name: 'Evals: Nightly'

on:
  schedule:
    - cron: '0 1 * * *' # Runs at 1 AM every day
  workflow_dispatch:
    inputs:
      run_all:
        description: 'Run all evaluations (including usually passing)'
        type: 'boolean'
        default: true

permissions:
  contents: 'read'
  checks: 'write'
  actions: 'read'

jobs:
  evals:
    name: 'Evals (USUALLY_PASSING) nightly run'
    runs-on: 'gemini-cli-ubuntu-16-core'
    strategy:
      fail-fast: false
      matrix:
        model:
          - 'gemini-3-pro-preview'
          - 'gemini-3-flash-preview'
          - 'gemini-2.5-pro'
          - 'gemini-2.5-flash'
          - 'gemini-2.5-flash-lite'
        run_attempt: [1, 2, 3]
    steps:
      - name: 'Checkout'
        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5

      - name: 'Set up Node.js'
        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
        with:
          node-version-file: '.nvmrc'
          cache: 'npm'

      - name: 'Install dependencies'
        run: 'npm ci'

      - name: 'Build project'
        run: 'npm run build'

      - name: 'Create logs directory'
        run: 'mkdir -p evals/logs'

      - name: 'Run Evals'
        env:
          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
          GEMINI_MODEL: '${{ matrix.model }}'
          RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
        run: 'npm run test:all_evals'

      - name: 'Upload Logs'
        if: 'always()'
        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
        with:
          name: 'eval-logs-${{ matrix.model }}-${{ matrix.run_attempt }}'
          path: 'evals/logs'
          retention-days: 7

  aggregate-results:
    name: 'Aggregate Results'
    needs: ['evals']
    if: 'always()'
    runs-on: 'gemini-cli-ubuntu-16-core'
    steps:
      - name: 'Checkout'
        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5

      - name: 'Download Logs'
        uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
        with:
          path: 'artifacts'

      - name: 'Generate Summary'
        env:
          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
        run: 'node scripts/aggregate_evals.js artifacts >> "$GITHUB_STEP_SUMMARY"'