name: Refresh docs snapshot

# The backend embeds a vendored docs snapshot (backend/windmill-api/docs_snapshot/*.gz)
# so in-product docs search works with no runtime egress. This job re-fetches it from
# windmill.dev on a schedule and opens a PR when it changed, keeping the embedded docs
# fresh independently of the release cadence (the binary embeds whatever is on the
# source tree at build time, so a merged refresh rides into the next release build).
on:
  schedule:
    - cron: "0 6 * * 1" # Mondays 06:00 UTC
  workflow_dispatch:

jobs:
  refresh:
    runs-on: ubicloud
    permissions:
      contents: write
      pull-requests: write
    steps:
      - uses: actions/create-github-app-token@v2
        id: app
        with:
          app-id: ${{ vars.INTERNAL_APP_ID }}
          private-key: ${{ secrets.INTERNAL_APP_KEY }}
      - uses: actions/checkout@v4
        with:
          token: ${{ steps.app.outputs.token }}
      - name: Fetch + re-gzip docs snapshot
        run: cd backend/windmill-api/docs_snapshot && ./fetch.sh
      - name: Sanity-check the fetched corpus
        # curl -f in fetch.sh rejects HTTP errors, but not a valid-but-garbage 200
        # (truncated file, error page). Guard against embedding a broken snapshot.
        run: |
          cd backend/windmill-api/docs_snapshot
          test "$(wc -c < llms-full.txt.gz)" -gt 100000
          test "$(wc -c < llms.txt.gz)" -gt 1000
          pages=$(gzip -dc llms-full.txt.gz | grep -c '^Source:' || true)
          echo "pages in snapshot: $pages"
          test "${pages:-0}" -ge 200
      - uses: peter-evans/create-pull-request@v6
        with:
          token: ${{ steps.app.outputs.token }}
          branch: chore/refresh-docs-snapshot
          add-paths: backend/windmill-api/docs_snapshot/*.gz
          commit-message: "chore: refresh vendored docs snapshot"
          title: "chore: refresh vendored docs snapshot"
          body: |
            Automated refresh of the embedded docs snapshot
            (`backend/windmill-api/docs_snapshot/*.gz`) from windmill.dev.

            Review the diff for unexpected churn (a bad upstream docs deploy would
            show up as a large drop in pages or content) before merging.