agnes-the-ai-analyst/.github/workflows/release.yml

name: Release

on:
  push:
    branches: [main, "feature/**"]

permissions:
  contents: write
  packages: write

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v5

      - uses: actions/setup-python@v6
        with:
          python-version: "3.13"

      - name: Install uv
        uses: astral-sh/setup-uv@v7

      - name: Install dependencies
        run: uv pip install --system ".[dev]"

      - name: Run tests
        run: pytest tests/ -v --tb=short
        env:
          TESTING: "1"

  build-and-push:
    needs: test
    runs-on: ubuntu-latest
    outputs:
      image_tag: ${{ steps.meta.outputs.versioned_tag }}
      version: ${{ steps.meta.outputs.version }}
      channel: ${{ steps.meta.outputs.channel }}
    steps:
      - uses: actions/checkout@v5
        with:
          fetch-depth: 0
          fetch-tags: true

      - name: Claim version tag (with retry to avoid race conditions)
        id: meta
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"

          YEAR_MONTH=$(date +%Y.%m)
          if [[ "${{ github.ref }}" == "refs/heads/main" ]]; then
            CHANNEL="stable"
          else
            CHANNEL="dev"
          fi
          SHORT_SHA=$(echo "${{ github.sha }}" | cut -c1-7)

          # Claim a unique version by pushing a git tag BEFORE building.
          # Retry up to 5 times if another CI run took our N.
          TAG_CLAIMED=false
          for ATTEMPT in 1 2 3 4 5; do
            git fetch --tags --force
            # Use max(N) not count — safe even if tags are deleted
            MAX_N=$(git tag -l "*-${YEAR_MONTH}.*" | sed 's/.*\.//' | sort -n | tail -1)
            N=$(( ${MAX_N:-0} + 1 ))
            VERSION="${YEAR_MONTH}.${N}"
            TAG="${CHANNEL}-${VERSION}"

            git tag -a "$TAG" -m "Release $TAG"
            if git push origin "$TAG" 2>/dev/null; then
              echo "Claimed tag $TAG (attempt $ATTEMPT)"
              TAG_CLAIMED=true
              break
            else
              echo "Tag $TAG already exists, retrying... (attempt $ATTEMPT)"
              git tag -d "$TAG"
              sleep 2
            fi
          done

          if [ "$TAG_CLAIMED" != "true" ]; then
            echo "::error::Failed to claim a unique version tag after 5 attempts"
            exit 1
          fi

          echo "channel=${CHANNEL}" >> "$GITHUB_OUTPUT"
          echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
          echo "versioned_tag=${TAG}" >> "$GITHUB_OUTPUT"
          echo "short_sha=${SHORT_SHA}" >> "$GITHUB_OUTPUT"

          echo "Channel: ${CHANNEL}"
          echo "Version: ${VERSION}"
          echo "Versioned tag: ${TAG}"          

      - name: Log in to GHCR
        uses: docker/login-action@v4
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Build and push
        uses: docker/build-push-action@v7
        with:
          push: true
          build-args: |
            AGNES_VERSION=${{ steps.meta.outputs.version }}
            RELEASE_CHANNEL=${{ steps.meta.outputs.channel }}            
          tags: |
            ghcr.io/${{ github.repository }}:${{ steps.meta.outputs.channel }}
            ghcr.io/${{ github.repository }}:${{ steps.meta.outputs.versioned_tag }}
            ghcr.io/${{ github.repository }}:sha-${{ steps.meta.outputs.short_sha }}            

  smoke-test:
    needs: build-and-push
    if: github.ref == 'refs/heads/main'
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v5

      - name: Start Agnes from built image
        run: |
          # Create empty .env (docker-compose.yml requires env_file: .env, gitignored)
          touch .env
          # Use prod compose (GHCR images) + CI overlay (test secrets)
          export AGNES_TAG="${{ needs.build-and-push.outputs.image_tag }}"
          docker compose -f docker-compose.yml -f docker-compose.prod.yml -f docker-compose.ci.yml up -d app
          # Wait for healthy (max 60s)
          timeout 60 bash -c 'until curl -sf http://localhost:8000/api/health | python3 -c "import sys,json; d=json.load(sys.stdin); sys.exit(0 if d[\"status\"]!=\"unhealthy\" else 1)"; do sleep 3; done'          

      - name: Run smoke tests
        run: bash scripts/smoke-test.sh http://localhost:8000

      - name: Collect logs on failure
        if: failure()
        run: docker compose -f docker-compose.yml -f docker-compose.prod.yml -f docker-compose.ci.yml logs > smoke-test-logs.txt

      - name: Upload logs
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: smoke-test-logs
          path: smoke-test-logs.txt

      - name: Teardown
        if: always()
        run: docker compose -f docker-compose.yml -f docker-compose.prod.yml -f docker-compose.ci.yml down -v