name: GPU E2E Test

on:
  workflow_call:
    inputs:
      image-tag:
        description: "Image tag to test (typically the commit SHA)"
        required: true
        type: string

permissions:
  contents: read
  packages: read

jobs:
  e2e-gpu:
    name: "E2E GPU (${{ matrix.name }})"
    runs-on: ${{ matrix.runner }}
    continue-on-error: ${{ matrix.experimental }}
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        include:
          - name: linux-arm64
            runner: linux-arm64-gpu-l4-latest-1
            cluster: e2e-gpu-arm64
            port: "8083"
            experimental: false
          - name: linux-amd64
            runner: linux-amd64-gpu-rtxpro6000-latest-1
            cluster: e2e-gpu-amd64
            port: "8084"
            experimental: false
          - name: wsl-amd64
            runner: wsl-amd64-gpu-rtxpro6000-latest-1
            cluster: e2e-gpu-wsl
            port: "8085"
            experimental: true
    container:
      image: ghcr.io/nvidia/openshell/ci:latest
      credentials:
        username: ${{ github.actor }}
        password: ${{ secrets.GITHUB_TOKEN }}
      options: --privileged
      volumes:
        - /var/run/docker.sock:/var/run/docker.sock
    env:
      MISE_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
      IMAGE_TAG: ${{ inputs.image-tag }}
      OPENSHELL_REGISTRY: ghcr.io/nvidia/openshell
      OPENSHELL_REGISTRY_HOST: ghcr.io
      OPENSHELL_REGISTRY_NAMESPACE: nvidia/openshell
      OPENSHELL_REGISTRY_USERNAME: ${{ github.actor }}
      OPENSHELL_REGISTRY_PASSWORD: ${{ secrets.GITHUB_TOKEN }}
      OPENSHELL_GATEWAY: ${{ matrix.cluster }}
    steps:
      - uses: actions/checkout@v4

      - name: Log in to GHCR
        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u "${{ github.actor }}" --password-stdin

      - name: Pull cluster image
        run: docker pull ghcr.io/nvidia/openshell/cluster:${{ inputs.image-tag }}

      - name: Install Python dependencies and generate protobuf stubs
        run: uv sync --frozen && mise run --no-deps python:proto

      - name: Bootstrap GPU cluster
        env:
          GATEWAY_HOST: host.docker.internal
          GATEWAY_PORT: ${{ matrix.port }}
          CLUSTER_NAME: ${{ matrix.cluster }}
          # Passes --gpu to the gateway bootstrap so the cluster comes up with GPU passthrough enabled.
          CLUSTER_GPU: "1"
          SKIP_IMAGE_PUSH: "1"
          SKIP_CLUSTER_IMAGE_BUILD: "1"
          OPENSHELL_CLUSTER_IMAGE: ghcr.io/nvidia/openshell/cluster:${{ inputs.image-tag }}
        run: mise run --no-deps --skip-deps cluster

      - name: Run tests
        run: mise run --no-deps --skip-deps e2e:python:gpu