node-recovery.yml

name: Node recovery

# Runs the ARC role's node recovery watcher in a three-node kind cluster (tests/node_recovery/run.sh): the role's rendered Deployment and RBAC, the watcher image built from this checkout, and a stopped worker container standing in for a node that goes down. Only on changes that can affect the watcher.
#
# GitHub-hosted ubuntu-latest has Docker, kind, kubectl and jq already.

on:
  pull_request:
    paths:
      - roles/github_runner_arc/**
      - scripts/node-recovery.sh
      - node-recovery/**
      - tests/node_recovery/**
      - .github/workflows/node-recovery.yml
  workflow_dispatch:

concurrency:
  group: node-recovery-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

jobs:
  recovery:
    name: Recovery in kind
    runs-on: ubuntu-latest
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@v7

      - name: Install Ansible
        run: |
          set -euo pipefail
          if ! python3 -m venv "${RUNNER_TEMP}/venv" 2>/dev/null; then
            sudo apt-get update -qq
            sudo apt-get install -y -qq python3-venv
            python3 -m venv "${RUNNER_TEMP}/venv"
          fi
          "${RUNNER_TEMP}/venv/bin/pip" install --quiet --prefer-binary ansible-core
          echo "${RUNNER_TEMP}/venv/bin" >> "$GITHUB_PATH"

      - name: Run the node recovery test
        run: tests/node_recovery/run.sh