name: CI

# Stream 11 verification pipeline.
#
# Three parallel jobs:
#   * cpp-tests      — builds nisps host C++ tests, builds nisps.wasm, runs
#                      the parity check, runs the lint script, and reports
#                      per-engine throughput on both host targets.
#   * manifold-tests — typechecks the React manifold app, runs bun unit
#                      tests, builds the production bundle, runs Playwright
#                      e2e tests.
#
#   * firmware-build — compiles three representative PlatformIO envs for the
#                      RP2350 target.
#
# Firmware entered CI for the first time with the Phase 4 PlatformIO migration
# (plan §5, S9). It was previously excluded because arduino-cli + the rp2040
# board package cost ~2 minutes per run for "low verification value" — an
# assessment that did not survive contact: the SelfTest variant sat broken for
# an unknown period, calling a DisplayDriver method that did not exist at the
# pinned memllib commit, and nothing noticed because nothing built it. PIO's
# toolchain caches cleanly, so the cost is now a cache restore.

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

jobs:
  cpp-tests:
    name: C++ tests + WASM + parity + lint
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install build deps
        run: |
          sudo apt-get update
          sudo apt-get install -y --no-install-recommends \
            cmake ninja-build build-essential perl

      - name: Setup Emscripten
        # mymindstorm/setup-emsdk caches the SDK between runs. Pin to a
        # known-working version; bump deliberately.
        uses: mymindstorm/setup-emsdk@v14
        with:
          version: '3.1.69'
          actions-cache-folder: 'emsdk-cache'

      - name: Verify emcc
        run: emcc --version

      - name: Setup Node (for parity_wasm.mjs)
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Build C++ tests + run ctest
        env:
          # CI is non-interactive — turn off colour for log readability.
          CMAKE_BUILD_PARALLEL_LEVEL: '4'
        run: bash scripts/build-cpp-tests.sh

      # Freshness gate. manifold/public/nisps.{js,wasm} are TRACKED artifacts:
      # the VPS webhook builds only manifold/, so vite copies whatever is
      # committed into the production bundle. Prove the committed artifact
      # still agrees with the C++ we just built, BEFORE the rebuild below
      # overwrites it. A stale commit fails here instead of silently shipping.
      - name: WASM freshness gate (committed artifact vs native)
        env:
          NISPS_PARITY_NO_BUILD: '1'
        run: bash scripts/parity-check.sh

      - name: Build WASM
        # setup-emsdk puts emcc on PATH; build-wasm.sh picks it up via
        # `command -v emcc`. No EMCC override needed.
        run: bash scripts/build-wasm.sh

      - name: Parity check (native vs WASM)
        env:
          NISPS_PARITY_NO_BUILD: '1'  # we just built; don't re-build
        run: bash scripts/parity-check.sh

      - name: Lint
        run: bash scripts/lint-cpp.sh

      # Throughput is reported, not asserted — the same call the firmware
      # flash/RAM step makes below, for a stronger reason: a wall-clock
      # threshold on a shared runner is either slack enough to be meaningless
      # or tight enough to fail on someone else's noisy neighbour. What this
      # buys is (a) a per-commit ns/sample + realtime-factor record in the log,
      # where a 2-3x regression — the failure mode ALIGNMENT defect 5 names —
      # is unmissable even at runner noise levels, (b) proof the bench still
      # builds and runs on BOTH targets, and (c) the wasm/native ratio.
      # Runner noise makes small moves unreadable; for a real comparison run
      # scripts/bench-engines.sh --compare locally.
      - name: Engine throughput report (native + WASM, not asserted)
        run: bash scripts/bench-engines.sh --target-ms 60

      - name: Upload parity blobs on failure
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: parity-blobs
          path: |
            tests/cpp/parity_native.bin
            tests/cpp/parity_wasm.bin
          if-no-files-found: ignore
          retention-days: 7

  manifold-tests:
    name: Manifold typecheck + unit + e2e
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Setup Bun
        uses: oven-sh/setup-bun@v2
        with:
          bun-version: latest

      # Enforces the "schema changes ship with regenerated C++ AND TypeScript
      # in the same change" rule. Regenerate from schemas/ and fail if the
      # committed outputs differ; then run the codegen golden test.
      - name: Codegen is committed and idempotent
        run: |
          cd codegen
          bun install --frozen-lockfile
          bun run generate.ts
          bun run generate-midi-devices.ts
          bun run tests/golden_test.ts
          # The schemas' per-voice-space `curve` declarations are DESCRIPTIVE
          # of nisps/engines/*.hpp. Prove they still describe it.
          bun run tests/curve_drift_test.ts
          cd ..
          GEN_DIRS="nisps/modes/generated nisps/midi/generated nisps/ml/generated \
                    manifold/src/modes/generated manifold/src/midi-devices/generated"
          git add -N $GEN_DIRS
          if ! git diff --exit-code -- $GEN_DIRS; then
            echo "::error::Generated outputs are stale. Run codegen and commit the result." >&2
            exit 1
          fi

      - name: Install manifold deps
        working-directory: manifold
        run: bun install --frozen-lockfile

      - name: Typecheck
        working-directory: manifold
        run: bun run typecheck

      - name: Unit tests
        working-directory: manifold
        run: bun run test

      - name: Build manifold bundle
        working-directory: manifold
        run: bun run build

      - name: Install Playwright browsers
        working-directory: manifold
        run: bunx playwright install --with-deps chromium

      - name: Run Playwright tests
        working-directory: manifold
        run: bunx playwright test

      - name: Upload Playwright report on failure
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: playwright-report
          path: manifold/playwright-report/
          retention-days: 7

  firmware-build:
    name: Firmware (RP2350, PlatformIO)
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      # The platform wrapper and the arduino-pico framework are fetched from
      # git and total ~1-2 GB. Key on platformio.ini because that file pins
      # both versions — change a pin, get a fresh toolchain.
      - name: Cache PlatformIO toolchain
        uses: actions/cache@v4
        with:
          path: |
            ~/.platformio
            ~/.cache/pip
          key: pio-${{ runner.os }}-${{ hashFiles('firmware/MEMLNaut-NISPS/platformio.ini') }}
          restore-keys: pio-${{ runner.os }}-

      - name: Install PlatformIO
        run: pip install --upgrade platformio

      # Four representative envs rather than all sixteen: they differ mostly in
      # which mode type is instantiated, so a compile break is usually common to
      # all. slpworkshop is the shipped default, pafsynth is the heaviest RAM
      # user, selftest takes the separate NISPS_SELFTEST fork through main.cpp
      # (the one that broke unnoticed before), and soundanalysismidi is the ONLY
      # microphone variant — the sole mode whose DriverConfig differs from its
      # engine's, via an on_driver_config() override. Drop it and the mic path
      # stops being compiled by anything.
      - name: Build representative firmware variants
        working-directory: firmware/MEMLNaut-NISPS
        run: pio run -e slpworkshop -e pafsynth -e selftest -e soundanalysismidi

      # Sizes are reported, not asserted. A threshold would either be slack
      # enough to be meaningless or tight enough to fail on unrelated work;
      # this puts the numbers in the log so a jump is visible in review.
      # Flash = .text + .rodata, RAM = .data + .bss + vector table +
      # uninitialized — matching arduino-cli's convention, NOT PlatformIO's
      # own console line, which double-counts .data on this board.
      - name: Report flash/RAM per variant
        working-directory: firmware/MEMLNaut-NISPS
        run: |
          SIZE=$(find ~/.platformio/packages -name 'arm-none-eabi-size' | head -1)
          for e in slpworkshop pafsynth selftest soundanalysismidi; do
            "$SIZE" -A ".pio/build/$e/firmware.elf" | awk -v e="$e" '
              /^\.text/{t=$2} /^\.rodata/{r=$2} /^\.data/{d=$2}
              /^\.bss/{b=$2} /^\.ram_vector_table/{v=$2}
              /^\.uninitialized_data/{u=$2}
              END{printf "%-14s flash=%-8d ram=%-8d\n", e, t+r, d+b+v+u}'
          done