crop-chem-docs/.gitea/workflows/image-only.yml

name: Image rebuild (skip scrape)

# Fast path for code-only changes. Skips the scrape and goes straight
# to: rebuild indexes (from corpus already committed on main) + image
# build + push. Runtime ~10 min vs ~9 h for the full monthly refresh.
#
# Use when a PR only changes code/config — anything where the upstream
# corpus hasn't moved but we want the new Python in the running image.

on:
  workflow_dispatch:
  push:
    branches:
      - main
    paths:
      - "docs_mcp/**"
      - "rag/**"
      - "scrape/**"
      - "requirements.txt"
      - "Dockerfile"
      - "sources.json"

# If multiple pushes land in quick succession, cancel the older one
# rather than queueing both — each run is ~90 min and the older
# commit's image just gets overwritten by the newer one anyway.
concurrency:
  group: image-only
  cancel-in-progress: true

env:
  REGISTRY_PUSH: 192.168.0.2:1234
  REGISTRY_PULL: git.jpaul.io
  IMAGE: ${{ github.repository }}
  OLLAMA_URL: http://192.168.0.2:11434,http://192.168.0.2:11435,http://192.168.0.125:11434
  EMBED_MODEL: nomic-embed-text
  PRODUCT_NAME: crop_chem

jobs:
  build:
    runs-on: docker
    container:
      image: catthehacker/ubuntu:act-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Verify image name resolves
        # ${{ github.event.repository.name }} silently resolves to EMPTY on
        # schedule events (Gitea >=1.27), which built the tag
        # "192.168.0.2:1234/<owner>/:latest" and failed the build only AFTER
        # the full scrape. IMAGE now comes from github.repository; this step
        # fails in seconds if it ever goes empty again.
        run: |
          echo "IMAGE=${IMAGE}"
          case "${IMAGE}" in
            */?*) ;;
            *) echo "ERROR: IMAGE did not resolve to owner/repo"; exit 1 ;;
          esac

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.12"

      - name: Install dependencies
        run: |
          python -m pip install -q --upgrade pip
          python -m pip install -q -r requirements.txt

      - name: Verify committed corpus is present
        run: |
          test -d corpus || { echo "ERROR: corpus/ missing on this ref"; exit 1; }
          n_md=$(find corpus -name '*.md' | wc -l)
          n_json=$(find corpus -name '*.json' | wc -l)
          echo "corpus: $(du -sh corpus | cut -f1) on disk, ${n_md} .md / ${n_json} .json"
          test "$n_md" -gt 100 || { echo "ERROR: corpus has fewer than 100 labels — was the rename committed?"; exit 1; }

      - name: Rebuild indexes from committed corpus
        run: python -m rag.index --rebuild

      - name: Log in to Gitea container registry
        run: echo "${{ secrets.REGISTRY_TOKEN }}" | docker login "${REGISTRY_PUSH}" -u "${{ github.repository_owner }}" --password-stdin

      - name: Build & push image
        run: |
          SHA_TAG=$(echo "$GITHUB_SHA" | cut -c1-12)
          CORPUS_TAG="corpus-$(date -u +%Y.%m.%d)"
          docker build \
            -t "${REGISTRY_PUSH}/${IMAGE}:latest" \
            -t "${REGISTRY_PUSH}/${IMAGE}:${SHA_TAG}" \
            -t "${REGISTRY_PUSH}/${IMAGE}:${CORPUS_TAG}" \
            .
          # Smoke: the image must at least import its server module before we
          # publish it. mcp 2.x renamed mcp.server.fastmcp -> mcp.server.mcpserver,
          # so an unpinned dep produced a green build that crash-looped in prod.
          # Import is side-effect-free here (lazy singletons), so this needs no
          # Ollama/Chroma.
          docker run --rm --entrypoint python \
            "${REGISTRY_PUSH}/${IMAGE}:latest" -c "import docs_mcp.server"
          docker push "${REGISTRY_PUSH}/${IMAGE}:latest"
          docker push "${REGISTRY_PUSH}/${IMAGE}:${SHA_TAG}"
          docker push "${REGISTRY_PUSH}/${IMAGE}:${CORPUS_TAG}"

      - name: Link container package to this repo
        env:
          GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
        run: |
          OWNER="${{ github.repository_owner }}"
          PKG="${GITHUB_REPOSITORY##*/}"
          BODY=$(mktemp)
          CODE=$(curl -sS -o "$BODY" -w "%{http_code}" -X POST \
            -H "Authorization: token ${GITEA_TOKEN}" \
            "https://${REGISTRY_PULL}/api/v1/packages/${OWNER}/container/${PKG}/-/link/${PKG}")
          echo "link http=$CODE  body=$(cat "$BODY")"
          case "$CODE" in
            201) echo "linked package to ${OWNER}/${PKG}" ;;
            400) echo "already linked — ok" ;;
            *)   echo "unexpected status $CODE"; exit 1 ;;
          esac

      - name: Prune old container versions
        # GC requires broader scope than REGISTRY_TOKEN's push perms
        # (got HTTP 403 enumerating /packages/.../versions on run #122).
        # Non-critical — housekeeping only. Don't fail the whole run.
        # TODO: issue a separate PAT with admin:package scope and set
        # as PACKAGES_ADMIN_TOKEN, then use it here.
        continue-on-error: true
        env:
          GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
        run: |
          python scripts/registry_gc.py \
            --owner "${{ github.repository_owner }}" \
            --package "${GITHUB_REPOSITORY##*/}" \
            --keep-days 180 \
            --keep-latest 6