.github/workflows/resource_sync.yml

name: Resource Sync

on:
  schedule:
    - cron: "0 4 * * *"
  workflow_dispatch:
    inputs:
      limit:
        description: "Candidate fetch limit per source"
        required: false
        default: "20"
      max_promotions:
        description: "Optional max number of candidate promotions"
        required: false
        default: ""
      enforce_pashto_relevance:
        description: "Also remove existing entries without Pashto evidence"
        required: false
        default: "true"

permissions:
  contents: write
  pull-requests: write

env:
  RESOURCE_LIMIT: ${{ github.event.inputs.limit || '20' }}
  MAX_PROMOTIONS: ${{ github.event.inputs.max_promotions || '' }}
  ENFORCE_PASHTO_RELEVANCE: ${{ github.event.inputs.enforce_pashto_relevance || 'true' }}

jobs:
  sync:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          python -m pip install -e ".[dev]"

      - name: Review existing resources for stale or low-value entries
        run: |
          if [ "${ENFORCE_PASHTO_RELEVANCE}" = "true" ]; then
            python scripts/review_existing_resources.py --enforce-pashto-relevance
          else
            python scripts/review_existing_resources.py
          fi

      - name: Sync candidate resources
        run: python scripts/sync_resources.py --limit "${RESOURCE_LIMIT}"

      - name: Auto-promote valid candidates
        run: |
          if [ -n "${MAX_PROMOTIONS}" ]; then
            python scripts/promote_candidates.py --max-promotions "${MAX_PROMOTIONS}"
          else
            python scripts/promote_candidates.py
          fi

      - name: Validate catalog
        run: python scripts/validate_resource_catalog.py

      - name: Generate resource views
        run: python scripts/generate_resource_views.py

      - name: Ensure labels exist
        uses: actions/github-script@v7
        with:
          script: |
            const labels = [
              { name: "resource-update", color: "0e8a16", description: "Automated resource catalog updates" },
              { name: "needs-review", color: "fbca04", description: "Needs maintainer review before merge" }
            ];
            for (const label of labels) {
              try {
                await github.rest.issues.getLabel({
                  owner: context.repo.owner,
                  repo: context.repo.repo,
                  name: label.name
                });
              } catch (error) {
                if (error.status === 404) {
                  await github.rest.issues.createLabel({
                    owner: context.repo.owner,
                    repo: context.repo.repo,
                    name: label.name,
                    color: label.color,
                    description: label.description
                  });
                } else {
                  throw error;
                }
              }
            }

      - name: Create review PR
        uses: peter-evans/create-pull-request@v6
        with:
          branch: bot/resource-sync
          delete-branch: true
          commit-message: "chore(resources): sync candidate feed and auto-promote valid entries"
          title: "chore(resources): sync and auto-promote Pashto resources"
          body: |
            Automated daily resource sync.

            Scope:
            - Reviews existing catalog entries and removes stale ones only with strong logged reasons
            - Updates `resources/catalog/pending_candidates.json`
            - Auto-promotes valid non-duplicate candidates into `resources/catalog/resources.json`
            - Regenerates resource indexes and search payload
          labels: |
            resource-update
            needs-review
          add-paths: |
            resources/catalog/pending_candidates.json
            resources/catalog/resources.json
            resources/catalog/removal_log.json
            resources/README.md
            resources/datasets/README.md
            resources/models/README.md
            resources/benchmarks/README.md
            resources/tools/README.md
            resources/papers/README.md
            resources/projects/README.md
            resources/codes/README.md
            docs/search/resources.json