when:
  branch: main
  event: [push, pull_request]

steps:
  eval-baseline:
    image: node:23-alpine
    environment:
      DEEPSEEK_API_KEY:
        from_secret: DEEPSEEK_API_KEY
    commands:
      - apk add --no-cache git python3 py3-pip
      - npm install -g promptfoo
      - cd promptfoo-eval
      - promptfoo eval --max-concurrency 2 --no-cache -o results.json
      - python3 cost-tracker.py
      - |
        FAILURES=$(python3 -c "import json; d=json.load(open('results.json')); s=d['results']['stats']; print(s['failures']+s['errors'])")
        echo "Tests: $(python3 -c "import json; d=json.load(open('results.json')); s=d['results']['stats']; print(s['successes'])") passed, $FAILURES failed"
        if [ "$FAILURES" != "0" ]; then exit 1; fi
      - echo "✅ All eval tests passed!"