researchowl/.gitea/workflows/build.yml

name: Build & Deploy ResearchOwl

on:
  push:
    branches:
      - main

env:
  REGISTRY: gitea.gitea.svc.cluster.local:3000
  K8S_MANIFESTS_REPO: http://chemavx:${{ secrets.CI_TOKEN }}@gitea.gitea.svc.cluster.local:3000/chemavx/k8s-manifests.git
  GIT_SSL_NO_VERIFY: "true"
  TELEGRAM_CHAT_ID: "5138407666"

jobs:
  build-and-push:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4
        with:
          ssl-verify: false

      - name: Verify vendored SEO engine
        run: |
          set -e
          CANON_URL="http://gitea.gitea.svc.cluster.local:3000/chemavx/chemavx-seo-tools/raw/branch/main/seo_rules.py"
          curl -fsS -u "chemavx:${{ secrets.CI_TOKEN }}" "$CANON_URL" -o /tmp/canonical_seo_rules.py
          N=$(grep -n "BEGIN VENDORED seo_rules.py" src/seo/rules.py | head -1 | cut -d: -f1)
          tail -n +$((N+1)) src/seo/rules.py > /tmp/vendored_body.py
          if cmp -s /tmp/canonical_seo_rules.py /tmp/vendored_body.py; then
            echo "OK: vendored SEO engine matches canonical chemavx-seo-tools/seo_rules.py"
          else
            echo "::error::SEO ENGINE DRIFT — src/seo/rules.py != canonical seo_rules.py. Run 'make sync-seo' and commit."
            diff -u /tmp/canonical_seo_rules.py /tmp/vendored_body.py | head -40 || true
            exit 1
          fi

      - name: Set image tag
        id: tag
        run: echo "TAG=${GITHUB_SHA::8}" >> $GITHUB_OUTPUT

      - name: Log in to registry
        run: echo "${{ secrets.CI_TOKEN }}" | docker login gitea.gitea.svc.cluster.local:3000 -u chemavx --password-stdin

      - name: Clean previous buildx builder
        run: docker buildx rm ci-builder 2>/dev/null || true

      - name: Create buildx builder
        run: |
          cat > /tmp/buildkitd.toml << 'EOF'
          [registry."registry-cache.registry-cache.svc.cluster.local:5000"]
            http = true
            insecure = true

          [registry."gitea.gitea.svc.cluster.local:3000"]
            http = true
            insecure = true

          [registry."docker.io"]
            mirrors = ["registry-cache.registry-cache.svc.cluster.local:5000"]
          EOF
          docker buildx create \
            --name ci-builder \
            --driver docker-container \
            --driver-opt network=host \
            --config /tmp/buildkitd.toml \
            --use
          docker buildx inspect --bootstrap

      - name: Build and push image
        run: |
          TAG=${{ steps.tag.outputs.TAG }}
          docker buildx build \
            --builder ci-builder \
            --cache-from type=registry,ref=gitea.gitea.svc.cluster.local:3000/chemavx/researchowl:buildcache \
            --cache-to type=registry,ref=gitea.gitea.svc.cluster.local:3000/chemavx/researchowl:buildcache,mode=max \
            -t gitea.gitea.svc.cluster.local:3000/chemavx/researchowl:${TAG} \
            --push \
            -f Dockerfile .

      - name: Verify image in registry
        run: |
          TAG=${{ steps.tag.outputs.TAG }}
          HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
            -u "chemavx:${{ secrets.CI_TOKEN }}" \
            -H "Accept: application/vnd.docker.distribution.manifest.v2+json" \
            "http://gitea.gitea.svc.cluster.local:3000/v2/chemavx/researchowl/manifests/${TAG}")
          if [ "$HTTP_CODE" != "200" ]; then
            echo "ERROR: chemavx/researchowl:${TAG} not found in registry (HTTP $HTTP_CODE)"
            exit 1
          fi
          echo "OK: chemavx/researchowl:${TAG} verified in registry"

      - name: Run the suite inside the image
        run: |
          TAG=${{ steps.tag.outputs.TAG }}
          BASE=gitea.gitea.svc.cluster.local:3000/chemavx/researchowl:${TAG}
          # Contra la imagen recién construida, no contra el árbol de fuentes:
          # la suite tiene que ver las librerías que se van a desplegar. Antes
          # corría sólo en el portátil, con otro anthropic que el del pod, y por
          # eso un kwarg que el SDK ya no aceptaba pasó meses sin que nada lo
          # dijera.
          docker buildx build \
            --builder ci-builder \
            --load \
            --build-arg BASE=${BASE} \
            -t researchowl-test:${TAG} \
            -f Dockerfile.test .
          docker run --rm researchowl-test:${TAG}

      - name: Update k8s manifests
        run: |
          pip3 install pyyaml -q

          TAG=${{ steps.tag.outputs.TAG }}

          git config --global user.email "ci@git.chemavx.xyz"
          git config --global user.name "Gitea CI"

          git clone ${{ env.K8S_MANIFESTS_REPO }} /tmp/k8s-manifests
          cd /tmp/k8s-manifests

          sed -i "s|image: .*researchowl:.*|image: git.chemavx.xyz/chemavx/researchowl:${TAG}|g" \
            researchowl/deployment.yaml
          sed -i "s|imagePullPolicy: Never|imagePullPolicy: Always|g" \
            researchowl/deployment.yaml

          python3 -c "
          import yaml, sys
          f = 'researchowl/deployment.yaml'
          try:
              list(yaml.safe_load_all(open(f)))
              print('OK: ' + f)
          except yaml.YAMLError as e:
              print('FAIL: ' + f + ': ' + str(e), file=sys.stderr)
              sys.exit(1)
          "

          git add researchowl/deployment.yaml
          git diff --cached --quiet || git commit -m "ci: update researchowl image to ${TAG} [skip ci]"
          git push

      - name: Notify Telegram
        if: always()
        env:
          TAG: ${{ steps.tag.outputs.TAG }}
          JOB_STATUS: ${{ job.status }}
          TELEGRAM_TOKEN: ${{ secrets.TELEGRAM_BOT_TOKEN }}
        run: |
          TAG="${TAG:-${GITHUB_SHA:0:8}}"
          if [ "$JOB_STATUS" = "success" ]; then
            MSG="✅ Deploy researchowl:${TAG} completado"
          else
            MSG="❌ Deploy researchowl:${TAG} fallido (status: ${JOB_STATUS})"
          fi
          if [ -n "${TELEGRAM_TOKEN}" ]; then
            curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendMessage" \
              -d "chat_id=${{ env.TELEGRAM_CHAT_ID }}" \
              --data-urlencode "text=${MSG}"
          fi