name: CI/CD Pipeline

on:
  push:
    branches: [master]
  pull_request:
    branches: [master]
  workflow_dispatch:

concurrency:
  group: ci-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
  STAGING_COMPOSE_FILE: docker-compose.staging.yml
  STAGING_SERVICE: staging-go
  STAGING_CONTAINER: corescope-staging-go

# Pipeline (sequential, fail-fast):
#   go-test → e2e-test → build → deploy → publish
#   PRs stop after build. Master continues to deploy + publish.

jobs:
  # ───────────────────────────────────────────────────────────────
  # 1. Go Build & Test
  # ───────────────────────────────────────────────────────────────
  go-test:
    name: "✅ Go Build & Test"
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v5
        with:
          fetch-depth: 0

      - name: Clean Go module cache
        run: rm -rf ~/go/pkg/mod 2>/dev/null || true

      - name: Set up Go 1.22
        uses: actions/setup-go@v6
        with:
          go-version: '1.22'
          cache-dependency-path: |
            cmd/server/go.sum
            cmd/ingestor/go.sum

      - name: Build and test Go server (with coverage)
        run: |
          set -e -o pipefail
          cd cmd/server
          go build .
          go test -coverprofile=server-coverage.out ./... 2>&1 | tee server-test.log
          echo "--- Go Server Coverage ---"
          go tool cover -func=server-coverage.out | tail -1

      - name: Build and test Go ingestor (with coverage)
        run: |
          set -e -o pipefail
          cd cmd/ingestor
          go build .
          go test -coverprofile=ingestor-coverage.out ./... 2>&1 | tee ingestor-test.log
          echo "--- Go Ingestor Coverage ---"
          go tool cover -func=ingestor-coverage.out | tail -1

      - name: Verify proto syntax
        run: |
          set -e
          sudo apt-get update -qq
          sudo apt-get install -y protobuf-compiler
          for proto in proto/*.proto; do
            echo "  ✓ $(basename "$proto")"
            protoc --proto_path=proto --descriptor_set_out=/dev/null "$proto"
          done
          echo "✅ All .proto files are syntactically valid"

      - name: Generate Go coverage badges
        if: success()
        run: |
          mkdir -p .badges

          SERVER_COV="0"
          if [ -f cmd/server/server-coverage.out ]; then
            SERVER_COV=$(cd cmd/server && go tool cover -func=server-coverage.out | tail -1 | grep -oP '[\d.]+(?=%)')
          fi
          SERVER_COLOR="red"
          if [ "$(echo "$SERVER_COV >= 80" | bc -l 2>/dev/null)" = "1" ]; then SERVER_COLOR="green"
          elif [ "$(echo "$SERVER_COV >= 60" | bc -l 2>/dev/null)" = "1" ]; then SERVER_COLOR="yellow"; fi
          echo "{\"schemaVersion\":1,\"label\":\"go server coverage\",\"message\":\"${SERVER_COV}%\",\"color\":\"${SERVER_COLOR}\"}" > .badges/go-server-coverage.json

          INGESTOR_COV="0"
          if [ -f cmd/ingestor/ingestor-coverage.out ]; then
            INGESTOR_COV=$(cd cmd/ingestor && go tool cover -func=ingestor-coverage.out | tail -1 | grep -oP '[\d.]+(?=%)')
          fi
          INGESTOR_COLOR="red"
          if [ "$(echo "$INGESTOR_COV >= 80" | bc -l 2>/dev/null)" = "1" ]; then INGESTOR_COLOR="green"
          elif [ "$(echo "$INGESTOR_COV >= 60" | bc -l 2>/dev/null)" = "1" ]; then INGESTOR_COLOR="yellow"; fi
          echo "{\"schemaVersion\":1,\"label\":\"go ingestor coverage\",\"message\":\"${INGESTOR_COV}%\",\"color\":\"${INGESTOR_COLOR}\"}" > .badges/go-ingestor-coverage.json

          echo "## Go Coverage" >> $GITHUB_STEP_SUMMARY
          echo "| Module | Coverage |" >> $GITHUB_STEP_SUMMARY
          echo "|--------|----------|" >> $GITHUB_STEP_SUMMARY
          echo "| Server | ${SERVER_COV}% |" >> $GITHUB_STEP_SUMMARY
          echo "| Ingestor | ${INGESTOR_COV}% |" >> $GITHUB_STEP_SUMMARY

      - name: Upload Go coverage badges
        if: success()
        uses: actions/upload-artifact@v6
        with:
          name: go-badges
          path: .badges/go-*.json
          retention-days: 1
          if-no-files-found: ignore
          include-hidden-files: true

  # ───────────────────────────────────────────────────────────────
  # 2. Playwright E2E Tests (against Go server with fixture DB)
  # ───────────────────────────────────────────────────────────────
  e2e-test:
    name: "🎭 Playwright E2E Tests"
    needs: [go-test]
    runs-on: [self-hosted, Linux]
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout code
        uses: actions/checkout@v5
        with:
          fetch-depth: 0

      - name: Free disk space
        run: |
          # Prune old runner diagnostic logs (can accumulate 50MB+)
          find ~/actions-runner/_diag/ -name '*.log' -mtime +3 -delete 2>/dev/null || true
          # Show available disk space
          df -h / | tail -1

      - name: Set up Node.js 22
        uses: actions/setup-node@v5
        with:
          node-version: '22'

      - name: Clean Go module cache
        run: rm -rf ~/go/pkg/mod 2>/dev/null || true

      - name: Set up Go 1.22
        uses: actions/setup-go@v6
        with:
          go-version: '1.22'
          cache-dependency-path: cmd/server/go.sum

      - name: Build Go server
        run: |
          cd cmd/server
          go build -o ../../corescope-server .
          echo "Go server built successfully"

      - name: Install npm dependencies
        run: npm ci --production=false

      - name: Install Playwright browser
        run: |
          npx playwright install chromium 2>/dev/null || true
          npx playwright install-deps chromium 2>/dev/null || true

      - name: Instrument frontend JS for coverage
        run: sh scripts/instrument-frontend.sh

      - name: Start Go server with fixture DB
        run: |
          fuser -k 13581/tcp 2>/dev/null || true
          sleep 1
          ./corescope-server -port 13581 -db test-fixtures/e2e-fixture.db -public public-instrumented &
          echo $! > .server.pid
          for i in $(seq 1 30); do
            if curl -sf http://localhost:13581/api/stats > /dev/null 2>&1; then
              echo "Server ready after ${i}s"
              break
            fi
            if [ "$i" -eq 30 ]; then
              echo "Server failed to start within 30s"
              exit 1
            fi
            sleep 1
          done

      - name: Run Playwright E2E tests (fail-fast)
        run: |
          BASE_URL=http://localhost:13581 node test-e2e-playwright.js 2>&1 | tee e2e-output.txt

      - name: Collect frontend coverage (parallel)
        if: success() && github.event_name == 'push'
        run: |
          BASE_URL=http://localhost:13581 node scripts/collect-frontend-coverage.js 2>&1 | tee fe-coverage-output.txt || true

      - name: Generate frontend coverage badges
        if: success()
        run: |
          E2E_PASS=$(grep -oP '[0-9]+(?=/)' e2e-output.txt | tail -1 || echo "0")

          mkdir -p .badges
          if [ -f .nyc_output/frontend-coverage.json ] || [ -f .nyc_output/e2e-coverage.json ]; then
            npx nyc report --reporter=text-summary --reporter=text 2>&1 | tee fe-report.txt
            FE_COVERAGE=$(grep 'Statements' fe-report.txt | head -1 | grep -oP '[\d.]+(?=%)' || echo "0")
            FE_COVERAGE=${FE_COVERAGE:-0}
            FE_COLOR="red"
            [ "$(echo "$FE_COVERAGE > 50" | bc -l 2>/dev/null)" = "1" ] && FE_COLOR="yellow"
            [ "$(echo "$FE_COVERAGE > 80" | bc -l 2>/dev/null)" = "1" ] && FE_COLOR="brightgreen"
            echo "{\"schemaVersion\":1,\"label\":\"frontend coverage\",\"message\":\"${FE_COVERAGE}%\",\"color\":\"${FE_COLOR}\"}" > .badges/frontend-coverage.json
            echo "## Frontend: ${FE_COVERAGE}% coverage" >> $GITHUB_STEP_SUMMARY
          fi
          echo "{\"schemaVersion\":1,\"label\":\"e2e tests\",\"message\":\"${E2E_PASS:-0} passed\",\"color\":\"brightgreen\"}" > .badges/e2e-tests.json

      - name: Stop test server
        if: always()
        run: |
          if [ -f .server.pid ]; then
            kill $(cat .server.pid) 2>/dev/null || true
            rm -f .server.pid
          fi

      - name: Upload E2E badges
        if: success()
        uses: actions/upload-artifact@v6
        with:
          name: e2e-badges
          path: .badges/
          retention-days: 1
          if-no-files-found: ignore
          include-hidden-files: true

  # ───────────────────────────────────────────────────────────────
  # 3. Build Docker Image
  # ───────────────────────────────────────────────────────────────
  build:
    name: "🏗️ Build Docker Image"
    needs: [e2e-test]
    runs-on: [self-hosted, meshcore-vm]
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Set up Node.js 22
        uses: actions/setup-node@v5
        with:
          node-version: '22'

      - name: Free disk space
        run: |
          docker system prune -af 2>/dev/null || true
          docker builder prune -af 2>/dev/null || true
          df -h /

      - name: Build Go Docker image
        run: |
          echo "${GITHUB_SHA::7}" > .git-commit
          APP_VERSION=$(node -p "require('./package.json').version") \
          GIT_COMMIT="${GITHUB_SHA::7}" \
          APP_VERSION=$(grep -oP 'APP_VERSION:-\K[^}]+' docker-compose.yml | head -1 || echo "3.0.0")
          GIT_COMMIT=$(git rev-parse --short HEAD)
          BUILD_TIME=$(date -u '+%Y-%m-%dT%H:%M:%SZ')
          export APP_VERSION GIT_COMMIT BUILD_TIME
          docker compose -f "$STAGING_COMPOSE_FILE" -p corescope-staging build "$STAGING_SERVICE"
          echo "Built Go staging image ✅"

  # ───────────────────────────────────────────────────────────────
  # 4. Deploy Staging (master only)
  # ───────────────────────────────────────────────────────────────
  deploy:
    name: "🚀 Deploy Staging"
    if: github.event_name == 'push'
    needs: [build]
    runs-on: [self-hosted, meshcore-vm]
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Deploy staging
        run: |
          # Stop old container and release memory
          docker compose -f "$STAGING_COMPOSE_FILE" -p corescope-staging down --timeout 30 2>/dev/null || true

          # Wait for container to be fully gone and OS to reclaim memory (3GB limit)
          for i in $(seq 1 15); do
            if ! docker ps -a --format '{{.Names}}' | grep -q 'corescope-staging-go'; then
              break
            fi
            sleep 1
          done
          sleep 5  # extra pause for OS memory reclaim

          # Ensure staging data dir exists (config.json lives here, no separate file mount)
          STAGING_DATA="${STAGING_DATA_DIR:-$HOME/meshcore-staging-data}"
          mkdir -p "$STAGING_DATA"

          # If no config exists, copy the example (CI doesn't have a real prod config)
          if [ ! -f "$STAGING_DATA/config.json" ]; then
            echo "Staging config missing — copying config.example.json"
            cp config.example.json "$STAGING_DATA/config.json" 2>/dev/null || true
          fi

          docker compose -f "$STAGING_COMPOSE_FILE" -p corescope-staging up -d staging-go

      - name: Healthcheck staging container
        run: |
          for i in $(seq 1 120); do
            HEALTH=$(docker inspect corescope-staging-go --format '{{.State.Health.Status}}' 2>/dev/null || echo "starting")
            if [ "$HEALTH" = "healthy" ]; then
              echo "Staging healthy after ${i}s"
              break
            fi
            if [ "$i" -eq 120 ]; then
              echo "Staging failed health check after 120s"
              docker logs corescope-staging-go --tail 50
              exit 1
            fi
            sleep 1
          done

      - name: Smoke test staging API
        run: |
          if curl -sf http://localhost:82/api/stats | grep -q engine; then
            echo "Staging verified — engine field present ✅"
          else
            echo "Staging /api/stats did not return engine field"
            exit 1
          fi

      - name: Clean up old Docker images
        if: always()
        run: |
          # Remove dangling images and images older than 24h (keeps current build)
          echo "--- Docker disk usage before cleanup ---"
          docker system df
          docker image prune -af --filter "until=24h" 2>/dev/null || true
          docker builder prune -f --keep-storage=1GB 2>/dev/null || true
          echo "--- Docker disk usage after cleanup ---"
          docker system df

  # ───────────────────────────────────────────────────────────────
  # 5. Publish Badges & Summary (master only)
  # ───────────────────────────────────────────────────────────────
  publish:
    name: "📝 Publish Badges & Summary"
    if: github.event_name == 'push'
    needs: [deploy]
    runs-on: [self-hosted, Linux]
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Download Go coverage badges
        continue-on-error: true
        uses: actions/download-artifact@v6
        with:
          name: go-badges
          path: .badges/

      - name: Download E2E badges
        continue-on-error: true
        uses: actions/download-artifact@v6
        with:
          name: e2e-badges
          path: .badges/

      - name: Publish coverage badges to repo
        continue-on-error: true
        env:
          GH_TOKEN: ${{ secrets.BADGE_PUSH_TOKEN }}
        run: |
          # GITHUB_TOKEN cannot push to protected branches (required status checks).
          # Use admin PAT (BADGE_PUSH_TOKEN) via GitHub Contents API instead.
          for badge in .badges/*.json; do
            FILENAME=$(basename "$badge")
            FILEPATH=".badges/$FILENAME"
            CONTENT=$(base64 -w0 "$badge")
            CURRENT_SHA=$(gh api "repos/${{ github.repository }}/contents/$FILEPATH" --jq '.sha' 2>/dev/null || echo "")
            if [ -n "$CURRENT_SHA" ]; then
              gh api "repos/${{ github.repository }}/contents/$FILEPATH" \
                -X PUT \
                -f message="ci: update $FILENAME [skip ci]" \
                -f content="$CONTENT" \
                -f sha="$CURRENT_SHA" \
                -f branch="master" \
                --silent 2>&1 || echo "Failed to update $FILENAME"
            else
              gh api "repos/${{ github.repository }}/contents/$FILEPATH" \
                -X PUT \
                -f message="ci: update $FILENAME [skip ci]" \
                -f content="$CONTENT" \
                -f branch="master" \
                --silent 2>&1 || echo "Failed to create $FILENAME"
            fi
          done
          echo "Badge publish complete"

      - name: Post deployment summary
        run: |
          echo "## Staging Deployed ✓" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "**Commit:** \`$(git rev-parse --short HEAD)\` — $(git log -1 --format=%s)" >> $GITHUB_STEP_SUMMARY