name: RuvLTRA-Small Tests

on:
  push:
    branches: [main, develop]
    paths:
      - 'crates/ruvllm/**'
      - 'crates/ruvllm-cli/**'
      - '.github/workflows/ruvltra-tests.yml'
  pull_request:
    branches: [main, develop]
    paths:
      - 'crates/ruvllm/**'
      - 'crates/ruvllm-cli/**'
  workflow_dispatch:
    inputs:
      run_benchmarks:
        description: 'Run performance benchmarks'
        required: false
        default: 'false'
        type: boolean
      run_stress_tests:
        description: 'Run stress tests'
        required: false
        default: 'false'
        type: boolean

env:
  CARGO_TERM_COLOR: always
  RUST_BACKTRACE: 1

jobs:
  # ============================================================================
  # Unit Tests - Model Loading, Quantization, SONA, ANE Dispatch
  # ============================================================================
  unit-tests:
    name: Unit Tests (${{ matrix.os }})
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest, macos-latest, windows-latest]
        include:
          - os: ubuntu-latest
            features: ""
          - os: macos-latest
            features: "coreml"
          - os: windows-latest
            features: ""

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable
        with:
          components: clippy, rustfmt

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: ${{ matrix.os }}-unit-tests

      - name: Run RuvLTRA Unit Tests
        run: |
          cargo test --package ruvllm ruvltra_tests \
            ${{ matrix.features && format('--features {0}', matrix.features) || '' }} \
            -- --nocapture
        env:
          RUST_LOG: debug

      - name: Run Quantization Tests
        run: |
          cargo test --package ruvllm quantization_accuracy \
            -- --nocapture

      - name: Run SONA Integration Tests
        run: |
          cargo test --package ruvllm sona_integration \
            -- --nocapture

      - name: Run ANE Dispatch Tests
        if: matrix.os == 'macos-latest'
        run: |
          cargo test --package ruvllm ane_dispatch --features coreml \
            -- --nocapture

  # ============================================================================
  # End-to-End Tests - Full Inference Pipeline
  # ============================================================================
  e2e-tests:
    name: E2E Tests (${{ matrix.os }})
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest, macos-latest]

    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: ${{ matrix.os }}-e2e-tests

      - name: Run E2E Pipeline Tests
        run: |
          cargo test --package ruvllm ruvltra_e2e::full_inference_pipeline \
            -- --nocapture

      - name: Run Streaming Tests
        run: |
          cargo test --package ruvllm ruvltra_e2e::streaming_generation \
            -- --nocapture

      - name: Run Quality Validation Tests
        run: |
          cargo test --package ruvllm ruvltra_e2e::quality_validation \
            -- --nocapture

      - name: Run Memory Validation Tests
        run: |
          cargo test --package ruvllm ruvltra_e2e::memory_validation \
            -- --nocapture

  # ============================================================================
  # Apple Silicon Specific Tests
  # ============================================================================
  apple-silicon-tests:
    name: Apple Silicon Tests
    runs-on: macos-14  # M1/M2 runners
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: macos-arm64-tests

      - name: Check Architecture
        run: |
          uname -m
          sysctl -n machdep.cpu.brand_string || true

      - name: Run ANE Integration Tests
        run: |
          cargo test --package ruvllm --features coreml,hybrid-ane \
            ane_integration -- --nocapture

      - name: Run SONA on Apple Silicon
        run: |
          cargo test --package ruvllm --features coreml \
            sona_integration -- --nocapture

      - name: Run Full RuvLTRA Test Suite
        run: |
          cargo test --package ruvllm --features coreml \
            ruvltra_tests -- --nocapture

      - name: Verify ANE Capabilities Detection
        run: |
          cargo test --package ruvllm --features coreml \
            test_ane_capabilities_detection -- --nocapture --exact

  # ============================================================================
  # Quantization Accuracy Tests
  # ============================================================================
  quantization-tests:
    name: Quantization Accuracy
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: quantization-tests

      - name: Test All Quantization Formats
        run: |
          cargo test --package ruvllm quantization \
            -- --nocapture

      - name: Test Q4_K Accuracy
        run: |
          cargo test --package ruvllm test_q4_k_dequantization \
            -- --nocapture --exact

      - name: Test Q8_0 Accuracy
        run: |
          cargo test --package ruvllm test_q8_0_dequantization \
            -- --nocapture --exact

      - name: Test Tensor Size Calculations
        run: |
          cargo test --package ruvllm test_tensor_size \
            -- --nocapture

  # ============================================================================
  # Thread Safety Tests
  # ============================================================================
  thread-safety-tests:
    name: Thread Safety
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: thread-safety-tests

      - name: Run Thread Safety Tests
        run: |
          cargo test --package ruvllm thread_safety \
            -- --nocapture --test-threads=4

      - name: Run Concurrent Inference Tests
        run: |
          cargo test --package ruvllm ruvltra_e2e::stress_tests::test_concurrent_inference \
            -- --nocapture --exact

  # ============================================================================
  # Performance Benchmarks (Optional)
  # ============================================================================
  benchmarks:
    name: Performance Benchmarks
    runs-on: macos-14
    if: github.event_name == 'workflow_dispatch' && github.event.inputs.run_benchmarks == 'true'
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: benchmarks

      - name: Run Performance Benchmarks
        run: |
          cargo test --package ruvllm --release --features coreml \
            -- --ignored --nocapture 2>&1 | tee benchmark-results.txt

      - name: Upload Benchmark Results
        uses: actions/upload-artifact@v4
        with:
          name: benchmark-results
          path: benchmark-results.txt

  # ============================================================================
  # Stress Tests (Optional)
  # ============================================================================
  stress-tests:
    name: Stress Tests
    runs-on: ubuntu-latest
    if: github.event_name == 'workflow_dispatch' && github.event.inputs.run_stress_tests == 'true'
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: stress-tests

      - name: Run Stress Tests
        run: |
          cargo test --package ruvllm --release \
            ruvltra_e2e::stress_tests -- --nocapture --test-threads=1
        timeout-minutes: 30

  # ============================================================================
  # Code Quality
  # ============================================================================
  code-quality:
    name: Code Quality
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable
        with:
          components: clippy, rustfmt

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: code-quality

      - name: Check Formatting
        run: |
          cargo fmt --package ruvllm -- --check

      - name: Run Clippy
        run: |
          cargo clippy --package ruvllm --all-targets -- -D warnings

      - name: Check Documentation
        run: |
          cargo doc --package ruvllm --no-deps
        env:
          RUSTDOCFLAGS: -D warnings

  # ============================================================================
  # Test Coverage
  # ============================================================================
  coverage:
    name: Test Coverage
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable
        with:
          components: llvm-tools-preview

      - name: Install cargo-llvm-cov
        uses: taiki-e/install-action@cargo-llvm-cov

      - name: Cache Cargo
        uses: Swatinem/rust-cache@v2
        with:
          key: coverage

      - name: Generate Coverage Report
        run: |
          cargo llvm-cov --package ruvllm \
            --html --output-dir coverage \
            -- --nocapture

      - name: Upload Coverage Report
        uses: actions/upload-artifact@v4
        with:
          name: coverage-report
          path: coverage/

      - name: Check Coverage Threshold
        run: |
          COVERAGE=$(cargo llvm-cov --package ruvllm --json 2>/dev/null | jq -r '.data[0].totals.lines.percent // 0')
          echo "Coverage: ${COVERAGE}%"
          # Require at least 60% line coverage
          if (( $(echo "$COVERAGE < 60" | bc -l) )); then
            echo "Coverage ${COVERAGE}% is below threshold of 60%"
            exit 1
          fi
        continue-on-error: true

  # ============================================================================
  # Summary Job
  # ============================================================================
  test-summary:
    name: Test Summary
    runs-on: ubuntu-latest
    needs: [unit-tests, e2e-tests, quantization-tests, thread-safety-tests, code-quality]
    if: always()
    steps:
      - name: Check Test Results
        run: |
          echo "## RuvLTRA-Small Test Summary" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "| Test Suite | Status |" >> $GITHUB_STEP_SUMMARY
          echo "|------------|--------|" >> $GITHUB_STEP_SUMMARY
          echo "| Unit Tests | ${{ needs.unit-tests.result == 'success' && '✅ Passed' || '❌ Failed' }} |" >> $GITHUB_STEP_SUMMARY
          echo "| E2E Tests | ${{ needs.e2e-tests.result == 'success' && '✅ Passed' || '❌ Failed' }} |" >> $GITHUB_STEP_SUMMARY
          echo "| Quantization | ${{ needs.quantization-tests.result == 'success' && '✅ Passed' || '❌ Failed' }} |" >> $GITHUB_STEP_SUMMARY
          echo "| Thread Safety | ${{ needs.thread-safety-tests.result == 'success' && '✅ Passed' || '❌ Failed' }} |" >> $GITHUB_STEP_SUMMARY
          echo "| Code Quality | ${{ needs.code-quality.result == 'success' && '✅ Passed' || '❌ Failed' }} |" >> $GITHUB_STEP_SUMMARY

      - name: Fail if Any Test Failed
        if: |
          needs.unit-tests.result == 'failure' ||
          needs.e2e-tests.result == 'failure' ||
          needs.quantization-tests.result == 'failure' ||
          needs.thread-safety-tests.result == 'failure' ||
          needs.code-quality.result == 'failure'
        run: exit 1