release-canary.yml

name: Release Canary

on:
  workflow_dispatch:
  workflow_run:
    workflows: ["Release Dev"]
    types: [completed]

permissions:
  contents: read

defaults:
  run:
    shell: bash

jobs:
  macos:
    name: macOS Homebrew
    if: ${{ github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success' }}
    runs-on: macos-latest-xlarge
    timeout-minutes: 20
    steps:
      - name: Ensure VM driver
        run: |
          launchctl setenv OPENSHELL_DRIVERS vm

      - name: Install and check status
        run: |
          curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/${{ github.event.workflow_run.head_sha || github.sha }}/install.sh | sh
          openshell status

  ubuntu:
    name: Ubuntu Docker
    if: ${{ github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success' }}
    runs-on: ubuntu-latest
    timeout-minutes: 20
    steps:
      - name: Ensure Docker
        run: |
          if ! command -v docker >/dev/null 2>&1; then
            sudo apt-get update
            sudo apt-get install -y docker.io
          fi
          sudo systemctl start docker || sudo service docker start
          mkdir -p "${HOME}/.config/openshell"
          printf 'OPENSHELL_DRIVERS=docker\n' > "${HOME}/.config/openshell/gateway.env"
          docker info

      - name: Install and check status
        run: |
          curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/${{ github.event.workflow_run.head_sha || github.sha }}/install.sh | sh
          openshell status

  fedora:
    name: Fedora RPM
    if: ${{ github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success' }}
    runs-on: linux-amd64-cpu8
    timeout-minutes: 20
    container:
      image: fedora:latest
      options: --privileged
    steps:
      - name: Ensure Podman
        run: |
          dnf install -y curl podman
          mkdir -p "${HOME}/.config/openshell"
          printf 'OPENSHELL_DRIVERS=podman\n' > "${HOME}/.config/openshell/gateway.env"
          podman info

      - name: Install and check status
        run: |
          curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/${{ github.event.workflow_run.head_sha || github.sha }}/install.sh | sh
          openshell status

  kubernetes:
    name: Kubernetes Helm (kind)
    if: ${{ github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success' }}
    runs-on: ubuntu-latest
    timeout-minutes: 20
    env:
      KIND_CLUSTER_NAME: release-canary-${{ github.run_id }}
      RELEASE_NAME: openshell
      RELEASE_NAMESPACE: openshell
      KIND_GATEWAY_NAME: kind
    steps:
      - name: Install Helm
        uses: azure/setup-helm@v5

      - name: Create kind cluster
        uses: helm/kind-action@v1
        with:
          cluster_name: ${{ env.KIND_CLUSTER_NAME }}
          wait: 120s

      - name: Install OpenShell Helm chart from GHCR OCI
        run: |
          set -euo pipefail
          helm install "$RELEASE_NAME" oci://ghcr.io/nvidia/openshell/helm-chart \
            --version 0.0.0-dev \
            --namespace "$RELEASE_NAMESPACE" --create-namespace \
            --set server.disableTls=true \
            --wait --timeout 5m

      - name: Verify gateway pod is Ready
        run: |
          set -euo pipefail
          kubectl wait --namespace "$RELEASE_NAMESPACE" \
            --for=condition=Ready pod \
            --selector="app.kubernetes.io/name=openshell,app.kubernetes.io/instance=${RELEASE_NAME}" \
            --timeout=300s

      - name: Port-forward gateway service
        run: |
          set -euo pipefail
          nohup kubectl port-forward --namespace "$RELEASE_NAMESPACE" \
            "svc/${RELEASE_NAME}" 8080:8080 \
            > port-forward.log 2>&1 &
          echo $! > port-forward.pid
          for _ in $(seq 1 30); do
            if (echo > /dev/tcp/127.0.0.1/8080) >/dev/null 2>&1; then
              echo "port-forward is reachable"
              exit 0
            fi
            sleep 1
          done
          echo "port-forward did not become reachable" >&2
          cat port-forward.log >&2
          exit 1

      - name: Install OpenShell CLI
        run: |
          set -euo pipefail
          mkdir -p "${HOME}/.config/openshell"
          printf 'OPENSHELL_DRIVERS=docker\n' > "${HOME}/.config/openshell/gateway.env"
          curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/${{ github.event.workflow_run.head_sha || github.sha }}/install.sh | sh

      - name: Register kind gateway and check status
        run: |
          set -euo pipefail
          openshell gateway add http://127.0.0.1:8080 --local --name "$KIND_GATEWAY_NAME"
          openshell status

      - name: Diagnostics on failure
        if: failure()
        run: |
          set +e
          echo "--- helm status ---"
          helm status "$RELEASE_NAME" --namespace "$RELEASE_NAMESPACE"
          echo "--- helm get manifest ---"
          helm get manifest "$RELEASE_NAME" --namespace "$RELEASE_NAMESPACE"
          echo "--- get all ---"
          kubectl get all --namespace "$RELEASE_NAMESPACE"
          echo "--- describe pods ---"
          kubectl describe pods --namespace "$RELEASE_NAMESPACE"
          echo "--- pod logs ---"
          kubectl logs --namespace "$RELEASE_NAMESPACE" \
            --selector="app.kubernetes.io/name=openshell,app.kubernetes.io/instance=${RELEASE_NAME}" \
            --tail=200 --all-containers --prefix
          echo "--- port-forward log ---"
          cat port-forward.log 2>/dev/null
          echo "--- openshell gateway list ---"
          openshell gateway list 2>/dev/null
          echo "--- openshell version ---"
          openshell --version 2>/dev/null