elizaos--eliza/.github/workflows/certification-image.yml

# certification-image — builds and publishes the GPU certification image
# (docker/certification/Dockerfile.gpu) that vast.ai certification runs boot
# (#14548, epic #14541). The image bakes everything the 16 KB onstart script
# cannot carry: CUDA llama-server, the sha256-pinned gpu-vision models,
# node24/bun/playwright/tesseract/ffmpeg. Pushes
# ghcr.io/elizaos/certification-gpu:{latest,sha-<short>} via GITHUB_TOKEN —
# no extra registry secret. Rebuilds are rare (image inputs only), so this
# triggers on dispatch plus pushes that touch its own inputs, never on PRs.

name: certification-image

on:
  workflow_dispatch:
  push:
    branches: [develop]
    paths:
      - "docker/certification/Dockerfile.gpu"
      - "scripts/gpu-vision/setup.mjs"
      - "scripts/gpu-vision/lib.mjs"
      - "scripts/gpu-vision/models.lock.json"
      - ".github/workflows/certification-image.yml"

concurrency:
  group: certification-image-${{ github.ref }}
  cancel-in-progress: false

permissions:
  contents: read

env:
  REGISTRY: ghcr.io
  IMAGE_NAME: ${{ github.repository_owner }}/certification-gpu

jobs:
  build-and-push:
    name: build-and-push
    # Same fleet fallback as build-agent-image: hetzner when online (the
    # image is ~15 GB with baked models and CUDA layers; hosted runners need
    # the disk-free step below to survive it).
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 180
    permissions:
      contents: read
      packages: write
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          submodules: false
          show-progress: false

      - name: Free up disk space
        run: |
          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL || true
          sudo docker image prune -a -f || true
          df -h /

      - uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0
        with:
          registry: ${{ env.REGISTRY }}
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c
        with:
          driver-opts: |
            env.BUILDKIT_STEP_LOG_MAX_SIZE=10485760
            env.BUILDKIT_STEP_LOG_MAX_SPEED=10485760

      # Docker tags must be lowercase; github.repository_owner is "elizaOS".
      - id: image
        run: echo "name=${REGISTRY}/${IMAGE_NAME,,}" >> "$GITHUB_OUTPUT"

      - id: meta
        uses: docker/metadata-action@80c7e94dd9b9319bd5eb7a0e0fe9291e23a2a2e9
        with:
          images: ${{ steps.image.outputs.name }}
          # :latest tracks develop — it is what run-certification.mjs boots by
          # default; :sha-<short> pins for reproducible re-runs.
          tags: |
            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/develop' }}
            type=sha,prefix=sha-,format=short

      - name: Build and push
        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a
        with:
          context: .
          file: docker/certification/Dockerfile.gpu
          push: true
          tags: ${{ steps.meta.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels }}
          # Single-manifest image: vast pulls by tag, provenance attestation
          # manifests confuse some of its pullers.
          provenance: false
          cache-from: type=gha
          cache-to: type=gha,mode=max

      - name: Image summary
        run: |
          {
            echo "## certification-image"
            echo ""
            echo "Pushed tags:"
            echo '```'
            echo "${{ steps.meta.outputs.tags }}"
            echo '```'
            echo ""
            echo "Boot it on vast: \`node scripts/vast/run-certification.mjs --image ${{ steps.image.outputs.name }}:latest ...\`"
          } >> "$GITHUB_STEP_SUMMARY"