V0.12.1 (#106) #28
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Copyright(C) 2024-2025 Advanced Micro Devices, Inc. All rights reserved. | |
| # SPDX-License-Identifier: MIT | |
| # This workflow runs tests for the evaluation tool | |
| # Triggers when eval source code or tests are modified | |
| # Platform: Windows only | |
| name: Test Evaluation Tool | |
| on: | |
| workflow_call: | |
| push: | |
| branches: ["main"] | |
| paths: | |
| - "src/gaia/eval/**" | |
| - "src/gaia/eval/configs/**" | |
| - "src/gaia/eval/webapp/**" | |
| - "tests/test_eval*.py" | |
| - "groundtruth/**" | |
| - "test_data/**" | |
| pull_request: | |
| branches: ["main"] | |
| types: [opened, synchronize, reopened, ready_for_review] | |
| paths: | |
| - "src/gaia/eval/**" | |
| - "src/gaia/eval/configs/**" | |
| - "src/gaia/eval/webapp/**" | |
| - "tests/test_eval*.py" | |
| - "groundtruth/**" | |
| - "test_data/**" | |
| workflow_dispatch: | |
| permissions: | |
| contents: read | |
| jobs: | |
| test-eval-windows: | |
| name: Test Eval Tool (Windows) | |
| runs-on: windows-latest | |
| if: github.event_name != 'pull_request' || github.event.pull_request.draft == false || contains(github.event.pull_request.labels.*.name, 'ready_for_ci') | |
| timeout-minutes: 10 # 2 minute target but allow some buffer | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Set up Python 3.10 | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.10' | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -e . | |
| pip install pytest pytest-cov pytest-mock | |
| pip install anthropic rich | |
| - name: Run eval unit tests | |
| run: | | |
| pytest tests/test_eval.py -v --cov=src/gaia/eval --cov-report=term-missing | |
| - name: Test eval CLI commands | |
| run: | | |
| # Test help command | |
| python -m gaia.cli eval --help | |
| # Test visualize help | |
| python -m gaia.cli visualize --help | |
| - name: Set up Node.js | |
| uses: actions/setup-node@v4 | |
| with: | |
| node-version: '18' | |
| - name: Test webapp functionality | |
| run: | | |
| cd src/gaia/eval/webapp | |
| # Install dependencies | |
| npm install | |
| # Run syntax checks | |
| npm test | |
| # Test that server can start (Windows-compatible version) | |
| $env:PORT = 3456 # Use non-default port to avoid conflicts | |
| $process = Start-Process node -ArgumentList "server.js" -PassThru -ErrorAction Stop | |
| Start-Sleep -Seconds 3 | |
| if ($process.HasExited) { | |
| Write-Error "Server failed to start or crashed immediately" | |
| exit 1 | |
| } | |
| # Try to connect to the server | |
| try { | |
| $response = Invoke-WebRequest -Uri "http://localhost:3456" -TimeoutSec 5 -UseBasicParsing | |
| Write-Output "Server responded with status: $($response.StatusCode)" | |
| } catch { | |
| Write-Error "Server did not respond to HTTP request" | |
| Stop-Process -Id $process.Id -Force -ErrorAction SilentlyContinue | |
| exit 1 | |
| } | |
| Stop-Process -Id $process.Id -Force | |
| Write-Output "Webapp server test passed" |