test_gaia_cli_windows.yml

# Copyright(C) 2025-2026 Advanced Micro Devices, Inc. All rights reserved.
# SPDX-License-Identifier: MIT

# This workflow tests the GAIA CLI on Windows with full Lemonade server integration
# Tests include: CLI functionality, Lemonade integration, audio features, and core commands
# Platform: Windows (with Lemonade server and NPU support)

name: GAIA CLI Tests (Windows)

on:
  workflow_call:
  push:
    branches: ["main"]
    paths:
      - "src/**"
      - "tests/**"
      - "setup.py"
      - "pyproject.toml"
  pull_request:
    branches: ["main"]
    types: [opened, synchronize, reopened, ready_for_review]
    paths:
      - "src/**"
      - "tests/**"
      - "setup.py"
      - "pyproject.toml"
  merge_group:
  workflow_dispatch:

# Cancel in-progress runs when a new run is triggered
concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

jobs:
  test-gaia-cli-windows:
    name: Test GAIA CLI on Windows (Full Integration)
    runs-on: ${{ contains(github.event.pull_request.labels.*.name, 'stx-test') && 'stx-test' || 'stx' }}
    if: github.event_name != 'pull_request' || github.event.pull_request.draft == false || contains(github.event.pull_request.labels.*.name, 'ready_for_ci')
    steps:
      - uses: actions/checkout@v6

      - name: Setup Python Environment
        uses: ./.github/actions/setup-venv
        with:
          python-version: '3.12'
          # Note: 'blender' excluded as bpy requires Blender runtime
          install-package: '.[dev,talk,rag,mcp,api]'
          extra-index-url: 'https://download.pytorch.org/whl/cpu'

      - name: Install Lemonade Server
        uses: ./.github/actions/install-lemonade

      - name: Verify GAIA Installation
        run: |
          Write-Host "Verifying GAIA installation..."
          $gaiaPath = Get-Command gaia -ErrorAction SilentlyContinue
          if (-not $gaiaPath) {
            Write-Host "Error: gaia not installed correctly"
            Write-Host "Current PATH: $env:Path"
            exit 1
          }
          Write-Host "Found gaia at: $($gaiaPath.Source)"
          python --version
          python -m pip check

      - uses: FedericoCarboni/setup-ffmpeg@v3
        id: setup-ffmpeg

      - name: Start Lemonade Server and Run Tests
        timeout-minutes: 20
        env:
          HUGGINGFACE_ACCESS_TOKEN: ${{ secrets.HUGGINGFACE_ACCESS_TOKEN }}
          HF_TOKEN: ${{ secrets.HUGGINGFACE_ACCESS_TOKEN }}
          PYTHONUTF8: 1
        run: |
          Write-Host "Verify Python environment"
          python -c "import sys; print(sys.executable)"

          Write-Host "Find gaia executable location"
          $gaiaPath = Get-Command gaia -ErrorAction SilentlyContinue
          if (-not $gaiaPath) {
            Write-Host "Error: Cannot find gaia executable in PATH"
            Write-Host "Current PATH: $env:Path"
            exit 1
          }
          Write-Host "Found gaia at: $($gaiaPath.Source)"

          # Start the server in the background as a process (not PowerShell job)
          Write-Host "Starting lemonade-server in background..."
          # Start the server as a background process
          $serverProcess = Start-Process -FilePath "lemonade-server" -ArgumentList "serve", "--no-tray", "--port", "13305" -PassThru -WindowStyle Hidden
          Write-Host "Started lemonade-server process with ID: $($serverProcess.Id)"

          # Wait for server to start up
          Write-Host "Waiting for server to start up..."
          $maxWaitTime = 30  # seconds
          $waitTime = 0
          $serverReady = $false

          while ($waitTime -lt $maxWaitTime -and -not $serverReady) {
              Start-Sleep -Seconds 2
              $waitTime += 2

              try {
                  $response = Invoke-RestMethod -Uri "http://localhost:13305/api/v1/health" -Method GET -TimeoutSec 5
                  Write-Host "Server is ready and responding to health checks"
                  $serverReady = $true
              } catch {
                  Write-Host "Server not ready yet (waited $waitTime seconds)..."
              }
          }

          if (-not $serverReady) {
              Write-Host "Server failed to start within $maxWaitTime seconds"
              try {
                  if (-not $serverProcess.HasExited) {
                      $serverProcess.Kill()
                  }
              } catch {
                  Write-Host "Error stopping server process: $_"
              }
              throw "Failed to start lemonade-server for tests"
          }

          Write-Host "Lemonade server started successfully"

          # Pull the model now that server is running
          Write-Host "Pulling Llama-3.2-3B-Instruct-Hybrid model..."
          lemonade-server pull Llama-3.2-3B-Instruct-Hybrid

      - name: Run Unit Tests (Direct CMD - Full Error Visibility)
        shell: cmd
        env:
          PYTHONUTF8: 1
        run: |
          REM Activate virtual environment
          call "%GITHUB_WORKSPACE%\.venv\Scripts\activate.bat"

          echo ================================================================
          echo                 GAIA UNIT TESTS - FULL ERROR LOGGING
          echo ================================================================
          echo Virtual Environment: %VIRTUAL_ENV%
          echo Python Version:
          python --version
          echo Working Directory: %CD%
          echo.

          REM Initialize test tracking
          set test_llm_exit=0
          set test_asr_exit=0
          set test_tts_exit=0

          REM ================================================================
          REM TEST_LLM.PY
          REM ================================================================
          echo ****************************************************************
          echo                          TEST_LLM.PY
          echo ****************************************************************
          echo Starting test_llm.py at %TIME%...
          echo.

          python tests\unit\test_llm.py
          set test_llm_exit=%ERRORLEVEL%

          echo.
          echo ----------------------------------------------------------------
          echo test_llm.py completed at %TIME% with exit code: %test_llm_exit%
          if %test_llm_exit% equ 0 (
              echo [SUCCESS] test_llm.py passed
          ) else (
              echo [FAILURE] test_llm.py failed with exit code %test_llm_exit%
              echo Full error output displayed above - no truncation
          )
          echo ----------------------------------------------------------------
          echo.

          REM ================================================================
          REM TEST_ASR.PY
          REM ================================================================
          echo ****************************************************************
          echo                          TEST_ASR.PY
          echo ****************************************************************
          echo Starting test_asr.py at %TIME%...
          echo.

          python tests\unit\test_asr.py
          set test_asr_exit=%ERRORLEVEL%

          echo.
          echo ----------------------------------------------------------------
          echo test_asr.py completed at %TIME% with exit code: %test_asr_exit%
          if %test_asr_exit% equ 0 (
              echo [SUCCESS] test_asr.py passed
          ) else (
              echo [FAILURE] test_asr.py failed with exit code %test_asr_exit%
              echo Full error output displayed above - no truncation
          )
          echo ----------------------------------------------------------------
          echo.

          REM ================================================================
          REM TEST_TTS.PY
          REM ================================================================
          echo ****************************************************************
          echo                          TEST_TTS.PY
          echo ****************************************************************
          echo Starting test_tts.py at %TIME%...
          echo.

          python tests\unit\test_tts.py
          set test_tts_exit=%ERRORLEVEL%

          echo.
          echo ----------------------------------------------------------------
          echo test_tts.py completed at %TIME% with exit code: %test_tts_exit%
          if %test_tts_exit% equ 0 (
              echo [SUCCESS] test_tts.py passed
          ) else (
              echo [FAILURE] test_tts.py failed with exit code %test_tts_exit%
              echo Full error output displayed above - no truncation
          )
          echo ----------------------------------------------------------------
          echo.

          REM ================================================================
          REM FINAL SUMMARY
          REM ================================================================
          echo ================================================================
          echo                      FINAL TEST SUMMARY
          echo ================================================================
          echo test_llm.py:  exit code %test_llm_exit%
          echo test_asr.py:  exit code %test_asr_exit%
          echo test_tts.py:  exit code %test_tts_exit%
          echo ================================================================

          REM Calculate total failures
          set /a total_failures=%test_llm_exit%+%test_asr_exit%+%test_tts_exit%

          if %total_failures% equ 0 (
              echo [OVERALL SUCCESS] All tests passed successfully
              echo ================================================================
              exit /b 0
          ) else (
              echo [OVERALL FAILURE] One or more tests failed
              echo ================================================================
              echo FAILED TESTS:
              if %test_llm_exit% neq 0 echo   - test_llm.py ^(exit code %test_llm_exit%^)
              if %test_asr_exit% neq 0 echo   - test_asr.py ^(exit code %test_asr_exit%^)
              if %test_tts_exit% neq 0 echo   - test_tts.py ^(exit code %test_tts_exit%^)
              echo ================================================================
              echo IMPORTANT: All error messages are displayed in full above
              echo No PowerShell wrapping or truncation - raw Python output preserved
              echo ================================================================
              exit /b 1
          )

      - name: Run Summarizer Integration Tests (CMD - CLI Testing)
        shell: cmd
        env:
          PYTHONUTF8: 1
        run: |
          REM Activate virtual environment
          call "%GITHUB_WORKSPACE%\.venv\Scripts\activate.bat"

          echo ================================================================
          echo              GAIA SUMMARIZER CLI INTEGRATION TESTS
          echo ================================================================
          echo Virtual Environment: %VIRTUAL_ENV%
          echo Python Version:
          python --version
          echo Working Directory: %CD%
          echo.

          REM Initialize test tracking
          set summarizer_exit=0

          REM ================================================================
          REM TEST_SUMMARIZER.PY - CLI INTEGRATION TESTS
          REM ================================================================
          echo ****************************************************************
          echo                    SUMMARIZER CLI INTEGRATION TESTS
          echo ****************************************************************
          echo Starting test_summarizer.py at %TIME%...
          echo Testing complete CLI workflow: gaia summarize command
          echo.

          python -m pytest tests\test_summarizer.py -vs --tb=short
          set summarizer_exit=%ERRORLEVEL%

          echo.
          echo ----------------------------------------------------------------
          echo test_summarizer.py completed at %TIME% with exit code: %summarizer_exit%
          if %summarizer_exit% equ 0 (
              echo [SUCCESS] Summarizer CLI integration tests passed
          ) else (
              echo [FAILURE] Summarizer CLI integration tests failed with exit code %summarizer_exit%
              echo Full error output displayed above - no truncation
          )
          echo ----------------------------------------------------------------
          echo.

          REM ================================================================
          REM SUMMARIZER TEST SUMMARY
          REM ================================================================
          echo ================================================================
          echo                   SUMMARIZER TEST SUMMARY
          echo ================================================================
          echo test_summarizer.py:  exit code %summarizer_exit%
          echo ================================================================

          if %summarizer_exit% neq 0 (
              echo [FAILURE] Summarizer CLI integration tests failed
              echo ================================================================
              echo FAILED TEST:
              echo   - test_summarizer.py ^(exit code %summarizer_exit%^)
              echo ================================================================
              echo IMPORTANT: All error messages are displayed in full above
              echo No PowerShell wrapping or truncation - raw Python output preserved
              echo ================================================================
              exit /b 1
          ) else (
              echo [SUCCESS] Summarizer CLI integration tests passed successfully
              echo ================================================================
          )

      - name: Run Lemonade Client Integration Tests (CMD)
        shell: cmd
        env:
          PYTHONUTF8: 1
          GAIA_TEST_MODEL: Llama-3.2-3B-Instruct-Hybrid
        run: |
          REM Activate virtual environment
          call "%GITHUB_WORKSPACE%\.venv\Scripts\activate.bat"

          echo ================================================================
          echo              LEMONADE CLIENT INTEGRATION TESTS
          echo ================================================================
          echo Virtual Environment: %VIRTUAL_ENV%
          echo Python Version:
          python --version
          echo Test Model: %GAIA_TEST_MODEL%
          echo Working Directory: %CD%
          echo.

          REM Initialize test tracking
          set lemonade_exit=0

          REM ================================================================
          REM TEST_LEMONADE_CLIENT.PY - INTEGRATION TESTS ONLY
          REM ================================================================
          echo ****************************************************************
          echo                 LEMONADE CLIENT INTEGRATION TESTS
          echo ****************************************************************
          echo Starting test_lemonade_client.py integration tests at %TIME%...
          echo.

          REM Run only integration tests (skip mock tests which don't need server)
          python -m pytest tests\test_lemonade_client.py -vs --tb=short -k "Integration"
          set lemonade_exit=%ERRORLEVEL%

          echo.
          echo ----------------------------------------------------------------
          echo test_lemonade_client.py completed at %TIME% with exit code: %lemonade_exit%
          if %lemonade_exit% equ 0 (
              echo [SUCCESS] Lemonade client integration tests passed
          ) else (
              echo [FAILURE] Lemonade client integration tests failed with exit code %lemonade_exit%
              echo Full error output displayed above - no truncation
          )
          echo ----------------------------------------------------------------
          echo.

          REM ================================================================
          REM LEMONADE CLIENT TEST SUMMARY
          REM ================================================================
          echo ================================================================
          echo                LEMONADE CLIENT TEST SUMMARY
          echo ================================================================
          echo test_lemonade_client.py:  exit code %lemonade_exit%
          echo ================================================================

          if %lemonade_exit% neq 0 (
              echo [FAILURE] Lemonade client integration tests failed
              echo ================================================================
              echo FAILED TEST:
              echo   - test_lemonade_client.py ^(exit code %lemonade_exit%^)
              echo ================================================================
              echo IMPORTANT: All error messages are displayed in full above
              echo No PowerShell wrapping or truncation - raw Python output preserved
              echo ================================================================
              exit /b 1
          ) else (
              echo [SUCCESS] Lemonade client integration tests passed successfully
              echo ================================================================
          )

      - name: Debug GAIA Logs on Failure
        if: failure()
        shell: cmd
        run: |
          echo === Debugging GAIA failure ===

          echo === Check for GAIA log files ===
          if exist "gaia.cli.log" (
            echo Found gaia.cli.log:
            type gaia.cli.log
          ) else (
            echo No gaia.cli.log found
          )

          echo === Check running processes ===
          tasklist | findstr /i "python gaia lemonade-server"

          echo === Check ports in use ===
          netstat -an | findstr ":8000 :8001"