teqo-backup/.github/workflows/ci.yml

# Post-merge verifier on `main`: always the FULL suite (no affected skips).
# When green, deploys production via `vercel deploy --prod` (Vercel Git builds
# are ignored — see scripts/vercel-ignore-build.sh). If HEAD moved while this
# run was in flight, `requeue` dispatches another run for the new tip.
name: CI

on:
  push:
    branches: [main]
  workflow_dispatch:

concurrency:
  group: main-verify
  cancel-in-progress: false

permissions:
  contents: read
  actions: write

env:
  DATABASE_URL: postgresql://teqo:teqo@localhost:5432/teqo_test
  PAYLOAD_SECRET: test-only-secret-not-used-in-production
  NEXT_PUBLIC_SITE_URL: http://localhost:3000

jobs:
  static:
    runs-on: ubuntu-latest
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@v5
      - uses: pnpm/action-setup@v6
      - uses: actions/setup-node@v5
        with:
          node-version: 24
          cache: pnpm
      - run: pnpm install --frozen-lockfile
      - run: node scripts/check-test-locations.mjs
      - run: pnpm lint
      - run: pnpm format:check
      - run: pnpm typecheck
      - run: pnpm knip
      - run: pnpm check:cycles
      - run: pnpm test:unit
      - name: Cancel workflow on failure
        if: failure()
        uses: ./.github/actions/cancel-workflow-on-failure

  int:
    runs-on: ubuntu-latest
    timeout-minutes: 25
    services:
      postgres:
        image: postgres:17-alpine
        env:
          POSTGRES_USER: teqo
          POSTGRES_PASSWORD: teqo
          POSTGRES_DB: teqo_test
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -U teqo"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 12          
    steps:
      - uses: actions/checkout@v5
      - uses: pnpm/action-setup@v6
      - uses: actions/setup-node@v5
        with:
          node-version: 24
          cache: pnpm
      - run: pnpm install --frozen-lockfile
      - run: pnpm migrate
      - run: pnpm db:seed:minimal
      - run: pnpm test:int
      - name: Cancel workflow on failure
        if: failure()
        uses: ./.github/actions/cancel-workflow-on-failure

  build:
    runs-on: ubuntu-latest
    timeout-minutes: 25
    services:
      postgres:
        image: postgres:17-alpine
        env:
          POSTGRES_USER: teqo
          POSTGRES_PASSWORD: teqo
          POSTGRES_DB: teqo_test
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -U teqo"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 12          
    steps:
      - uses: actions/checkout@v5
      - uses: pnpm/action-setup@v6
      - uses: actions/setup-node@v5
        with:
          node-version: 24
          cache: pnpm
      - run: pnpm install --frozen-lockfile
      - name: Build (against the local service database)
        run: pnpm build
      - name: Cancel workflow on failure
        if: failure()
        uses: ./.github/actions/cancel-workflow-on-failure

  e2e:
    runs-on: ubuntu-latest
    timeout-minutes: 40
    # Main always runs the full suite: split it across 2 runners (OPS34), each
    # building its own `.next/e2e` (measured 2026-08-10: build 172s + tests
    # 196s + ~54s fixed → ≈ 5.5 min per shard vs 435s serial). `fail-fast:
    # false` so one shard's failure keeps the other's diagnostics. Keep the
    # [1, 2] / 2 literal in sync with `e2eShardConfig` in
    # scripts/lib/test-affected-core.mjs (ci-pr reads it via the scope job).
    strategy:
      fail-fast: false
      matrix:
        shard: [1, 2]
    env:
      # Explicit CI workers; the local default stays 2 (playwright.config.ts).
      PLAYWRIGHT_WORKERS: 2
    services:
      postgres:
        image: postgres:17-alpine
        env:
          POSTGRES_USER: teqo
          POSTGRES_PASSWORD: teqo
          POSTGRES_DB: teqo_test
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -U teqo"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 12          
    steps:
      - uses: actions/checkout@v5
      - uses: pnpm/action-setup@v6
      - uses: actions/setup-node@v5
        with:
          node-version: 24
          cache: pnpm
      - run: pnpm install --frozen-lockfile
      - name: Install Playwright chromium
        run: pnpm exec playwright install --with-deps chromium
      - run: pnpm migrate
      - run: pnpm db:seed:minimal
      - name: Build for e2e
        run: pnpm build
        env:
          NEXT_DIST_DIR: .next/e2e
      - name: E2E tests (full suite, shard ${{ matrix.shard }})
        # No `--` separator: pnpm would forward it verbatim to playwright and
        # the flag would be parsed as a file pattern ("No tests found").
        run: pnpm test:e2e --shard=${{ matrix.shard }}/2
      - name: Cancel workflow on failure
        if: failure()
        uses: ./.github/actions/cancel-workflow-on-failure

  checks:
    name: checks
    runs-on: ubuntu-latest
    needs: [static, int, build, e2e]
    if: always()
    steps:
      - name: All main verifier checks green
        env:
          NEEDS: ${{ toJSON(needs) }}
        run: |
          set -euo pipefail
          echo "$NEEDS" | jq -e '
            to_entries
            | all(.value.result == "success" or .value.result == "skipped")
          '          

  deploy:
    runs-on: ubuntu-latest
    needs: [checks]
    if: needs.checks.result == 'success'
    # pull → local `vercel build` (pnpm install + Next/Payload build against prod env) → upload.
    timeout-minutes: 35
    outputs:
      stale: ${{ steps.tip.outputs.stale || 'false' }}
      cooldown: ${{ steps.cooldown.outputs.active || 'false' }}
      wait_seconds: ${{ steps.cooldown.outputs.wait_seconds || '0' }}
    env:
      VERCEL_ORG_ID: ${{ secrets.VERCEL_ORG_ID }}
      VERCEL_PROJECT_ID: ${{ secrets.VERCEL_PROJECT_ID }}
      VERCEL_TOKEN: ${{ secrets.VERCEL_TOKEN }}
    steps:
      - uses: actions/checkout@v5
        with:
          fetch-depth: 0
      - name: Guard stale HEAD
        id: tip
        run: |
          set -euo pipefail
          git fetch origin main --quiet
          tip=$(git rev-parse origin/main)
          if [ "$tip" != "$GITHUB_SHA" ]; then
            echo "Skip deploy: origin/main is $tip, this run verified $GITHUB_SHA"
            echo "stale=true" >> "$GITHUB_OUTPUT"
            exit 0
          fi
          echo "stale=false" >> "$GITHUB_OUTPUT"          
      # Cooldown script is plain Node — no pnpm. Disable package-manager-cache
      # here: setup-node@v5 defaults to true and looks for pnpm before action-setup.
      - uses: actions/setup-node@v5
        if: steps.tip.outputs.stale != 'true'
        with:
          node-version: 24
          package-manager-cache: false
      - name: Require Vercel credentials
        if: steps.tip.outputs.stale != 'true'
        run: |
          set -euo pipefail
          missing=()
          [ -z "${VERCEL_TOKEN:-}" ] && missing+=(VERCEL_TOKEN)
          [ -z "${VERCEL_ORG_ID:-}" ] && missing+=(VERCEL_ORG_ID)
          [ -z "${VERCEL_PROJECT_ID:-}" ] && missing+=(VERCEL_PROJECT_ID)
          if [ "${#missing[@]}" -gt 0 ]; then
            echo "::error::Missing repo secrets for gated deploy: ${missing[*]}. Add them under Settings → Secrets, then re-run this workflow."
            exit 1
          fi
          # Fail closed on obvious paste mistakes (must be team_/prj_ from .vercel/project.json).
          case "$VERCEL_ORG_ID" in team_*) ;; *)
            echo "::error::VERCEL_ORG_ID must look like team_… (from .vercel/project.json after vercel link)."
            exit 1
            ;;
          esac
          case "$VERCEL_PROJECT_ID" in prj_*) ;; *)
            echo "::error::VERCEL_PROJECT_ID must look like prj_… (from .vercel/project.json after vercel link)."
            exit 1
            ;;
          esac          
      - name: Check deploy cooldown
        id: cooldown
        if: steps.tip.outputs.stale != 'true'
        run: node scripts/vercel-deploy-cooldown.mjs
      - name: Log deploy deferral
        if: steps.tip.outputs.stale != 'true' && steps.cooldown.outputs.active == 'true'
        run: |
          echo "Deploy deferred: last production deploy is younger than 15 minutes."
          echo "Requeue will retry in ${{ steps.cooldown.outputs.wait_seconds }}s."          
      # `vercel build` shells out to pnpm (packageManager in package.json); without
      # these steps the runner only has npm → spawn pnpm ENOENT.
      - uses: pnpm/action-setup@v6
        if: steps.tip.outputs.stale != 'true' && steps.cooldown.outputs.active != 'true'
      - uses: actions/setup-node@v5
        if: steps.tip.outputs.stale != 'true' && steps.cooldown.outputs.active != 'true'
        with:
          node-version: 24
          cache: pnpm
      - name: Install Vercel CLI
        if: steps.tip.outputs.stale != 'true' && steps.cooldown.outputs.active != 'true'
        run: npm install --global vercel@55
      - name: Deploy production
        if: steps.tip.outputs.stale != 'true' && steps.cooldown.outputs.active != 'true'
        run: |
          set -euo pipefail
          # Workflow-level env points at the CI teqo_test service. Drop it so
          # `vercel build` uses `.vercel/.env.production.local` from `vercel pull`
          # (otherwise Payload migrate hits 127.0.0.1:5432 → ECONNREFUSED).
          unset DATABASE_URL PAYLOAD_SECRET NEXT_PUBLIC_SITE_URL
          # Canonical CI link (Vercel KB): env VERCEL_*_ID + pull → build → deploy --prebuilt.
          # "Could not retrieve Project Settings" usually means bad/expired token or wrong IDs (403).
          vercel pull --yes --environment=production --token="$VERCEL_TOKEN"
          vercel build --prod --token="$VERCEL_TOKEN"
          # stdout is always the deployment URL (CLI contract). Capture it — do not
          # pipe the whole CLI log or the exit code / URL get lost.
          deploy_url=$(vercel deploy --prebuilt --prod --archive=tgz --token="$VERCEL_TOKEN")
          echo "Deployed: $deploy_url"
          # Git auto-deploy OFF is intentional. If "Auto-assign Custom Production
          # Domains" is also OFF, --prod only stages *.vercel.app and leaves
          # pt.jorgesolla.com.br on the previous Current — promote + verify here.
          node scripts/vercel-ensure-production-alias.mjs "$deploy_url"
          # Docs: promote staged production, then alias (Git Integration is OFF by design).
          vercel promote "$deploy_url" --token="$VERCEL_TOKEN" --scope="$VERCEL_ORG_ID" || true
          # `--yes` is only valid for `alias rm`, not `alias set` (CLI 55).
          vercel alias set "$deploy_url" pt.jorgesolla.com.br --token="$VERCEL_TOKEN" --scope="$VERCEL_ORG_ID"          

  requeue:
    runs-on: ubuntu-latest
    needs: [checks, deploy]
    if: always()
    timeout-minutes: 40
    permissions:
      actions: write
      contents: read
    steps:
      - uses: actions/checkout@v5
        with:
          fetch-depth: 0
      - name: Re-dispatch if main advanced or deploy deferred
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          GH_REPO: ${{ github.repository }}
          DEPLOY_RESULT: ${{ needs.deploy.result }}
          DEPLOY_COOLDOWN: ${{ needs.deploy.outputs.cooldown }}
          DEPLOY_WAIT_SECONDS: ${{ needs.deploy.outputs.wait_seconds }}
        run: |
          set -euo pipefail
          git fetch origin main --quiet
          tip=$(git rev-parse origin/main)
          if [ "$tip" != "$GITHUB_SHA" ]; then
            echo "origin/main moved to $tip (verified $GITHUB_SHA) — requeue ci.yml"
            gh workflow run ci.yml --ref main
            exit 0
          fi
          if [ "${DEPLOY_RESULT:-}" != "success" ]; then
            echo "Deploy job did not succeed (${DEPLOY_RESULT:-skipped}) — idle"
            exit 0
          fi
          if [ "${DEPLOY_COOLDOWN:-}" = "true" ]; then
            wait="${DEPLOY_WAIT_SECONDS:-0}"
            echo "Deploy deferred by cooldown — waiting ${wait}s then requeue ci.yml"
            sleep "$wait"
            git fetch origin main --quiet
            tip=$(git rev-parse origin/main)
            if [ "$tip" != "$GITHUB_SHA" ]; then
              echo "main advanced during cooldown wait ($tip) — requeue for new tip"
            else
              echo "Cooldown elapsed for $GITHUB_SHA — requeue ci.yml"
            fi
            gh workflow run ci.yml --ref main
            exit 0
          fi
          echo "HEAD still $GITHUB_SHA — idle"