check-data-health.yml

name: Check Current Data Health

on:
  schedule:
    - cron: '0 3 * * 1'
  workflow_dispatch:

concurrency:
  group: check-current-data-health
  cancel-in-progress: false

permissions:
  contents: read
  issues: write

jobs:
  check-data-health:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout repository
        uses: actions/checkout@v7

      - name: Setup pnpm
        uses: ./.github/actions/setup-pnpm

      - name: Check current data health
        id: data-health
        continue-on-error: true
        run: |
          pnpm exec tsx scripts/validate/data-health.ts \
            --as-of="$(TZ=Asia/Shanghai date +%F)" \
            --fail-on=error \
            --fail-on-code=stale-verification,future-verification-date \
            2>&1 | tee data-health-current.log

      - name: Report stale or invalid data
        if: steps.data-health.outcome == 'failure'
        uses: actions/github-script@v8
        with:
          script: |
            const fs = require('node:fs');
            const title = 'Current manifest data requires review';
            const output = fs.readFileSync('data-health-current.log', 'utf8').slice(-6000);
            const body = `## Current Data Health Check Failed

            The scheduled check evaluates freshness against today's date in Asia/Shanghai without
            rewriting the committed snapshot.

            **Check run:** [View details](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }})

            \`\`\`text
            ${output}
            \`\`\``;

            const issues = await github.paginate(github.rest.issues.listForRepo, {
              owner: context.repo.owner,
              repo: context.repo.repo,
              state: 'open',
              labels: 'automated',
              per_page: 100
            });
            const existingIssue = issues.find(issue => issue.title === title);

            if (!existingIssue) {
              await github.rest.issues.create({
                owner: context.repo.owner,
                repo: context.repo.repo,
                title,
                body,
                labels: ['automated', 'maintenance']
              });
            } else {
              await github.rest.issues.update({
                owner: context.repo.owner,
                repo: context.repo.repo,
                issue_number: existingIssue.number,
                body
              });
            }

      - name: Close resolved data-health issues
        if: steps.data-health.outcome == 'success'
        uses: actions/github-script@v8
        with:
          script: |
            const issues = await github.paginate(github.rest.issues.listForRepo, {
              owner: context.repo.owner,
              repo: context.repo.repo,
              state: 'open',
              labels: 'automated',
              per_page: 100
            });

            for (const issue of issues.filter(issue => issue.title === 'Current manifest data requires review')) {
              await github.rest.issues.createComment({
                owner: context.repo.owner,
                repo: context.repo.repo,
                issue_number: issue.number,
                body: `Current-date data health passed in ${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}.`
              });
              await github.rest.issues.update({
                owner: context.repo.owner,
                repo: context.repo.repo,
                issue_number: issue.number,
                state: 'closed',
                state_reason: 'completed'
              });
            }

      - name: Fail after reporting
        if: steps.data-health.outcome == 'failure'
        run: exit 1