Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
switch agent loop testing from pip to uv
Adam6228a86155cb
diff --git a/.github/workflows/test-cua-models.yml b/.github/workflows/test-cua-models.ymlindex a30ed49b72..01c3a880cc 100644--- a/.github/workflows/test-cua-models.yml+++ b/.github/workflows/test-cua-models.yml@@ -77,8 +77,8 @@ jobs:- name: Checkout repositoryuses: actions/checkout@v4- - name: Set up Python- uses: actions/setup-python@v5+ - name: Set up uv and Python+ uses: astral-sh/setup-uv@v4with:python-version: "3.12"@@ -87,18 +87,18 @@ jobs:sudo apt-get updatesudo apt-get install -y libgl1-mesa-dri libglib2.0-0- - name: Install CUA dependencies+ - name: Install CUA dependencies (uv)run: |- pip install --upgrade pip- pip install -e libs/python/agent -e libs/python/computer- pip install -e libs/python/core- pip install "cua-agent[uitars-hf]"- pip install pytest+ uv venv+ uv pip install -e libs/python/agent -e libs/python/computer+ uv pip install -e libs/python/core+ uv pip install "cua-agent[uitars-hf]"+ uv pip install pytest- name: Test model with agent looprun: |cd tests/agent_loop_testing- python agent_test.py --model "${{ matrix.model }}"+ uv run python agent_test.py --model "${{ matrix.model }}"env:ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}# OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}