cs249r_book/.github/workflows/site-validate-dev.yml

name: '🌐 Landing Site · ✅ Validate (Dev)'

# =============================================================================
# Unified Site — Content & Build Validation
# =============================================================================
#
# Validates the unified mlsysbook.ai landing site (landing + about + community
# + newsletter) before the preview/publish workflows ever touch it.
#
# Flow:
#   1. BUILD_SITE   — Quarto render of the unified site
#   2. CHECK_LINKS  — Lychee external-link reachability (Tier 2, non-blocking)
#   3. SUMMARY      — Aggregate results
#
# Why this exists:
#   site-preview-dev.yml jumps straight to building & SSH-deploying. With no
#   validation gate the dev preview can land broken. This workflow is the
#   missing CI counterpart added as part of the staged-rollout safety net.
#
# Triggers:
#   - push: dev branch, site/** or shared/** paths
#   - pull_request: site/** or shared/** changes
#   - workflow_dispatch: manual
#
# Deploys to: N/A (validate only)
#
# Related:
#   - site-preview-dev.yml  — Dev preview deploy (gates on this passing)
#   - site-publish-live.yml — Production deploy
#
# =============================================================================

on:
  workflow_dispatch:
  # Reusable: site-preview-dev.yml calls this via `uses:` so the deploy
  # job can `needs:` a green validate. Standalone push/PR triggers stay
  # so the publish guard and README badge still see direct runs on dev.
  workflow_call:
  pull_request:
    paths:
      - 'site/**'
      - 'shared/**'
      - '.github/workflows/site-validate-dev.yml'
      - '.github/workflows/site-preview-dev.yml'
  push:
    branches: [dev]
    paths:
      - 'site/**'
      - 'shared/**'
      - '.github/workflows/site-validate-dev.yml'
      - '.github/workflows/site-preview-dev.yml'

permissions:
  contents: read

concurrency:
  # `head_ref || run_id` keeps PR cancel-on-amend behavior while making
  # push and workflow_call runs unique per-run, so a push to dev that
  # triggers both this workflow standalone AND Preview's `uses:` call
  # doesn't collide on a shared group. See staffml-validate-dev.yml.
  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
  cancel-in-progress: true

jobs:
  # ===========================================================================
  # Stage 1: Quarto site build
  # ===========================================================================
  build-site:
    name: '🔨 Build Unified Site'
    runs-on: ubuntu-latest
    timeout-minutes: 10

    steps:
      - name: 📥 Checkout
        uses: actions/checkout@v6

      - name: 🐍 Setup Python
        uses: actions/setup-python@v6
        with:
          python-version: ${{ vars.PYTHON_VERSION || '3.12' }}

      - name: 📬 Install newsletter sync deps (no API call)
        run: |
          pip install -r site/newsletter/requirements.txt
          # We deliberately do NOT pull from Buttondown here — that requires
          # a secret and is the deploy workflow's responsibility. We only need
          # the deps so Quarto can render the newsletter index.

      - name: 🔧 Setup Quarto
        uses: quarto-dev/quarto-actions/setup@v2

      - name: 🔨 Build Unified Site (HTML)
        working-directory: site
        run: quarto render

      - name: 🔍 Validate build output
        run: |
          MISSING=0
          for page in index.html about/index.html community/index.html newsletter/index.html; do
            if [ ! -f "site/_build/$page" ]; then
              echo "❌ MISSING: $page"
              MISSING=$((MISSING + 1))
            fi
          done
          if [ "$MISSING" -gt 0 ]; then
            echo "❌ $MISSING critical pages missing from build."
            exit 1
          fi
          echo "✅ Site built successfully"
          echo "📊 Build size: $(du -sh site/_build | cut -f1)"
          echo "📄 Pages: $(find site/_build -name '*.html' | wc -l)"

  # ===========================================================================
  # Stage 2: Link integrity (Tier 2 — non-blocking baseline)
  # ===========================================================================
  # Tier 1 pre-commit (shared/scripts/check-internal-links.py) already blocks
  # broken internal links + anchors. This Lychee pass adds external
  # reachability as a warning. Flip fail_on_broken=true once baseline is clean.
  check-links:
    name: '🔗 Check Links'
    uses: ./.github/workflows/infra-link-check.yml
    with:
      path_pattern: './site/**/*.qmd'
      lycheeignore_path: 'shared/config/.lycheeignore'
      fail_on_broken: false
      max_concurrency: 8

  # ===========================================================================
  # Summary
  # ===========================================================================
  summary:
    name: '📊 Summary'
    runs-on: ubuntu-latest
    needs: [build-site, check-links]
    if: always()

    steps:
      - name: 📊 Generate Summary
        run: |
          echo "## 🌐 Unified Site Validation Results" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "| Check | Status |" >> $GITHUB_STEP_SUMMARY
          echo "|-------|--------|" >> $GITHUB_STEP_SUMMARY
          echo "| 🔨 Site Build (HTML) | ${{ needs.build-site.result }} |" >> $GITHUB_STEP_SUMMARY
          echo "| 🔗 Link Check | ${{ needs.check-links.result }} (non-blocking) |" >> $GITHUB_STEP_SUMMARY

      - name: ❌ Check for failures
        run: |
          if [ "${{ needs.build-site.result }}" = "failure" ]; then
            echo "❌ Validation failed"
            exit 1
          fi
          if [ "${{ needs.check-links.result }}" = "failure" ]; then
            echo "⚠️ Link check found issues (non-blocking)"
          fi
          echo "✅ Core checks passed"