name: regression

permissions:
  contents: read

# Suppress hyperframes CLI telemetry from HeyGen's own CI runs.
# External users' CI continues to emit telemetry unless they set this themselves.
env:
  HYPERFRAMES_NO_TELEMETRY: "1"

# Graphite can update a branch and its PR base separately for the same head
# SHA. Keep only the newest expensive regression run for each PR/ref.
concurrency:
  group: regression-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

on:
  pull_request:
  push:
    branches:
      - main

jobs:
  changes:
    name: Detect changes
    runs-on: ubuntu-latest
    timeout-minutes: 2
    outputs:
      code: ${{ steps.filter.outputs.code }}
    steps:
      # Force git-based change detection instead of the pull_request REST API.
      # The API path can fail the whole workflow on transient listFiles
      # timeouts before any regression shard even starts.
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
        with:
          fetch-depth: 0
      - uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4
        id: filter
        with:
          token: ""
          filters: |
            code:
              - "packages/core/**"
              - "packages/producer/**"
              - "packages/engine/**"
              - "Dockerfile*"

  preflight:
    name: Preflight (lint + format)
    needs: changes
    if: needs.changes.outputs.code == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
      - uses: ./.github/actions/preflight

  regression-shards:
    needs: [changes, preflight]
    if: needs.changes.outputs.code == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 60
    strategy:
      fail-fast: true
      matrix:
        # Shards are bin-packed by measured per-test duration (LPT heuristic on
        # CI run 25893372795) so each row carries ~15-16 min of work. When a
        # new fixture lands, drop it into the currently-lightest shard or
        # re-balance against fresh `test_suite_summary` timings. Worst-shard
        # work time was 19.3 min under the old tag-based split (styles-e);
        # the rebalance brings every shard within ~40s of the others.
        include:
          - shard: shard-1
            args: "hdr-regression style-5-prod style-3-prod mov-prores"
          - shard: shard-2
            args: "style-15-prod hdr-hlg-regression style-1-prod many-cuts vfr-screen-recording render-symlinked-assets"
          - shard: shard-3
            args: "style-7-prod style-8-prod style-10-prod css-spinner-render-compat webm-transparency mp4-h264-sdr webm-vp9"
          - shard: shard-4
            args: "style-16-prod style-9-prod style-17-prod iframe-render-compat variables-prod mp4-h265-sdr"
          - shard: shard-5
            args: "style-4-prod style-11-prod style-2-prod animejs-adapter typegpu-adapter parallel-capture-regression"
          - shard: shard-6
            args: "overlay-montage-prod style-12-prod chat missing-host-comp-id png-sequence portrait-edge-bleed"
          - shard: shard-7
            args: "sub-composition-video style-18-prod raf-ball-render-compat font-variant-numeric sub-comp-t0 sub-comp-id-selector"
          - shard: shard-8
            args: "style-13-prod style-6-prod vignelli-stacking gsap-letters-render-compat audio-mux-parity"
    steps:
      - name: Checkout (with LFS)
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
        with:
          lfs: true

      - name: Validate LFS files
        run: |
          echo "Checking golden baseline MP4s are real files (not LFS pointers)..."
          for mp4 in packages/producer/tests/*/output/output.mp4; do
            if [ -f "$mp4" ]; then
              size=$(stat --format=%s "$mp4")
              if [ "$size" -lt 1000 ]; then
                echo "ERROR: $mp4 appears to be an LFS pointer ($size bytes)"
                exit 1
              fi
              echo "OK: $mp4 ($size bytes)"
            fi
          done

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3

      - name: Build test Docker image (cached)
        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
        with:
          context: .
          file: Dockerfile.test
          load: true
          tags: hyperframes-producer:test
          cache-from: type=gha,scope=regression-test-image
          # PR matrices can fan out across many stacked branches at once. Let
          # them consume the shared cache, but keep a single writer on main so
          # concurrent exports cannot exhaust the Actions cache service.
          cache-to: ${{ github.event_name == 'push' && 'type=gha,mode=max,scope=regression-test-image' || '' }}

      - name: "Run regression shard: ${{ matrix.shard }}"
        run: |
          echo "Shard: ${{ matrix.shard }}"
          echo "Args: ${{ matrix.args }}"
          docker run --rm \
            --security-opt seccomp=unconfined \
            --shm-size=4g \
            -v ${{ github.workspace }}/packages/producer/tests:/app/packages/producer/tests \
            hyperframes-producer:test \
            ${{ matrix.args }}

      - name: Upload failure artifacts
        if: failure()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
        with:
          name: regression-failures-${{ matrix.shard }}
          path: packages/producer/tests/*/failures/
          if-no-files-found: ignore

  # Summary job — matches the required check name in branch protection
  regression:
    runs-on: ubuntu-latest
    needs: [changes, regression-shards]
    if: always()
    steps:
      - name: Check results
        run: |
          if [ "${{ needs.changes.outputs.code }}" != "true" ]; then
            echo "No code changes — skipping regression (auto-pass)"
            exit 0
          fi
          if [ "${{ needs.regression-shards.result }}" != "success" ]; then
            echo "One or more regression shards failed"
            exit 1
          fi