Ruview/.github/workflows/firmware-qemu.yml

name: Firmware QEMU Tests (ADR-061)

on:
  push:
    paths:
      - 'firmware/**'
      - 'scripts/qemu-esp32s3-test.sh'
      - 'scripts/validate_qemu_output.py'
      - 'scripts/generate_nvs_matrix.py'
      - 'scripts/qemu_swarm.py'
      - 'scripts/swarm_health.py'
      - 'scripts/swarm_presets/**'
      - '.github/workflows/firmware-qemu.yml'
  pull_request:
    paths:
      - 'firmware/**'
      - 'scripts/qemu-esp32s3-test.sh'
      - 'scripts/validate_qemu_output.py'
      - 'scripts/generate_nvs_matrix.py'
      - 'scripts/qemu_swarm.py'
      - 'scripts/swarm_health.py'
      - 'scripts/swarm_presets/**'
      - '.github/workflows/firmware-qemu.yml'

env:
  IDF_VERSION: "v5.4"
  QEMU_REPO: "https://github.com/espressif/qemu.git"
  QEMU_BRANCH: "esp-develop"

jobs:
  build-qemu:
    name: Build Espressif QEMU
    runs-on: ubuntu-latest
    steps:
      - name: Cache QEMU build
        id: cache-qemu
        uses: actions/cache@v4
        with:
          path: /opt/qemu-esp32
          # Include date component so cache refreshes monthly when branch updates
          key: qemu-esp32s3-${{ env.QEMU_BRANCH }}-v5
          restore-keys: |
            qemu-esp32s3-${{ env.QEMU_BRANCH }}-

      - name: Install QEMU build dependencies
        if: steps.cache-qemu.outputs.cache-hit != 'true'
        run: |
          sudo apt-get update
          sudo apt-get install -y \
            git build-essential ninja-build pkg-config \
            libglib2.0-dev libpixman-1-dev libslirp-dev \
            libgcrypt20-dev \
            python3 python3-venv

      - name: Clone and build Espressif QEMU
        if: steps.cache-qemu.outputs.cache-hit != 'true'
        run: |
          git clone --depth 1 -b "$QEMU_BRANCH" "$QEMU_REPO" /tmp/qemu-esp
          cd /tmp/qemu-esp
          mkdir build && cd build
          ../configure \
            --target-list=xtensa-softmmu \
            --prefix=/opt/qemu-esp32 \
            --enable-slirp \
            --disable-werror
          ninja -j$(nproc)
          ninja install

      - name: Verify QEMU binary
        run: |
          file_size() { stat -c%s "$1" 2>/dev/null || stat -f%z "$1" 2>/dev/null || wc -c < "$1"; }
          /opt/qemu-esp32/bin/qemu-system-xtensa --version
          echo "QEMU binary size: $(file_size /opt/qemu-esp32/bin/qemu-system-xtensa) bytes"

      - name: Upload QEMU artifact
        uses: actions/upload-artifact@v4
        with:
          name: qemu-esp32
          path: /opt/qemu-esp32/
          retention-days: 7

  qemu-test:
    name: QEMU Test (${{ matrix.nvs_config }})
    needs: build-qemu
    runs-on: ubuntu-latest
    container:
      image: espressif/idf:v5.4

    strategy:
      fail-fast: false
      matrix:
        nvs_config:
          - default
          - full-adr060
          - edge-tier0
          - edge-tier1
          - tdm-3node
          - boundary-max
          - boundary-min

    steps:
      - uses: actions/checkout@v4

      - name: Download QEMU artifact
        uses: actions/download-artifact@v4
        with:
          name: qemu-esp32
          path: /opt/qemu-esp32

      - name: Make QEMU executable
        run: chmod +x /opt/qemu-esp32/bin/qemu-system-xtensa

      - name: Verify QEMU works
        run: /opt/qemu-esp32/bin/qemu-system-xtensa --version

      - name: Install Python dependencies
        run: |
          . $IDF_PATH/export.sh
          pip install esptool esp-idf-nvs-partition-gen

      - name: Set target ESP32-S3
        working-directory: firmware/esp32-csi-node
        run: |
          . $IDF_PATH/export.sh
          idf.py set-target esp32s3

      - name: Build firmware (mock CSI mode)
        working-directory: firmware/esp32-csi-node
        run: |
          . $IDF_PATH/export.sh
          idf.py \
            -D SDKCONFIG_DEFAULTS="sdkconfig.defaults;sdkconfig.qemu" \
            build

      - name: Generate NVS matrix
        run: |
          . $IDF_PATH/export.sh
          python3 scripts/generate_nvs_matrix.py \
            --output-dir firmware/esp32-csi-node/build/nvs_matrix \
            --only ${{ matrix.nvs_config }}

      - name: Create merged flash image
        working-directory: firmware/esp32-csi-node
        run: |
          . $IDF_PATH/export.sh

          # Determine merge_bin arguments
          OTA_ARGS=""
          if [ -f build/ota_data_initial.bin ]; then
            OTA_ARGS="0xf000 build/ota_data_initial.bin"
          fi

          python3 -m esptool --chip esp32s3 merge_bin \
            -o build/qemu_flash.bin \
            --flash_mode dio --flash_freq 80m --flash_size 8MB \
            --fill-flash-size 8MB \
            0x0     build/bootloader/bootloader.bin \
            0x8000  build/partition_table/partition-table.bin \
            $OTA_ARGS \
            0x20000 build/esp32-csi-node.bin

          file_size() { stat -c%s "$1" 2>/dev/null || stat -f%z "$1" 2>/dev/null || wc -c < "$1"; }
          echo "Flash image size: $(file_size build/qemu_flash.bin) bytes"

      - name: Inject NVS partition
        if: matrix.nvs_config != 'default'
        working-directory: firmware/esp32-csi-node
        run: |
          NVS_BIN="build/nvs_matrix/nvs_${{ matrix.nvs_config }}.bin"
          if [ -f "$NVS_BIN" ]; then
            file_size() { stat -c%s "$1" 2>/dev/null || stat -f%z "$1" 2>/dev/null || wc -c < "$1"; }
            echo "Injecting NVS: $NVS_BIN ($(file_size "$NVS_BIN") bytes)"
            dd if="$NVS_BIN" of=build/qemu_flash.bin \
              bs=1 seek=$((0x9000)) conv=notrunc 2>/dev/null
          else
            echo "WARNING: NVS binary not found: $NVS_BIN"
          fi

      - name: Run QEMU smoke test
        env:
          QEMU_PATH: /opt/qemu-esp32/bin/qemu-system-xtensa
          QEMU_TIMEOUT: "90"
        run: |
          echo "Starting QEMU (timeout: ${QEMU_TIMEOUT}s)..."

          timeout "$QEMU_TIMEOUT" "$QEMU_PATH" \
            -machine esp32s3 \
            -nographic \
            -drive file=firmware/esp32-csi-node/build/qemu_flash.bin,if=mtd,format=raw \
            -serial mon:stdio \
            -nic user,model=open_eth,net=10.0.2.0/24 \
            -no-reboot \
            2>&1 | tee firmware/esp32-csi-node/build/qemu_output.log || true

          echo "QEMU finished. Log size: $(wc -l < firmware/esp32-csi-node/build/qemu_output.log) lines"

      - name: Validate QEMU output
        run: |
          python3 scripts/validate_qemu_output.py \
            firmware/esp32-csi-node/build/qemu_output.log

      - name: Upload test logs
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: qemu-logs-${{ matrix.nvs_config }}
          path: |
            firmware/esp32-csi-node/build/qemu_output.log
            firmware/esp32-csi-node/build/nvs_matrix/
          retention-days: 14

  fuzz-test:
    name: Fuzz Testing (ADR-061 Layer 6)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Install clang
        run: |
          sudo apt-get update
          sudo apt-get install -y clang

      - name: Build fuzz targets
        working-directory: firmware/esp32-csi-node/test
        run: make all CC=clang

      - name: Run serialize fuzzer (60s)
        working-directory: firmware/esp32-csi-node/test
        run: make run_serialize FUZZ_DURATION=60 || echo "FUZZER_CRASH=serialize" >> "$GITHUB_ENV"

      - name: Run edge enqueue fuzzer (60s)
        working-directory: firmware/esp32-csi-node/test
        run: make run_edge FUZZ_DURATION=60 || echo "FUZZER_CRASH=edge" >> "$GITHUB_ENV"

      - name: Run NVS config fuzzer (60s)
        working-directory: firmware/esp32-csi-node/test
        run: make run_nvs FUZZ_DURATION=60 || echo "FUZZER_CRASH=nvs" >> "$GITHUB_ENV"

      - name: Check for crashes
        working-directory: firmware/esp32-csi-node/test
        run: |
          CRASHES=$(find . -type f \( -name "crash-*" -o -name "oom-*" -o -name "timeout-*" \) 2>/dev/null | wc -l)
          echo "Crash artifacts found: $CRASHES"
          if [ "$CRASHES" -gt 0 ] || [ -n "${FUZZER_CRASH:-}" ]; then
            echo "::error::Fuzzer found $CRASHES crash/oom/timeout artifacts. FUZZER_CRASH=${FUZZER_CRASH:-none}"
            ls -la crash-* oom-* timeout-* 2>/dev/null
            exit 1
          fi

      - name: Upload fuzz artifacts
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: fuzz-crashes
          path: |
            firmware/esp32-csi-node/test/crash-*
            firmware/esp32-csi-node/test/oom-*
            firmware/esp32-csi-node/test/timeout-*
          retention-days: 30

  nvs-matrix-validate:
    name: NVS Matrix Generation
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Install NVS generator
        run: pip install esp-idf-nvs-partition-gen

      - name: Generate all 14 NVS configs
        run: |
          python3 scripts/generate_nvs_matrix.py \
            --output-dir build/nvs_matrix

      - name: Verify all binaries generated
        run: |
          EXPECTED=14
          ACTUAL=$(find build/nvs_matrix -type f -name "nvs_*.bin" 2>/dev/null | wc -l)
          echo "Generated $ACTUAL / $EXPECTED NVS binaries"
          ls -la build/nvs_matrix/

          if [ "$ACTUAL" -lt "$EXPECTED" ]; then
            echo "::error::Only $ACTUAL of $EXPECTED NVS binaries generated"
            exit 1
          fi

      - name: Verify binary sizes
        run: |
          file_size() { stat -c%s "$1" 2>/dev/null || stat -f%z "$1" 2>/dev/null || wc -c < "$1"; }
          for f in build/nvs_matrix/nvs_*.bin; do
            SIZE=$(file_size "$f")
            if [ "$SIZE" -ne 24576 ]; then
              echo "::error::$f has unexpected size $SIZE (expected 24576)"
              exit 1
            fi
            echo "  OK: $(basename $f) ($SIZE bytes)"
          done

  # ---------------------------------------------------------------------------
  # ADR-062: QEMU Swarm Configurator Test
  #
  # Runs a lightweight 3-node swarm (ci_matrix preset) under QEMU to validate
  # multi-node orchestration, TDM slot coordination, and swarm-level health
  # assertions. Uses the pre-built QEMU binary from the build-qemu job and the
  # firmware built by qemu-test.
  #
  # The CI runner is non-root, so TAP bridge networking is unavailable.
  # The orchestrator (qemu_swarm.py) detects this and falls back to SLIRP
  # user-mode networking, which is sufficient for the ci_matrix preset.
  # ---------------------------------------------------------------------------
  swarm-test:
    name: Swarm Test (ADR-062)
    needs: [build-qemu]
    runs-on: ubuntu-latest
    container:
      image: espressif/idf:v5.4

    steps:
      - uses: actions/checkout@v4

      - name: Download QEMU artifact
        uses: actions/download-artifact@v4
        with:
          name: qemu-esp32
          path: /opt/qemu-esp32

      - name: Make QEMU executable
        run: chmod +x /opt/qemu-esp32/bin/qemu-system-xtensa

      - name: Install Python dependencies
        run: |
          . $IDF_PATH/export.sh
          pip install pyyaml esptool esp-idf-nvs-partition-gen

      - name: Build firmware for swarm
        working-directory: firmware/esp32-csi-node
        run: |
          . $IDF_PATH/export.sh
          idf.py set-target esp32s3
          idf.py -D SDKCONFIG_DEFAULTS="sdkconfig.defaults;sdkconfig.qemu" build
          python3 -m esptool --chip esp32s3 merge_bin \
            -o build/qemu_flash.bin \
            --flash_mode dio --flash_freq 80m --flash_size 8MB \
            --fill-flash-size 8MB \
            0x0     build/bootloader/bootloader.bin \
            0x8000  build/partition_table/partition-table.bin \
            0x20000 build/esp32-csi-node.bin

      - name: Run swarm smoke test
        run: |
          . $IDF_PATH/export.sh
          EXIT_CODE=0
          python3 scripts/qemu_swarm.py --preset ci_matrix \
            --qemu-path /opt/qemu-esp32/bin/qemu-system-xtensa \
            --output-dir build/swarm-results || EXIT_CODE=$?
          # Exit 0=PASS, 1=WARN (acceptable in CI without real hardware)
          if [ "$EXIT_CODE" -gt 1 ]; then
            echo "Swarm test failed with exit code $EXIT_CODE"
            exit "$EXIT_CODE"
          fi
        timeout-minutes: 10

      - name: Upload swarm results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: swarm-results
          path: |
            build/swarm-results/
          retention-days: 14