
             # Should return False on error (workflow might be gone)
             assert can_replay is False
-
-
-def test_hatchet_client_raises_without_token():
-    """Test that get_client raises ValueError without token.
-
-    Useful: Catches if someone removes the token validation,
-    which would cause cryptic errors later.
-    """
-    from reflector.hatchet.client import HatchetClientManager
-
-    with patch("reflector.hatchet.client.settings") as mock_settings:
-        mock_settings.HATCHET_CLIENT_TOKEN = None
-
-        with pytest.raises(ValueError, match="HATCHET_CLIENT_TOKEN must be set"):
-            HatchetClientManager.get_client()

server/tests/test_hatchet_file_pipeline.py

@@ -0,0 +1,233 @@
+"""
+Tests for the FilePipeline Hatchet workflow.
+
+Tests verify:
+1. with_error_handling behavior for file pipeline input model
+2. on_workflow_failure logic (don't overwrite 'ended' status)
+3. Input model validation
+"""
+
+from contextlib import asynccontextmanager
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import httpx
+import pytest
+from hatchet_sdk import NonRetryableException
+
+
+@asynccontextmanager
+async def _noop_db_context():
+    """Async context manager that yields without touching the DB."""
+    yield None
+
+
+@pytest.fixture(scope="module")
+def file_pipeline_module():
+    """Import file_pipeline with Hatchet client mocked."""
+    mock_client = MagicMock()
+    mock_client.workflow.return_value = MagicMock()
+    with patch(
+        "reflector.hatchet.client.HatchetClientManager.get_client",
+        return_value=mock_client,
+    ):
+        from reflector.hatchet.workflows import file_pipeline
+
+        return file_pipeline
+
+
+@pytest.fixture
+def mock_file_input():
+    """Minimal FilePipelineInput for tests."""
+    from reflector.hatchet.workflows.file_pipeline import FilePipelineInput
+
+    return FilePipelineInput(
+        transcript_id="ts-file-123",
+        room_id="room-456",
+    )
+
+
+@pytest.fixture
+def mock_ctx():
+    """Minimal Context-like object."""
+    ctx = MagicMock()
+    ctx.log = MagicMock()
+    return ctx
+
+
+def test_file_pipeline_input_model():
+    """Test FilePipelineInput validation."""
+    from reflector.hatchet.workflows.file_pipeline import FilePipelineInput
+
+    # Valid input with room_id
+    input_with_room = FilePipelineInput(transcript_id="ts-123", room_id="room-456")
+    assert input_with_room.transcript_id == "ts-123"
+    assert input_with_room.room_id == "room-456"
+
+    # Valid input without room_id
+    input_no_room = FilePipelineInput(transcript_id="ts-123")
+    assert input_no_room.room_id is None
+
+
+@pytest.mark.asyncio
+async def test_file_pipeline_error_handling_transient(
+    file_pipeline_module, mock_file_input, mock_ctx
+):
+    """Transient exception must NOT set error status."""
+    from reflector.hatchet.workflows.daily_multitrack_pipeline import (
+        TaskName,
+        with_error_handling,
+    )
+
+    async def failing_task(input, ctx):
+        raise httpx.TimeoutException("timed out")
+
+    wrapped = with_error_handling(TaskName.EXTRACT_AUDIO)(failing_task)
+
+    with patch(
+        "reflector.hatchet.workflows.daily_multitrack_pipeline.set_workflow_error_status",
+        new_callable=AsyncMock,
+    ) as mock_set_error:
+        with pytest.raises(httpx.TimeoutException):
+            await wrapped(mock_file_input, mock_ctx)
+
+        mock_set_error.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_file_pipeline_error_handling_hard_fail(
+    file_pipeline_module, mock_file_input, mock_ctx
+):
+    """Hard-fail (ValueError) must set error status and raise NonRetryableException."""
+    from reflector.hatchet.workflows.daily_multitrack_pipeline import (
+        TaskName,
+        with_error_handling,
+    )
+
+    async def failing_task(input, ctx):
+        raise ValueError("No audio file found")
+
+    wrapped = with_error_handling(TaskName.EXTRACT_AUDIO)(failing_task)
+
+    with patch(
+        "reflector.hatchet.workflows.daily_multitrack_pipeline.set_workflow_error_status",
+        new_callable=AsyncMock,
+    ) as mock_set_error:
+        with pytest.raises(NonRetryableException) as exc_info:
+            await wrapped(mock_file_input, mock_ctx)
+
+        assert "No audio file found" in str(exc_info.value)
+        mock_set_error.assert_called_once_with("ts-file-123")
+
+
+def test_diarize_result_uses_plain_dicts():
+    """DiarizationSegment is a TypedDict (plain dict), not a Pydantic model.
+
+    The diarize task must serialize segments as plain dicts (not call .model_dump()),
+    and assemble_transcript must be able to reconstruct them with DiarizationSegment(**s).
+    This was a real bug: 'dict' object has no attribute 'model_dump'.
+    """
+    from reflector.hatchet.workflows.file_pipeline import DiarizeResult
+    from reflector.processors.types import DiarizationSegment
+
+    # DiarizationSegment is a TypedDict — instances are plain dicts
+    segments = [
+        DiarizationSegment(start=0.0, end=1.5, speaker=0),
+        DiarizationSegment(start=1.5, end=3.0, speaker=1),
+    ]
+    assert isinstance(segments[0], dict), "DiarizationSegment should be a plain dict"
+
+    # DiarizeResult should accept list[dict] directly (no model_dump needed)
+    result = DiarizeResult(diarization=segments)
+    assert result.diarization is not None
+    assert len(result.diarization) == 2
+
+    # Consumer (assemble_transcript) reconstructs via DiarizationSegment(**s)
+    reconstructed = [DiarizationSegment(**s) for s in result.diarization]
+    assert reconstructed[0]["start"] == 0.0
+    assert reconstructed[0]["speaker"] == 0
+    assert reconstructed[1]["end"] == 3.0
+    assert reconstructed[1]["speaker"] == 1
+
+
+def test_diarize_result_handles_none():
+    """DiarizeResult with no diarization data (diarization disabled)."""
+    from reflector.hatchet.workflows.file_pipeline import DiarizeResult
+
+    result = DiarizeResult(diarization=None)
+    assert result.diarization is None
+
+    result_default = DiarizeResult()
+    assert result_default.diarization is None
+
+
+def test_transcribe_result_words_are_pydantic():
+    """TranscribeResult words come from Pydantic Word.model_dump() — verify roundtrip."""
+    from reflector.hatchet.workflows.file_pipeline import TranscribeResult
+    from reflector.processors.types import Word
+
+    words = [
+        Word(text="hello", start=0.0, end=0.5),
+        Word(text="world", start=0.5, end=1.0),
+    ]
+    # Words are Pydantic models, so model_dump() works
+    word_dicts = [w.model_dump() for w in words]
+    result = TranscribeResult(words=word_dicts)
+
+    # Consumer reconstructs via Word(**w)
+    reconstructed = [Word(**w) for w in result.words]
+    assert reconstructed[0].text == "hello"
+    assert reconstructed[1].start == 0.5
+
+
+@pytest.mark.asyncio
+async def test_file_pipeline_on_failure_sets_error_status(
+    file_pipeline_module, mock_file_input, mock_ctx
+):
+    """on_workflow_failure sets error status when transcript is processing."""
+    from reflector.hatchet.workflows.file_pipeline import on_workflow_failure
+
+    transcript_processing = MagicMock()
+    transcript_processing.status = "processing"
+
+    with patch(
+        "reflector.hatchet.workflows.file_pipeline.fresh_db_connection",
+        _noop_db_context,
+    ):
+        with patch(
+            "reflector.db.transcripts.transcripts_controller.get_by_id",
+            new_callable=AsyncMock,
+            return_value=transcript_processing,
+        ):
+            with patch(
+                "reflector.hatchet.workflows.file_pipeline.set_workflow_error_status",
+                new_callable=AsyncMock,
+            ) as mock_set_error:
+                await on_workflow_failure(mock_file_input, mock_ctx)
+                mock_set_error.assert_called_once_with(mock_file_input.transcript_id)
+
+
+@pytest.mark.asyncio
+async def test_file_pipeline_on_failure_does_not_overwrite_ended(
+    file_pipeline_module, mock_file_input, mock_ctx
+):
+    """on_workflow_failure must NOT overwrite 'ended' status."""
+    from reflector.hatchet.workflows.file_pipeline import on_workflow_failure
+
+    transcript_ended = MagicMock()
+    transcript_ended.status = "ended"
+
+    with patch(
+        "reflector.hatchet.workflows.file_pipeline.fresh_db_connection",
+        _noop_db_context,
+    ):
+        with patch(
+            "reflector.db.transcripts.transcripts_controller.get_by_id",
+            new_callable=AsyncMock,
+            return_value=transcript_ended,
+        ):
+            with patch(
+                "reflector.hatchet.workflows.file_pipeline.set_workflow_error_status",
+                new_callable=AsyncMock,
+            ) as mock_set_error:
+                await on_workflow_failure(mock_file_input, mock_ctx)
+                mock_set_error.assert_not_called()

server/tests/test_hatchet_live_post_pipeline.py

@@ -0,0 +1,218 @@
+"""
+Tests for the LivePostProcessingPipeline Hatchet workflow.
+
+Tests verify:
+1. with_error_handling behavior for live post pipeline input model
+2. on_workflow_failure logic (don't overwrite 'ended' status)
+3. Input model validation
+4. pipeline_post() now triggers Hatchet instead of Celery chord
+"""
+
+from contextlib import asynccontextmanager
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import httpx
+import pytest
+from hatchet_sdk import NonRetryableException
+
+
+@asynccontextmanager
+async def _noop_db_context():
+    """Async context manager that yields without touching the DB."""
+    yield None
+
+
+@pytest.fixture(scope="module")
+def live_pipeline_module():
+    """Import live_post_pipeline with Hatchet client mocked."""
+    mock_client = MagicMock()
+    mock_client.workflow.return_value = MagicMock()
+    with patch(
+        "reflector.hatchet.client.HatchetClientManager.get_client",
+        return_value=mock_client,
+    ):
+        from reflector.hatchet.workflows import live_post_pipeline
+
+        return live_post_pipeline
+
+
+@pytest.fixture
+def mock_live_input():
+    """Minimal LivePostPipelineInput for tests."""
+    from reflector.hatchet.workflows.live_post_pipeline import LivePostPipelineInput
+
+    return LivePostPipelineInput(
+        transcript_id="ts-live-789",
+        room_id="room-abc",
+    )
+
+
+@pytest.fixture
+def mock_ctx():
+    """Minimal Context-like object."""
+    ctx = MagicMock()
+    ctx.log = MagicMock()
+    return ctx
+
+
+def test_live_post_pipeline_input_model():
+    """Test LivePostPipelineInput validation."""
+    from reflector.hatchet.workflows.live_post_pipeline import LivePostPipelineInput
+
+    # Valid input with room_id
+    input_with_room = LivePostPipelineInput(transcript_id="ts-123", room_id="room-456")
+    assert input_with_room.transcript_id == "ts-123"
+    assert input_with_room.room_id == "room-456"
+
+    # Valid input without room_id
+    input_no_room = LivePostPipelineInput(transcript_id="ts-123")
+    assert input_no_room.room_id is None
+
+
+@pytest.mark.asyncio
+async def test_live_pipeline_error_handling_transient(
+    live_pipeline_module, mock_live_input, mock_ctx
+):
+    """Transient exception must NOT set error status."""
+    from reflector.hatchet.workflows.daily_multitrack_pipeline import (
+        TaskName,
+        with_error_handling,
+    )
+
+    async def failing_task(input, ctx):
+        raise httpx.TimeoutException("timed out")
+
+    wrapped = with_error_handling(TaskName.WAVEFORM)(failing_task)
+
+    with patch(
+        "reflector.hatchet.workflows.daily_multitrack_pipeline.set_workflow_error_status",
+        new_callable=AsyncMock,
+    ) as mock_set_error:
+        with pytest.raises(httpx.TimeoutException):
+            await wrapped(mock_live_input, mock_ctx)
+
+        mock_set_error.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_live_pipeline_error_handling_hard_fail(
+    live_pipeline_module, mock_live_input, mock_ctx
+):
+    """Hard-fail must set error status and raise NonRetryableException."""
+    from reflector.hatchet.workflows.daily_multitrack_pipeline import (
+        TaskName,
+        with_error_handling,
+    )
+
+    async def failing_task(input, ctx):
+        raise ValueError("Transcript not found")
+
+    wrapped = with_error_handling(TaskName.WAVEFORM)(failing_task)
+
+    with patch(
+        "reflector.hatchet.workflows.daily_multitrack_pipeline.set_workflow_error_status",
+        new_callable=AsyncMock,
+    ) as mock_set_error:
+        with pytest.raises(NonRetryableException) as exc_info:
+            await wrapped(mock_live_input, mock_ctx)
+
+        assert "Transcript not found" in str(exc_info.value)
+        mock_set_error.assert_called_once_with("ts-live-789")
+
+
+@pytest.mark.asyncio
+async def test_live_pipeline_on_failure_sets_error_status(
+    live_pipeline_module, mock_live_input, mock_ctx
+):
+    """on_workflow_failure sets error status when transcript is processing."""
+    from reflector.hatchet.workflows.live_post_pipeline import on_workflow_failure
+
+    transcript_processing = MagicMock()
+    transcript_processing.status = "processing"
+
+    with patch(
+        "reflector.hatchet.workflows.live_post_pipeline.fresh_db_connection",
+        _noop_db_context,
+    ):
+        with patch(
+            "reflector.db.transcripts.transcripts_controller.get_by_id",
+            new_callable=AsyncMock,
+            return_value=transcript_processing,
+        ):
+            with patch(
+                "reflector.hatchet.workflows.live_post_pipeline.set_workflow_error_status",
+                new_callable=AsyncMock,
+            ) as mock_set_error:
+                await on_workflow_failure(mock_live_input, mock_ctx)
+                mock_set_error.assert_called_once_with(mock_live_input.transcript_id)
+
+
+@pytest.mark.asyncio
+async def test_live_pipeline_on_failure_does_not_overwrite_ended(
+    live_pipeline_module, mock_live_input, mock_ctx
+):
+    """on_workflow_failure must NOT overwrite 'ended' status."""
+    from reflector.hatchet.workflows.live_post_pipeline import on_workflow_failure
+
+    transcript_ended = MagicMock()
+    transcript_ended.status = "ended"
+
+    with patch(
+        "reflector.hatchet.workflows.live_post_pipeline.fresh_db_connection",
+        _noop_db_context,
+    ):
+        with patch(
+            "reflector.db.transcripts.transcripts_controller.get_by_id",
+            new_callable=AsyncMock,
+            return_value=transcript_ended,
+        ):
+            with patch(
+                "reflector.hatchet.workflows.live_post_pipeline.set_workflow_error_status",
+                new_callable=AsyncMock,
+            ) as mock_set_error:
+                await on_workflow_failure(mock_live_input, mock_ctx)
+                mock_set_error.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_pipeline_post_triggers_hatchet():
+    """pipeline_post() should trigger Hatchet LivePostProcessingPipeline workflow."""
+    with patch(
+        "reflector.hatchet.client.HatchetClientManager.start_workflow",
+        new_callable=AsyncMock,
+        return_value="workflow-run-id",
+    ) as mock_start:
+        from reflector.pipelines.main_live_pipeline import pipeline_post
+
+        await pipeline_post(transcript_id="ts-test-123", room_id="room-test")
+
+        mock_start.assert_called_once_with(
+            "LivePostProcessingPipeline",
+            {
+                "transcript_id": "ts-test-123",
+                "room_id": "room-test",
+            },
+            additional_metadata={"transcript_id": "ts-test-123"},
+        )
+
+
+@pytest.mark.asyncio
+async def test_pipeline_post_triggers_hatchet_without_room_id():
+    """pipeline_post() should handle None room_id."""
+    with patch(
+        "reflector.hatchet.client.HatchetClientManager.start_workflow",
+        new_callable=AsyncMock,
+        return_value="workflow-run-id",
+    ) as mock_start:
+        from reflector.pipelines.main_live_pipeline import pipeline_post
+
+        await pipeline_post(transcript_id="ts-test-456")
+
+        mock_start.assert_called_once_with(
+            "LivePostProcessingPipeline",
+            {
+                "transcript_id": "ts-test-456",
+                "room_id": None,
+            },
+            additional_metadata={"transcript_id": "ts-test-456"},
+        )

server/tests/test_hatchet_trigger_migration.py

@@ -0,0 +1,90 @@
+"""
+Tests verifying Celery-to-Hatchet trigger migration.
+
+Ensures that:
+1. process_recording triggers FilePipeline via Hatchet (not Celery)
+2. transcript_record_upload triggers FilePipeline via Hatchet (not Celery)
+3. Old Celery task references are no longer in active call sites
+"""
+
+
+def test_process_recording_does_not_import_celery_file_task():
+    """Verify process.py no longer imports task_pipeline_file_process."""
+    import inspect
+
+    from reflector.worker import process
+
+    source = inspect.getsource(process)
+    # Should not contain the old Celery task import
+    assert "task_pipeline_file_process" not in source
+
+
+def test_transcripts_upload_does_not_import_celery_file_task():
+    """Verify transcripts_upload.py no longer imports task_pipeline_file_process."""
+    import inspect
+
+    from reflector.views import transcripts_upload
+
+    source = inspect.getsource(transcripts_upload)
+    # Should not contain the old Celery task import
+    assert "task_pipeline_file_process" not in source
+
+
+def test_transcripts_upload_imports_hatchet():
+    """Verify transcripts_upload.py imports HatchetClientManager."""
+    import inspect
+
+    from reflector.views import transcripts_upload
+
+    source = inspect.getsource(transcripts_upload)
+    assert "HatchetClientManager" in source
+
+
+def test_pipeline_post_is_async():
+    """Verify pipeline_post is now async (Hatchet trigger)."""
+    import asyncio
+
+    from reflector.pipelines.main_live_pipeline import pipeline_post
+
+    assert asyncio.iscoroutinefunction(pipeline_post)
+
+
+def test_transcript_process_service_does_not_import_celery_file_task():
+    """Verify transcript_process.py service no longer imports task_pipeline_file_process."""
+    import inspect
+
+    from reflector.services import transcript_process
+
+    source = inspect.getsource(transcript_process)
+    assert "task_pipeline_file_process" not in source
+
+
+def test_transcript_process_service_dispatch_uses_hatchet():
+    """Verify dispatch_transcript_processing uses HatchetClientManager for file processing."""
+    import inspect
+
+    from reflector.services import transcript_process
+
+    source = inspect.getsource(transcript_process.dispatch_transcript_processing)
+    assert "HatchetClientManager" in source
+    assert "FilePipeline" in source
+
+
+def test_new_task_names_exist():
+    """Verify new TaskName constants were added for file and live pipelines."""
+    from reflector.hatchet.constants import TaskName
+
+    # File pipeline tasks
+    assert TaskName.EXTRACT_AUDIO == "extract_audio"
+    assert TaskName.UPLOAD_AUDIO == "upload_audio"
+    assert TaskName.TRANSCRIBE == "transcribe"
+    assert TaskName.DIARIZE == "diarize"
+    assert TaskName.ASSEMBLE_TRANSCRIPT == "assemble_transcript"
+    assert TaskName.GENERATE_SUMMARIES == "generate_summaries"
+
+    # Live post-processing pipeline tasks
+    assert TaskName.WAVEFORM == "waveform"
+    assert TaskName.CONVERT_MP3 == "convert_mp3"
+    assert TaskName.UPLOAD_MP3 == "upload_mp3"
+    assert TaskName.REMOVE_UPLOAD == "remove_upload"
+    assert TaskName.FINAL_SUMMARIES == "final_summaries"

server/tests/test_transcripts_process.py

@@ -1,5 +1,3 @@
-import asyncio
-import time
 from unittest.mock import AsyncMock, patch
 
 import pytest
@@ -27,8 +25,6 @@ async def client(app_lifespan):
 
 
 @pytest.mark.usefixtures("setup_database")
-@pytest.mark.usefixtures("celery_session_app")
-@pytest.mark.usefixtures("celery_session_worker")
 @pytest.mark.asyncio
 async def test_transcript_process(
     tmpdir,
@@ -39,8 +35,13 @@ async def test_transcript_process(
     dummy_storage,
     client,
     monkeypatch,
+    mock_hatchet_client,
 ):
-    # public mode: this test uses an anonymous client; allow anonymous transcript creation
+    """Test upload + process dispatch via Hatchet.
+
+    The file pipeline is now dispatched to Hatchet (fire-and-forget),
+    so we verify the workflow was triggered rather than polling for completion.
+    """
     monkeypatch.setattr(settings, "PUBLIC_MODE", True)
 
     # create a transcript
@@ -63,51 +64,43 @@ async def test_transcript_process(
     assert response.status_code == 200
     assert response.json()["status"] == "ok"
 
-    # wait for processing to finish (max 1 minute)
-    timeout_seconds = 60
-    start_time = time.monotonic()
-    while (time.monotonic() - start_time) < timeout_seconds:
-        # fetch the transcript and check if it is ended
-        resp = await client.get(f"/transcripts/{tid}")
-        assert resp.status_code == 200
-        if resp.json()["status"] in ("ended", "error"):
-            break
-        await asyncio.sleep(1)
-    else:
-        pytest.fail(f"Initial processing timed out after {timeout_seconds} seconds")
+    # Verify Hatchet workflow was dispatched (from upload endpoint)
+    from reflector.hatchet.client import HatchetClientManager
 
-    # restart the processing
-    response = await client.post(
-        f"/transcripts/{tid}/process",
+    HatchetClientManager.start_workflow.assert_called_once_with(
+        "FilePipeline",
+        {"transcript_id": tid},
+        additional_metadata={"transcript_id": tid},
     )
-    assert response.status_code == 200
-    assert response.json()["status"] == "ok"
-    await asyncio.sleep(2)
 
-    # wait for processing to finish (max 1 minute)
-    timeout_seconds = 60
-    start_time = time.monotonic()
-    while (time.monotonic() - start_time) < timeout_seconds:
-        # fetch the transcript and check if it is ended
-        resp = await client.get(f"/transcripts/{tid}")
-        assert resp.status_code == 200
-        if resp.json()["status"] in ("ended", "error"):
-            break
-        await asyncio.sleep(1)
-    else:
-        pytest.fail(f"Restart processing timed out after {timeout_seconds} seconds")
+    # Verify transcript status was set to "uploaded"
+    resp = await client.get(f"/transcripts/{tid}")
+    assert resp.status_code == 200
+    assert resp.json()["status"] == "uploaded"
 
-    # check the transcript is ended
-    transcript = resp.json()
-    assert transcript["status"] == "ended"
-    assert transcript["short_summary"] == "LLM SHORT SUMMARY"
-    assert transcript["title"] == "Llm Title"
+    # Reset mock for reprocess test
+    HatchetClientManager.start_workflow.reset_mock()
 
-    # check topics and transcript
-    response = await client.get(f"/transcripts/{tid}/topics")
-    assert response.status_code == 200
-    assert len(response.json()) == 1
-    assert "Hello world. How are you today?" in response.json()[0]["transcript"]
+    # Clear workflow_run_id so /process endpoint can dispatch again
+    from reflector.db.transcripts import transcripts_controller
+
+    transcript = await transcripts_controller.get_by_id(tid)
+    await transcripts_controller.update(transcript, {"workflow_run_id": None})
+
+    # Reprocess via /process endpoint
+    with patch(
+        "reflector.services.transcript_process.task_is_scheduled_or_active",
+        return_value=False,
+    ):
+        response = await client.post(f"/transcripts/{tid}/process")
+        assert response.status_code == 200
+        assert response.json()["status"] == "ok"
+
+    # Verify second Hatchet dispatch (from /process endpoint)
+    HatchetClientManager.start_workflow.assert_called_once()
+    call_kwargs = HatchetClientManager.start_workflow.call_args.kwargs
+    assert call_kwargs["workflow_name"] == "FilePipeline"
+    assert call_kwargs["input_data"]["transcript_id"] == tid
 
 
 @pytest.mark.usefixtures("setup_database")
@@ -150,20 +143,25 @@ async def test_whereby_recording_uses_file_pipeline(monkeypatch, client):
 
     with (
         patch(
-            "reflector.services.transcript_process.task_pipeline_file_process"
-        ) as mock_file_pipeline,
+            "reflector.services.transcript_process.task_is_scheduled_or_active",
+            return_value=False,
+        ),
         patch(
             "reflector.services.transcript_process.HatchetClientManager"
         ) as mock_hatchet,
     ):
+        mock_hatchet.start_workflow = AsyncMock(return_value="test-workflow-id")
+
         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, not Hatchet
-        mock_file_pipeline.delay.assert_called_once_with(transcript_id=transcript.id)
-        mock_hatchet.start_workflow.assert_not_called()
+        # Whereby recordings should use Hatchet FilePipeline
+        mock_hatchet.start_workflow.assert_called_once()
+        call_kwargs = mock_hatchet.start_workflow.call_args.kwargs
+        assert call_kwargs["workflow_name"] == "FilePipeline"
+        assert call_kwargs["input_data"]["transcript_id"] == transcript.id
 
 
 @pytest.mark.usefixtures("setup_database")
@@ -224,8 +222,9 @@ async def test_dailyco_recording_uses_multitrack_pipeline(monkeypatch, client):
 
     with (
         patch(
-            "reflector.services.transcript_process.task_pipeline_file_process"
-        ) as mock_file_pipeline,
+            "reflector.services.transcript_process.task_is_scheduled_or_active",
+            return_value=False,
+        ),
         patch(
             "reflector.services.transcript_process.HatchetClientManager"
         ) as mock_hatchet,
@@ -237,7 +236,7 @@ async def test_dailyco_recording_uses_multitrack_pipeline(monkeypatch, client):
         assert response.status_code == 200
         assert response.json()["status"] == "ok"
 
-        # Daily.co multitrack recordings should use Hatchet workflow
+        # Daily.co multitrack recordings should use Hatchet DiarizationPipeline
         mock_hatchet.start_workflow.assert_called_once()
         call_kwargs = mock_hatchet.start_workflow.call_args.kwargs
         assert call_kwargs["workflow_name"] == "DiarizationPipeline"
@@ -246,7 +245,6 @@ async def test_dailyco_recording_uses_multitrack_pipeline(monkeypatch, client):
         assert call_kwargs["input_data"]["tracks"] == [
             {"s3_key": k} for k in track_keys
         ]
-        mock_file_pipeline.delay.assert_not_called()
 
 
 @pytest.mark.usefixtures("setup_database")

server/tests/test_transcripts_rtc_ws.py

@@ -2,6 +2,10 @@
 # FIXME test status of transcript
 # FIXME test websocket connection after RTC is finished still send the full events
 # FIXME try with locked session, RTC should not work
+# TODO: add integration tests for post-processing (LivePostPipeline) with a real
+#       Hatchet instance. These tests currently only cover the live pipeline.
+#       Post-processing events (WAVEFORM, FINAL_*, DURATION, STATUS=ended, mp3)
+#       are now dispatched via Hatchet and tested in test_hatchet_live_post_pipeline.py.
 
 import asyncio
 import json
@@ -49,7 +53,7 @@ class ThreadedUvicorn:
 
 
 @pytest.fixture
-def appserver(tmpdir, setup_database, celery_session_app, celery_session_worker):
+def appserver(tmpdir, setup_database):
     import threading
 
     from reflector.app import app
@@ -119,8 +123,6 @@ def appserver(tmpdir, setup_database, celery_session_app, celery_session_worker)
 
 
 @pytest.mark.usefixtures("setup_database")
-@pytest.mark.usefixtures("celery_session_app")
-@pytest.mark.usefixtures("celery_session_worker")
 @pytest.mark.asyncio
 async def test_transcript_rtc_and_websocket(
     tmpdir,
@@ -134,6 +136,7 @@ async def test_transcript_rtc_and_websocket(
     appserver,
     client,
     monkeypatch,
+    mock_hatchet_client,
 ):
     # goal: start the server, exchange RTC, receive websocket events
     # because of that, we need to start the server in a thread
@@ -208,35 +211,30 @@ async def test_transcript_rtc_and_websocket(
     stream_client.channel.send(json.dumps({"cmd": "STOP"}))
     await stream_client.stop()
 
-    # wait the processing to finish
-    timeout = 120
+    # Wait for live pipeline to flush (it dispatches post-processing to Hatchet)
+    timeout = 30
     while True:
-        # fetch the transcript and check if it is ended
         resp = await client.get(f"/transcripts/{tid}")
         assert resp.status_code == 200
-        if resp.json()["status"] in ("ended", "error"):
+        if resp.json()["status"] in ("processing", "ended", "error"):
             break
         await asyncio.sleep(1)
         timeout -= 1
         if timeout < 0:
-            raise TimeoutError("Timeout while waiting for transcript to be ended")
-
-    if resp.json()["status"] != "ended":
-        raise TimeoutError("Transcript processing failed")
+            raise TimeoutError("Timeout waiting for live pipeline to finish")
 
     # stop websocket task
     websocket_task.cancel()
 
-    # check events
+    # check live pipeline events
     assert len(events) > 0
     from pprint import pprint
 
     pprint(events)
 
-    # get events list
     eventnames = [e["event"] for e in events]
 
-    # check events
+    # Live pipeline produces TRANSCRIPT and TOPIC events during RTC
     assert "TRANSCRIPT" in eventnames
     ev = events[eventnames.index("TRANSCRIPT")]
     assert ev["data"]["text"].startswith("Hello world.")
@@ -249,50 +247,18 @@ async def test_transcript_rtc_and_websocket(
     assert ev["data"]["transcript"].startswith("Hello world.")
     assert ev["data"]["timestamp"] == 0.0
 
-    assert "FINAL_LONG_SUMMARY" in eventnames
-    ev = events[eventnames.index("FINAL_LONG_SUMMARY")]
-    assert ev["data"]["long_summary"] == "LLM LONG SUMMARY"
-
-    assert "FINAL_SHORT_SUMMARY" in eventnames
-    ev = events[eventnames.index("FINAL_SHORT_SUMMARY")]
-    assert ev["data"]["short_summary"] == "LLM SHORT SUMMARY"
-
-    assert "FINAL_TITLE" in eventnames
-    ev = events[eventnames.index("FINAL_TITLE")]
-    assert ev["data"]["title"] == "Llm Title"
-
-    assert "WAVEFORM" in eventnames
-    ev = events[eventnames.index("WAVEFORM")]
-    assert isinstance(ev["data"]["waveform"], list)
-    assert len(ev["data"]["waveform"]) >= 250
-    waveform_resp = await client.get(f"/transcripts/{tid}/audio/waveform")
-    assert waveform_resp.status_code == 200
-    assert waveform_resp.headers["content-type"] == "application/json"
-    assert isinstance(waveform_resp.json()["data"], list)
-    assert len(waveform_resp.json()["data"]) >= 250
-
-    # check status order
+    # Live pipeline status progression
     statuses = [e["data"]["value"] for e in events if e["event"] == "STATUS"]
+    assert "recording" in statuses
+    assert "processing" in statuses
     assert statuses.index("recording") < statuses.index("processing")
-    assert statuses.index("processing") < statuses.index("ended")
 
-    # ensure the last event received is ended
-    assert events[-1]["event"] == "STATUS"
-    assert events[-1]["data"]["value"] == "ended"
-
-    # check on the latest response that the audio duration is > 0
-    assert resp.json()["duration"] > 0
-    assert "DURATION" in eventnames
-
-    # check that audio/mp3 is available
-    audio_resp = await client.get(f"/transcripts/{tid}/audio/mp3")
-    assert audio_resp.status_code == 200
-    assert audio_resp.headers["Content-Type"] == "audio/mpeg"
+    # Post-processing (WAVEFORM, FINAL_*, DURATION, mp3, STATUS=ended) is now
+    # dispatched to Hatchet via LivePostPipeline — not tested here.
+    # See test_hatchet_live_post_pipeline.py for post-processing tests.
 
 
 @pytest.mark.usefixtures("setup_database")
-@pytest.mark.usefixtures("celery_session_app")
-@pytest.mark.usefixtures("celery_session_worker")
 @pytest.mark.asyncio
 async def test_transcript_rtc_and_websocket_and_fr(
     tmpdir,
@@ -306,6 +272,7 @@ async def test_transcript_rtc_and_websocket_and_fr(
     appserver,
     client,
     monkeypatch,
+    mock_hatchet_client,
 ):
     # goal: start the server, exchange RTC, receive websocket events
     # because of that, we need to start the server in a thread
@@ -382,42 +349,34 @@ async def test_transcript_rtc_and_websocket_and_fr(
     # instead of waiting a long time, we just send a STOP
     stream_client.channel.send(json.dumps({"cmd": "STOP"}))
 
-    # wait the processing to finish
     await asyncio.sleep(2)
 
     await stream_client.stop()
 
-    # wait the processing to finish
-    timeout = 120
+    # Wait for live pipeline to flush
+    timeout = 30
     while True:
-        # fetch the transcript and check if it is ended
         resp = await client.get(f"/transcripts/{tid}")
         assert resp.status_code == 200
-        if resp.json()["status"] == "ended":
+        if resp.json()["status"] in ("processing", "ended", "error"):
             break
         await asyncio.sleep(1)
         timeout -= 1
         if timeout < 0:
-            raise TimeoutError("Timeout while waiting for transcript to be ended")
-
-    if resp.json()["status"] != "ended":
-        raise TimeoutError("Transcript processing failed")
-
-    await asyncio.sleep(2)
+            raise TimeoutError("Timeout waiting for live pipeline to finish")
 
     # stop websocket task
     websocket_task.cancel()
 
-    # check events
+    # check live pipeline events
     assert len(events) > 0
     from pprint import pprint
 
     pprint(events)
 
-    # get events list
     eventnames = [e["event"] for e in events]
 
-    # check events
+    # Live pipeline produces TRANSCRIPT with translation
     assert "TRANSCRIPT" in eventnames
     ev = events[eventnames.index("TRANSCRIPT")]
     assert ev["data"]["text"].startswith("Hello world.")
@@ -430,23 +389,11 @@ async def test_transcript_rtc_and_websocket_and_fr(
     assert ev["data"]["transcript"].startswith("Hello world.")
     assert ev["data"]["timestamp"] == 0.0
 
-    assert "FINAL_LONG_SUMMARY" in eventnames
-    ev = events[eventnames.index("FINAL_LONG_SUMMARY")]
-    assert ev["data"]["long_summary"] == "LLM LONG SUMMARY"
-
-    assert "FINAL_SHORT_SUMMARY" in eventnames
-    ev = events[eventnames.index("FINAL_SHORT_SUMMARY")]
-    assert ev["data"]["short_summary"] == "LLM SHORT SUMMARY"
-
-    assert "FINAL_TITLE" in eventnames
-    ev = events[eventnames.index("FINAL_TITLE")]
-    assert ev["data"]["title"] == "Llm Title"
-
-    # check status order
+    # Live pipeline status progression
     statuses = [e["data"]["value"] for e in events if e["event"] == "STATUS"]
+    assert "recording" in statuses
+    assert "processing" in statuses
     assert statuses.index("recording") < statuses.index("processing")
-    assert statuses.index("processing") < statuses.index("ended")
 
-    # ensure the last event received is ended
-    assert events[-1]["event"] == "STATUS"
-    assert events[-1]["data"]["value"] == "ended"
+    # Post-processing (FINAL_*, STATUS=ended) is now dispatched to Hatchet
+    # via LivePostPipeline — not tested here.

server/tests/test_transcripts_upload.py

@@ -1,12 +1,7 @@
-import asyncio
-import time
-
 import pytest
 
 
 @pytest.mark.usefixtures("setup_database")
-@pytest.mark.usefixtures("celery_session_app")
-@pytest.mark.usefixtures("celery_session_worker")
 @pytest.mark.asyncio
 async def test_transcript_upload_file(
     tmpdir,
@@ -17,6 +12,7 @@ async def test_transcript_upload_file(
     dummy_storage,
     client,
     monkeypatch,
+    mock_hatchet_client,
 ):
     from reflector.settings import settings
 
@@ -43,27 +39,16 @@ async def test_transcript_upload_file(
     assert response.status_code == 200
     assert response.json()["status"] == "ok"
 
-    # wait the processing to finish (max 1 minute)
-    timeout_seconds = 60
-    start_time = time.monotonic()
-    while (time.monotonic() - start_time) < timeout_seconds:
-        # fetch the transcript and check if it is ended
-        resp = await client.get(f"/transcripts/{tid}")
-        assert resp.status_code == 200
-        if resp.json()["status"] in ("ended", "error"):
-            break
-        await asyncio.sleep(1)
-    else:
-        return pytest.fail(f"Processing timed out after {timeout_seconds} seconds")
+    # Verify Hatchet workflow was dispatched for file processing
+    from reflector.hatchet.client import HatchetClientManager
 
-    # check the transcript is ended
-    transcript = resp.json()
-    assert transcript["status"] == "ended"
-    assert transcript["short_summary"] == "LLM SHORT SUMMARY"
-    assert transcript["title"] == "Llm Title"
+    HatchetClientManager.start_workflow.assert_called_once_with(
+        "FilePipeline",
+        {"transcript_id": tid},
+        additional_metadata={"transcript_id": tid},
+    )
 
-    # check topics and transcript
-    response = await client.get(f"/transcripts/{tid}/topics")
-    assert response.status_code == 200
-    assert len(response.json()) == 1
-    assert "Hello world. How are you today?" in response.json()[0]["transcript"]
+    # Verify transcript status was updated to "uploaded"
+    resp = await client.get(f"/transcripts/{tid}")
+    assert resp.status_code == 200
+    assert resp.json()["status"] == "uploaded"

server/uv.lock

@@ -404,7 +404,7 @@ wheels = [
 
 [[package]]
 name = "black"
-version = "24.3.0"
+version = "26.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
@@ -412,18 +412,21 @@ dependencies = [
     { name = "packaging" },
     { name = "pathspec" },
     { name = "platformdirs" },
+    { name = "pytokens" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8f/5f/bac24a952668c7482cfdb4ebf91ba57a796c9da8829363a772040c1a3312/black-24.3.0.tar.gz", hash = "sha256:a0c9c4a0771afc6919578cec71ce82a3e31e054904e7197deacbc9382671c41f", size = 634292, upload-time = "2024-03-15T19:35:43.699Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e1/c5/61175d618685d42b005847464b8fb4743a67b1b8fdb75e50e5a96c31a27a/black-26.3.1.tar.gz", hash = "sha256:2c50f5063a9641c7eed7795014ba37b0f5fa227f3d408b968936e24bc0566b07", size = 666155, upload-time = "2026-03-12T03:36:03.593Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/68/df/ceea5828be9c4931cb5a75b7e8fb02971f57524da7a16dfec0d4d575327f/black-24.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4f1373a7808a8f135b774039f61d59e4be7eb56b2513d3d2f02a8b9365b8a8a9", size = 1571235, upload-time = "2024-03-15T19:45:27.77Z" },
-    { url = "https://files.pythonhosted.org/packages/46/5f/30398c5056cb72f883b32b6520ad00042a9d0454b693f70509867db03a80/black-24.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:aadf7a02d947936ee418777e0247ea114f78aff0d0959461057cae8a04f20597", size = 1414926, upload-time = "2024-03-15T19:43:52.993Z" },
-    { url = "https://files.pythonhosted.org/packages/6b/59/498885b279e890f656ea4300a2671c964acb6d97994ea626479c2e5501b4/black-24.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:65c02e4ea2ae09d16314d30912a58ada9a5c4fdfedf9512d23326128ac08ac3d", size = 1725920, upload-time = "2024-03-15T19:38:13.052Z" },
-    { url = "https://files.pythonhosted.org/packages/8f/b0/4bef40c808cc615187db983b75bacdca1c110a229d41ba9887549fac529c/black-24.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:bf21b7b230718a5f08bd32d5e4f1db7fc8788345c8aea1d155fc17852b3410f5", size = 1372608, upload-time = "2024-03-15T19:39:34.973Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/c6/1d174efa9ff02b22d0124c73fc5f4d4fb006d0d9a081aadc354d05754a13/black-24.3.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:2818cf72dfd5d289e48f37ccfa08b460bf469e67fb7c4abb07edc2e9f16fb63f", size = 1600822, upload-time = "2024-03-15T19:45:20.337Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/ed/704731afffe460b8ff0672623b40fce9fe569f2ee617c15857e4d4440a3a/black-24.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4acf672def7eb1725f41f38bf6bf425c8237248bb0804faa3965c036f7672d11", size = 1429987, upload-time = "2024-03-15T19:45:00.637Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/05/8dd038e30caadab7120176d4bc109b7ca2f4457f12eef746b0560a583458/black-24.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c7ed6668cbbfcd231fa0dc1b137d3e40c04c7f786e626b405c62bcd5db5857e4", size = 1755319, upload-time = "2024-03-15T19:38:24.009Z" },
-    { url = "https://files.pythonhosted.org/packages/71/9d/e5fa1ff4ef1940be15a64883c0bb8d2fcf626efec996eab4ae5a8c691d2c/black-24.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:56f52cfbd3dabe2798d76dbdd299faa046a901041faf2cf33288bc4e6dae57b5", size = 1385180, upload-time = "2024-03-15T19:39:37.014Z" },
-    { url = "https://files.pythonhosted.org/packages/4d/ea/31770a7e49f3eedfd8cd7b35e78b3a3aaad860400f8673994bc988318135/black-24.3.0-py3-none-any.whl", hash = "sha256:41622020d7120e01d377f74249e677039d20e6344ff5851de8a10f11f513bf93", size = 201493, upload-time = "2024-03-15T19:35:41.572Z" },
+    { url = "https://files.pythonhosted.org/packages/17/57/5f11c92861f9c92eb9dddf515530bc2d06db843e44bdcf1c83c1427824bc/black-26.3.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:28ef38aee69e4b12fda8dba75e21f9b4f979b490c8ac0baa7cb505369ac9e1ff", size = 1851987, upload-time = "2026-03-12T03:40:06.248Z" },
+    { url = "https://files.pythonhosted.org/packages/54/aa/340a1463660bf6831f9e39646bf774086dbd8ca7fc3cded9d59bbdf4ad0a/black-26.3.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bf9bf162ed91a26f1adba8efda0b573bc6924ec1408a52cc6f82cb73ec2b142c", size = 1689499, upload-time = "2026-03-12T03:40:07.642Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/01/b726c93d717d72733da031d2de10b92c9fa4c8d0c67e8a8a372076579279/black-26.3.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:474c27574d6d7037c1bc875a81d9be0a9a4f9ee95e62800dab3cfaadbf75acd5", size = 1754369, upload-time = "2026-03-12T03:40:09.279Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/09/61e91881ca291f150cfc9eb7ba19473c2e59df28859a11a88248b5cbbc4d/black-26.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:5e9d0d86df21f2e1677cc4bd090cd0e446278bcbbe49bf3659c308c3e402843e", size = 1413613, upload-time = "2026-03-12T03:40:10.943Z" },
+    { url = "https://files.pythonhosted.org/packages/16/73/544f23891b22e7efe4d8f812371ab85b57f6a01b2fc45e3ba2e52ba985b8/black-26.3.1-cp311-cp311-win_arm64.whl", hash = "sha256:9a5e9f45e5d5e1c5b5c29b3bd4265dcc90e8b92cf4534520896ed77f791f4da5", size = 1219719, upload-time = "2026-03-12T03:40:12.597Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/f8/da5eae4fc75e78e6dceb60624e1b9662ab00d6b452996046dfa9b8a6025b/black-26.3.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b5e6f89631eb88a7302d416594a32faeee9fb8fb848290da9d0a5f2903519fc1", size = 1895920, upload-time = "2026-03-12T03:40:13.921Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/9f/04e6f26534da2e1629b2b48255c264cabf5eedc5141d04516d9d68a24111/black-26.3.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:41cd2012d35b47d589cb8a16faf8a32ef7a336f56356babd9fcf70939ad1897f", size = 1718499, upload-time = "2026-03-12T03:40:15.239Z" },
+    { url = "https://files.pythonhosted.org/packages/04/91/a5935b2a63e31b331060c4a9fdb5a6c725840858c599032a6f3aac94055f/black-26.3.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0f76ff19ec5297dd8e66eb64deda23631e642c9393ab592826fd4bdc97a4bce7", size = 1794994, upload-time = "2026-03-12T03:40:17.124Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/0a/86e462cdd311a3c2a8ece708d22aba17d0b2a0d5348ca34b40cdcbea512e/black-26.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:ddb113db38838eb9f043623ba274cfaf7d51d5b0c22ecb30afe58b1bb8322983", size = 1420867, upload-time = "2026-03-12T03:40:18.83Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/e5/22515a19cb7eaee3440325a6b0d95d2c0e88dd180cb011b12ae488e031d1/black-26.3.1-cp312-cp312-win_arm64.whl", hash = "sha256:dfdd51fc3e64ea4f35873d1b3fb25326773d55d2329ff8449139ebaad7357efb", size = 1230124, upload-time = "2026-03-12T03:40:20.425Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/0d/52d98722666d6fc6c3dd4c76df339501d6efd40e0ff95e6186a7b7f0befd/black-26.3.1-py3-none-any.whl", hash = "sha256:2bd5aa94fc267d38bb21a70d7410a89f1a1d318841855f698746f8e7f51acd1b", size = 207542, upload-time = "2026-03-12T03:36:01.668Z" },
 ]
 
 [[package]]
@@ -2433,11 +2436,11 @@ wheels = [
 
 [[package]]
 name = "pathspec"
-version = "0.12.1"
+version = "1.0.4"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/ca/bc/f35b8446f4531a7cb215605d100cd88b7ac6f44ab3fc94870c120ab3adbf/pathspec-0.12.1.tar.gz", hash = "sha256:a482d51503a1ab33b1c67a6c3813a26953dbdc71c31dacaef9a838c4e29f5712", size = 51043, upload-time = "2023-12-10T22:30:45Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fa/36/e27608899f9b8d4dff0617b2d9ab17ca5608956ca44461ac14ac48b44015/pathspec-1.0.4.tar.gz", hash = "sha256:0210e2ae8a21a9137c0d470578cb0e595af87edaa6ebf12ff176f14a02e0e645", size = 131200, upload-time = "2026-01-27T03:59:46.938Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191, upload-time = "2023-12-10T22:30:43.14Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/3c/2c197d226f9ea224a9ab8d197933f9da0ae0aac5b6e0f884e2b8d9c8e9f7/pathspec-1.0.4-py3-none-any.whl", hash = "sha256:fb6ae2fd4e7c921a165808a552060e722767cfa526f99ca5156ed2ce45a5c723", size = 55206, upload-time = "2026-01-27T03:59:45.137Z" },
 ]
 
 [[package]]
@@ -2915,11 +2918,11 @@ wheels = [
 
 [[package]]
 name = "pyjwt"
-version = "2.11.0"
+version = "2.12.1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/5c/5a/b46fa56bf322901eee5b0454a34343cdbdae202cd421775a8ee4e42fd519/pyjwt-2.11.0.tar.gz", hash = "sha256:35f95c1f0fbe5d5ba6e43f00271c275f7a1a4db1dab27bf708073b75318ea623", size = 98019, upload-time = "2026-01-30T19:59:55.694Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c2/27/a3b6e5bf6ff856d2509292e95c8f57f0df7017cf5394921fc4e4ef40308a/pyjwt-2.12.1.tar.gz", hash = "sha256:c74a7a2adf861c04d002db713dd85f84beb242228e671280bf709d765b03672b", size = 102564, upload-time = "2026-03-13T19:27:37.25Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/6f/01/c26ce75ba460d5cd503da9e13b21a33804d38c2165dec7b716d06b13010c/pyjwt-2.11.0-py3-none-any.whl", hash = "sha256:94a6bde30eb5c8e04fee991062b534071fd1439ef58d2adc9ccb823e7bcd0469", size = 28224, upload-time = "2026-01-30T19:59:54.539Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/7a/8dd906bd22e79e47397a61742927f6747fe93242ef86645ee9092e610244/pyjwt-2.12.1-py3-none-any.whl", hash = "sha256:28ca37c070cad8ba8cd9790cd940535d40274d22f80ab87f3ac6a713e6e8454c", size = 29726, upload-time = "2026-03-13T19:27:35.677Z" },
 ]
 
 [package.optional-dependencies]
@@ -2951,15 +2954,15 @@ wheels = [
 
 [[package]]
 name = "pyopenssl"
-version = "25.3.0"
+version = "26.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "cryptography" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/80/be/97b83a464498a79103036bc74d1038df4a7ef0e402cfaf4d5e113fb14759/pyopenssl-25.3.0.tar.gz", hash = "sha256:c981cb0a3fd84e8602d7afc209522773b94c1c2446a3c710a75b06fe1beae329", size = 184073, upload-time = "2025-09-17T00:32:21.037Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/8e/11/a62e1d33b373da2b2c2cd9eb508147871c80f12b1cacde3c5d314922afdd/pyopenssl-26.0.0.tar.gz", hash = "sha256:f293934e52936f2e3413b89c6ce36df66a0b34ae1ea3a053b8c5020ff2f513fc", size = 185534, upload-time = "2026-03-15T14:28:26.353Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d1/81/ef2b1dfd1862567d573a4fdbc9f969067621764fbb74338496840a1d2977/pyopenssl-25.3.0-py3-none-any.whl", hash = "sha256:1fda6fc034d5e3d179d39e59c1895c9faeaf40a79de5fc4cbbfbe0d36f4a77b6", size = 57268, upload-time = "2025-09-17T00:32:19.474Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/7d/d4f7d908fa8415571771b30669251d57c3cf313b36a856e6d7548ae01619/pyopenssl-26.0.0-py3-none-any.whl", hash = "sha256:df94d28498848b98cc1c0ffb8ef1e71e40210d3b0a8064c9d29571ed2904bf81", size = 57969, upload-time = "2026-03-15T14:28:24.864Z" },
 ]
 
 [[package]]
@@ -3159,6 +3162,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/1b/d0/397f9626e711ff749a95d96b7af99b9c566a9bb5129b8e4c10fc4d100304/python_multipart-0.0.22-py3-none-any.whl", hash = "sha256:2b2cd894c83d21bf49d702499531c7bafd057d730c201782048f7945d82de155", size = 24579, upload-time = "2026-01-25T10:15:54.811Z" },
 ]
 
+[[package]]
+name = "pytokens"
+version = "0.4.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b6/34/b4e015b99031667a7b960f888889c5bd34ef585c85e1cb56a594b92836ac/pytokens-0.4.1.tar.gz", hash = "sha256:292052fe80923aae2260c073f822ceba21f3872ced9a68bb7953b348e561179a", size = 23015, upload-time = "2026-01-30T01:03:45.924Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3d/92/790ebe03f07b57e53b10884c329b9a1a308648fc083a6d4a39a10a28c8fc/pytokens-0.4.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d70e77c55ae8380c91c0c18dea05951482e263982911fc7410b1ffd1dadd3440", size = 160864, upload-time = "2026-01-30T01:02:57.882Z" },
+    { url = "https://files.pythonhosted.org/packages/13/25/a4f555281d975bfdd1eba731450e2fe3a95870274da73fb12c40aeae7625/pytokens-0.4.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4a58d057208cb9075c144950d789511220b07636dd2e4708d5645d24de666bdc", size = 248565, upload-time = "2026-01-30T01:02:59.912Z" },
+    { url = "https://files.pythonhosted.org/packages/17/50/bc0394b4ad5b1601be22fa43652173d47e4c9efbf0044c62e9a59b747c56/pytokens-0.4.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b49750419d300e2b5a3813cf229d4e5a4c728dae470bcc89867a9ad6f25a722d", size = 260824, upload-time = "2026-01-30T01:03:01.471Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/54/3e04f9d92a4be4fc6c80016bc396b923d2a6933ae94b5f557c939c460ee0/pytokens-0.4.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:d9907d61f15bf7261d7e775bd5d7ee4d2930e04424bab1972591918497623a16", size = 264075, upload-time = "2026-01-30T01:03:04.143Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/1b/44b0326cb5470a4375f37988aea5d61b5cc52407143303015ebee94abfd6/pytokens-0.4.1-cp311-cp311-win_amd64.whl", hash = "sha256:ee44d0f85b803321710f9239f335aafe16553b39106384cef8e6de40cb4ef2f6", size = 103323, upload-time = "2026-01-30T01:03:05.412Z" },
+    { url = "https://files.pythonhosted.org/packages/41/5d/e44573011401fb82e9d51e97f1290ceb377800fb4eed650b96f4753b499c/pytokens-0.4.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:140709331e846b728475786df8aeb27d24f48cbcf7bcd449f8de75cae7a45083", size = 160663, upload-time = "2026-01-30T01:03:06.473Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/e6/5bbc3019f8e6f21d09c41f8b8654536117e5e211a85d89212d59cbdab381/pytokens-0.4.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6d6c4268598f762bc8e91f5dbf2ab2f61f7b95bdc07953b602db879b3c8c18e1", size = 255626, upload-time = "2026-01-30T01:03:08.177Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/3c/2d5297d82286f6f3d92770289fd439956b201c0a4fc7e72efb9b2293758e/pytokens-0.4.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:24afde1f53d95348b5a0eb19488661147285ca4dd7ed752bbc3e1c6242a304d1", size = 269779, upload-time = "2026-01-30T01:03:09.756Z" },
+    { url = "https://files.pythonhosted.org/packages/20/01/7436e9ad693cebda0551203e0bf28f7669976c60ad07d6402098208476de/pytokens-0.4.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:5ad948d085ed6c16413eb5fec6b3e02fa00dc29a2534f088d3302c47eb59adf9", size = 268076, upload-time = "2026-01-30T01:03:10.957Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/df/533c82a3c752ba13ae7ef238b7f8cdd272cf1475f03c63ac6cf3fcfb00b6/pytokens-0.4.1-cp312-cp312-win_amd64.whl", hash = "sha256:3f901fe783e06e48e8cbdc82d631fca8f118333798193e026a50ce1b3757ea68", size = 103552, upload-time = "2026-01-30T01:03:12.066Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/78/397db326746f0a342855b81216ae1f0a32965deccfd7c830a2dbc66d2483/pytokens-0.4.1-py3-none-any.whl", hash = "sha256:26cef14744a8385f35d0e095dc8b3a7583f6c953c2e3d269c7f82484bf5ad2de", size = 13729, upload-time = "2026-01-30T01:03:45.029Z" },
+]
+
 [[package]]
 name = "pytorch-lightning"
 version = "2.5.6"
@@ -4268,10 +4290,10 @@ dependencies = [
     { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine == 'aarch64' and platform_python_implementation == 'CPython' and sys_platform == 'linux'" },
 ]
 wheels = [
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c9276857d241c6de257af765c0f51fc011af38cb725401495121b280913007cf" },
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:4573c6042950c20278e3608a9a38050ba0bc72e0049e1bbfd249caf859a8029b" },
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ddef94bf181e6447cbb05f38beaca8f6c5bb8d2b9ddced1aa3452025b9fc70d3" },
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:862e2e40bf09d865e5df080a84c1a39bbcef40e43140f4b1737eb3a389d3b38f" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c9276857d241c6de257af765c0f51fc011af38cb725401495121b280913007cf" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:4573c6042950c20278e3608a9a38050ba0bc72e0049e1bbfd249caf859a8029b" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ddef94bf181e6447cbb05f38beaca8f6c5bb8d2b9ddced1aa3452025b9fc70d3" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:862e2e40bf09d865e5df080a84c1a39bbcef40e43140f4b1737eb3a389d3b38f" },
 ]
 
 [[package]]
@@ -4294,10 +4316,10 @@ dependencies = [
     { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (platform_python_implementation == 'PyPy' and sys_platform == 'darwin') or (platform_python_implementation != 'CPython' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:e54bd7fc9472019308097d99102df9acee22aa2451ae808d27840bc874320292" },
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp311-cp311-win_amd64.whl", hash = "sha256:db37df7eee906f8fe0a639fdc673f3541cb2e173169b16d4133447eb922d1938" },
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:9377faee65a290578280ac7f4884c3586253dac2ca28c60f458ff6efe86a6b05" },
-    { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:9b302192b570657c1cc787a4d487ae4bbb7f2aab1c01b1fcc46757e7f86f391e" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:e54bd7fc9472019308097d99102df9acee22aa2451ae808d27840bc874320292" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp311-cp311-win_amd64.whl", hash = "sha256:db37df7eee906f8fe0a639fdc673f3541cb2e173169b16d4133447eb922d1938" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:9377faee65a290578280ac7f4884c3586253dac2ca28c60f458ff6efe86a6b05" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:9b302192b570657c1cc787a4d487ae4bbb7f2aab1c01b1fcc46757e7f86f391e" },
 ]
 
 [[package]]

www/.npmrc

@@ -1 +1,3 @@
-minimum-release-age=1440 #24hr in minutes
+minimum-release-age=1440 #24hr in minutes
+minimum-release-age-exclude[]=next
+minimum-release-age-exclude[]=@next/*

www/.prettierignore

@@ -0,0 +1 @@
+pnpm-lock.yaml

www/package.json

@@ -31,7 +31,7 @@
     "ioredis": "^5.10.0",
     "jest-worker": "^30.2.0",
     "lucide-react": "^0.575.0",
-    "next": "^16.1.6",
+    "next": "16.1.7",
     "next-auth": "^4.24.13",
     "next-themes": "^0.4.6",
     "nuqs": "^2.8.9",
@@ -75,7 +75,8 @@
       "js-yaml@<4.1.1": "4.1.1",
       "webpack": "5.105.3",
       "serialize-javascript": "7.0.4",
-      "immutable": "5.1.5"
+      "immutable": "5.1.5",
+      "next": "16.1.7"
     }
   }
 }