mirror of
https://github.com/trycua/computer.git
synced 2026-01-01 19:10:30 -06:00
Merge branch 'main' into feat/docs/init
This commit is contained in:
Morgan Dean
@@ -154,7 +154,7 @@ weights/icon_detect/model.pt
|
||||
weights/icon_detect/model.pt.zip
|
||||
weights/icon_detect/model.pt.zip.part*
|
||||
|
||||
libs/omniparser/weights/icon_detect/model.pt
|
||||
libs/python/omniparser/weights/icon_detect/model.pt
|
||||
|
||||
# Example test data and output
|
||||
examples/test_data/
|
||||
|
||||
66
.devcontainer/README.md
Normal file
66
.devcontainer/README.md
Normal file
@@ -0,0 +1,66 @@
|
||||
# Dev Container Setup
|
||||
|
||||
This repository includes a Dev Container configuration that simplifies the development setup to just 3 steps:
|
||||
|
||||
## Quick Start
|
||||
|
||||
|
||||
|
||||
1. **Install the Dev Containers extension ([VS Code](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) or [WindSurf](https://docs.windsurf.com/windsurf/advanced#dev-containers-beta))**
|
||||
2. **Open the repository in the Dev Container:**
|
||||
- Press `Ctrl+Shift+P` (or `⌘+Shift+P` on macOS)
|
||||
- Select `Dev Containers: Clone Repository in Container Volume...` and paste the repository URL: `https://github.com/trycua/cua.git` (if not cloned) or `Dev Containers: Open Folder in Container...` (if git cloned).
|
||||
> **Note**: On WindSurf, the post install hook might not run automatically. If so, run `/bin/bash .devcontainer/post-install.sh` manually.
|
||||
3. **Open the VS Code workspace:** Once the post-install.sh is done running, open the `.vscode/py.code-workspace` workspace and press 
|
||||
.
|
||||
4. **Run the Agent UI example:** Click 
|
||||
to start the Gradio UI. If prompted to install **debugpy (Python Debugger)** to enable remote debugging, select 'Yes' to proceed.
|
||||
5. **Access the Gradio UI:** The Gradio UI will be available at `http://localhost:7860` and will automatically forward to your host machine.
|
||||
|
||||
## What's Included
|
||||
|
||||
The dev container automatically:
|
||||
|
||||
- ✅ Sets up Python 3.11 environment
|
||||
- ✅ Installs all system dependencies (build tools, OpenGL, etc.)
|
||||
- ✅ Configures Python paths for all packages
|
||||
- ✅ Installs Python extensions (Black, Ruff, Pylance)
|
||||
- ✅ Forwards port 7860 for the Gradio web UI
|
||||
- ✅ Mounts your source code for live editing
|
||||
- ✅ Creates the required `.env.local` file
|
||||
|
||||
## Running Examples
|
||||
|
||||
After the container is built, you can run examples directly:
|
||||
|
||||
```bash
|
||||
# Run the agent UI (Gradio web interface)
|
||||
python examples/agent_ui_examples.py
|
||||
|
||||
# Run computer examples
|
||||
python examples/computer_examples.py
|
||||
|
||||
# Run computer UI examples
|
||||
python examples/computer_ui_examples.py
|
||||
```
|
||||
|
||||
The Gradio UI will be available at `http://localhost:7860` and will automatically forward to your host machine.
|
||||
|
||||
## Environment Variables
|
||||
|
||||
You'll need to add your API keys to `.env.local`:
|
||||
|
||||
```bash
|
||||
# Required for Anthropic provider
|
||||
ANTHROPIC_API_KEY=your_anthropic_key_here
|
||||
|
||||
# Required for OpenAI provider
|
||||
OPENAI_API_KEY=your_openai_key_here
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- The container connects to `host.docker.internal:7777` for Lume server communication
|
||||
- All Python packages are pre-installed and configured
|
||||
- Source code changes are reflected immediately (no rebuild needed)
|
||||
- The container uses the same Dockerfile as the regular Docker development environment
|
||||
18
.devcontainer/devcontainer.json
Normal file
18
.devcontainer/devcontainer.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"name": "C/ua - OSS",
|
||||
"build": {
|
||||
"dockerfile": "../Dockerfile"
|
||||
},
|
||||
"containerEnv": {
|
||||
"DISPLAY": "",
|
||||
"PYLUME_HOST": "host.docker.internal"
|
||||
},
|
||||
"forwardPorts": [7860],
|
||||
"portsAttributes": {
|
||||
"7860": {
|
||||
"label": "C/ua web client (Gradio)",
|
||||
"onAutoForward": "silent"
|
||||
}
|
||||
},
|
||||
"postCreateCommand": "/bin/bash .devcontainer/post-install.sh"
|
||||
}
|
||||
28
.devcontainer/post-install.sh
Executable file
28
.devcontainer/post-install.sh
Executable file
@@ -0,0 +1,28 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
WORKSPACE="/workspaces/cua"
|
||||
|
||||
# Setup .env.local
|
||||
echo "PYTHON_BIN=python" > /workspaces/cua/.env.local
|
||||
|
||||
# Run /scripts/build.sh
|
||||
./scripts/build.sh
|
||||
|
||||
# ---
|
||||
# Build is complete. Show user a clear message to open the workspace manually.
|
||||
# ---
|
||||
|
||||
cat << 'EOM'
|
||||
|
||||
============================================
|
||||
🚀 Build complete!
|
||||
|
||||
👉 Next steps:
|
||||
|
||||
1. Open '.vscode/py.code-workspace'
|
||||
2. Press 'Open Workspace'
|
||||
|
||||
Happy coding!
|
||||
============================================
|
||||
|
||||
EOM
|
||||
2
.gitattributes
vendored
Normal file
2
.gitattributes
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
* text=auto
|
||||
*.sh text eol=lf
|
||||
50
.github/workflows/npm-publish-computer.yml
vendored
Normal file
50
.github/workflows/npm-publish-computer.yml
vendored
Normal file
@@ -0,0 +1,50 @@
|
||||
name: Publish @trycua/computer to npm
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: main
|
||||
|
||||
jobs:
|
||||
publish:
|
||||
permissions:
|
||||
id-token: write
|
||||
contents: read
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Use Node.js 24.x
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: "24.x"
|
||||
registry-url: "https://registry.npmjs.org"
|
||||
|
||||
- name: Setup pnpm 10
|
||||
uses: pnpm/action-setup@v4
|
||||
with:
|
||||
version: 10
|
||||
|
||||
- name: Check if version changed
|
||||
id: check-version
|
||||
uses: EndBug/version-check@v2
|
||||
with:
|
||||
file-name: libs/typescript/computer/package.json
|
||||
diff-search: true
|
||||
|
||||
- name: Install dependencies
|
||||
if: steps.check-version.outputs.changed == 'true'
|
||||
working-directory: ./libs/typescript/computer
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Build package
|
||||
if: steps.check-version.outputs.changed == 'true'
|
||||
working-directory: ./libs/typescript/computer
|
||||
run: pnpm run build --if-present
|
||||
|
||||
- name: Publish to npm
|
||||
if: steps.check-version.outputs.changed == 'true'
|
||||
working-directory: ./libs/typescript/computer
|
||||
run: pnpm publish --access public --no-git-checks
|
||||
env:
|
||||
NPM_CONFIG_PROVENANCE: true
|
||||
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
|
||||
50
.github/workflows/npm-publish-core.yml
vendored
Normal file
50
.github/workflows/npm-publish-core.yml
vendored
Normal file
@@ -0,0 +1,50 @@
|
||||
name: Publish @trycua/core to npm
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: main
|
||||
|
||||
jobs:
|
||||
publish:
|
||||
permissions:
|
||||
id-token: write
|
||||
contents: read
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Use Node.js 24.x
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: "24.x"
|
||||
registry-url: "https://registry.npmjs.org"
|
||||
|
||||
- name: Setup pnpm 10
|
||||
uses: pnpm/action-setup@v4
|
||||
with:
|
||||
version: 10
|
||||
|
||||
- name: Check if version changed
|
||||
id: check-version
|
||||
uses: EndBug/version-check@v2
|
||||
with:
|
||||
file-name: libs/typescript/core/package.json
|
||||
diff-search: true
|
||||
|
||||
- name: Install dependencies
|
||||
if: steps.check-version.outputs.changed == 'true'
|
||||
working-directory: ./libs/typescript/core
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Build package
|
||||
if: steps.check-version.outputs.changed == 'true'
|
||||
working-directory: ./libs/typescript/core
|
||||
run: pnpm run build --if-present
|
||||
|
||||
- name: Publish to npm
|
||||
if: steps.check-version.outputs.changed == 'true'
|
||||
working-directory: ./libs/typescript/core
|
||||
run: pnpm publish --access public --no-git-checks
|
||||
env:
|
||||
NPM_CONFIG_PROVENANCE: true
|
||||
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
|
||||
162
.github/workflows/publish-agent.yml
vendored
162
.github/workflows/publish-agent.yml
vendored
@@ -1,162 +0,0 @@
|
||||
name: Publish Agent Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'agent-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
computer_version: ${{ steps.update-deps.outputs.computer_version }}
|
||||
som_version: ${{ steps.update-deps.outputs.som_version }}
|
||||
core_version: ${{ steps.update-deps.outputs.core_version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/agent-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for agent"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Update dependencies to latest versions
|
||||
id: update-deps
|
||||
run: |
|
||||
cd libs/agent
|
||||
|
||||
# Install required package for PyPI API access
|
||||
pip install requests
|
||||
|
||||
# Create a more robust Python script for PyPI version checking
|
||||
cat > get_latest_versions.py << 'EOF'
|
||||
import requests
|
||||
import json
|
||||
import sys
|
||||
|
||||
def get_package_version(package_name, fallback="0.1.0"):
|
||||
try:
|
||||
response = requests.get(f'https://pypi.org/pypi/{package_name}/json')
|
||||
print(f"API Response Status for {package_name}: {response.status_code}", file=sys.stderr)
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"API request failed for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
data = json.loads(response.text)
|
||||
|
||||
if 'info' not in data:
|
||||
print(f"Missing 'info' key in API response for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
return data['info']['version']
|
||||
except Exception as e:
|
||||
print(f"Error fetching version for {package_name}: {str(e)}", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
# Get latest versions
|
||||
print(get_package_version('cua-computer'))
|
||||
print(get_package_version('cua-som'))
|
||||
print(get_package_version('cua-core'))
|
||||
EOF
|
||||
|
||||
# Execute the script to get the versions
|
||||
VERSIONS=($(python get_latest_versions.py))
|
||||
LATEST_COMPUTER=${VERSIONS[0]}
|
||||
LATEST_SOM=${VERSIONS[1]}
|
||||
LATEST_CORE=${VERSIONS[2]}
|
||||
|
||||
echo "Latest cua-computer version: $LATEST_COMPUTER"
|
||||
echo "Latest cua-som version: $LATEST_SOM"
|
||||
echo "Latest cua-core version: $LATEST_CORE"
|
||||
|
||||
# Output the versions for the next job
|
||||
echo "computer_version=$LATEST_COMPUTER" >> $GITHUB_OUTPUT
|
||||
echo "som_version=$LATEST_SOM" >> $GITHUB_OUTPUT
|
||||
echo "core_version=$LATEST_CORE" >> $GITHUB_OUTPUT
|
||||
|
||||
# Determine major version for version constraint
|
||||
COMPUTER_MAJOR=$(echo $LATEST_COMPUTER | cut -d. -f1)
|
||||
SOM_MAJOR=$(echo $LATEST_SOM | cut -d. -f1)
|
||||
CORE_MAJOR=$(echo $LATEST_CORE | cut -d. -f1)
|
||||
|
||||
NEXT_COMPUTER_MAJOR=$((COMPUTER_MAJOR + 1))
|
||||
NEXT_SOM_MAJOR=$((SOM_MAJOR + 1))
|
||||
NEXT_CORE_MAJOR=$((CORE_MAJOR + 1))
|
||||
|
||||
# Update dependencies in pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
sed -i '' "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i '' "s/\"cua-som>=.*,<.*\"/\"cua-som>=$LATEST_SOM,<$NEXT_SOM_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i '' "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i "s/\"cua-som>=.*,<.*\"/\"cua-som>=$LATEST_SOM,<$NEXT_SOM_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
fi
|
||||
|
||||
# Display the updated dependencies
|
||||
echo "Updated dependencies in pyproject.toml:"
|
||||
grep -E "cua-computer|cua-som|cua-core" pyproject.toml
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "agent"
|
||||
package_dir: "libs/agent"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-agent"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "COMPUTER_VERSION=${{ needs.prepare.outputs.computer_version }}" >> $GITHUB_ENV
|
||||
echo "SOM_VERSION=${{ needs.prepare.outputs.som_version }}" >> $GITHUB_ENV
|
||||
echo "CORE_VERSION=${{ needs.prepare.outputs.core_version }}" >> $GITHUB_ENV
|
||||
80
.github/workflows/publish-computer-server.yml
vendored
80
.github/workflows/publish-computer-server.yml
vendored
@@ -1,80 +0,0 @@
|
||||
name: Publish Computer Server Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'computer-server-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.prepare.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/computer-server-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for computer-server"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "computer-server"
|
||||
package_dir: "libs/computer-server"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-computer-server"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "COMPUTER_VERSION=${{ needs.prepare.outputs.version }}" >> $GITHUB_ENV
|
||||
140
.github/workflows/publish-computer.yml
vendored
140
.github/workflows/publish-computer.yml
vendored
@@ -1,140 +0,0 @@
|
||||
name: Publish Computer Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'computer-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
core_version: ${{ steps.update-deps.outputs.core_version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/computer-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for computer"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Update dependencies to latest versions
|
||||
id: update-deps
|
||||
run: |
|
||||
cd libs/computer
|
||||
# Install required package for PyPI API access
|
||||
pip install requests
|
||||
|
||||
# Create a more robust Python script for PyPI version checking
|
||||
cat > get_latest_versions.py << 'EOF'
|
||||
import requests
|
||||
import json
|
||||
import sys
|
||||
|
||||
def get_package_version(package_name, fallback="0.1.0"):
|
||||
try:
|
||||
response = requests.get(f'https://pypi.org/pypi/{package_name}/json')
|
||||
print(f"API Response Status for {package_name}: {response.status_code}", file=sys.stderr)
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"API request failed for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
data = json.loads(response.text)
|
||||
|
||||
if 'info' not in data:
|
||||
print(f"Missing 'info' key in API response for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
return data['info']['version']
|
||||
except Exception as e:
|
||||
print(f"Error fetching version for {package_name}: {str(e)}", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
# Get latest versions
|
||||
print(get_package_version('cua-core'))
|
||||
EOF
|
||||
|
||||
# Execute the script to get the versions
|
||||
VERSIONS=($(python get_latest_versions.py))
|
||||
LATEST_CORE=${VERSIONS[0]}
|
||||
|
||||
echo "Latest cua-core version: $LATEST_CORE"
|
||||
|
||||
# Output the versions for the next job
|
||||
echo "core_version=$LATEST_CORE" >> $GITHUB_OUTPUT
|
||||
|
||||
# Determine major version for version constraint
|
||||
CORE_MAJOR=$(echo $LATEST_CORE | cut -d. -f1)
|
||||
NEXT_CORE_MAJOR=$((CORE_MAJOR + 1))
|
||||
|
||||
# Update dependencies in pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
sed -i '' "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
fi
|
||||
|
||||
# Display the updated dependencies
|
||||
echo "Updated dependencies in pyproject.toml:"
|
||||
grep -E "cua-core" pyproject.toml
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "computer"
|
||||
package_dir: "libs/computer"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-computer"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "CORE_VERSION=${{ needs.prepare.outputs.core_version }}" >> $GITHUB_ENV
|
||||
63
.github/workflows/publish-core.yml
vendored
63
.github/workflows/publish-core.yml
vendored
@@ -1,63 +0,0 @@
|
||||
name: Publish Core Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'core-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/core-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for core"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "core"
|
||||
package_dir: "libs/core"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-core"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
72
.github/workflows/publish-lume.yml
vendored
72
.github/workflows/publish-lume.yml
vendored
@@ -3,17 +3,17 @@ name: Publish Notarized Lume
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'lume-v*'
|
||||
- "lume-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to notarize (without v prefix)'
|
||||
description: "Version to notarize (without v prefix)"
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to notarize'
|
||||
description: "Version to notarize"
|
||||
required: true
|
||||
type: string
|
||||
secrets:
|
||||
@@ -64,7 +64,7 @@ jobs:
|
||||
|
||||
- name: Create .release directory
|
||||
run: mkdir -p .release
|
||||
|
||||
|
||||
- name: Set version
|
||||
id: set_version
|
||||
run: |
|
||||
@@ -82,11 +82,11 @@ jobs:
|
||||
echo "Error: No version found in tag or input"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
|
||||
# Update version in Main.swift
|
||||
echo "Updating version in Main.swift to $VERSION"
|
||||
sed -i '' "s/static let current: String = \".*\"/static let current: String = \"$VERSION\"/" libs/lume/src/Main.swift
|
||||
|
||||
|
||||
# Set output for later steps
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
@@ -106,18 +106,34 @@ jobs:
|
||||
# Import certificates
|
||||
echo $APPLICATION_CERT_BASE64 | base64 --decode > application.p12
|
||||
echo $INSTALLER_CERT_BASE64 | base64 --decode > installer.p12
|
||||
|
||||
|
||||
# Import certificates silently (minimize output)
|
||||
security import application.p12 -k build.keychain -P "$CERT_PASSWORD" -T /usr/bin/codesign -T /usr/bin/pkgbuild > /dev/null 2>&1
|
||||
security import installer.p12 -k build.keychain -P "$CERT_PASSWORD" -T /usr/bin/codesign -T /usr/bin/pkgbuild > /dev/null 2>&1
|
||||
|
||||
|
||||
# Allow codesign to access the certificates (minimal output)
|
||||
security set-key-partition-list -S apple-tool:,apple:,codesign: -s -k "$KEYCHAIN_PASSWORD" build.keychain > /dev/null 2>&1
|
||||
|
||||
# Verify certificates were imported but only show count, not details
|
||||
echo "Verifying signing identity (showing count only)..."
|
||||
security find-identity -v -p codesigning | grep -c "valid identities found" || true
|
||||
|
||||
|
||||
# Verify certificates were imported
|
||||
echo "Verifying signing identities..."
|
||||
CERT_COUNT=$(security find-identity -v -p codesigning build.keychain | grep -c "Developer ID Application" || echo "0")
|
||||
INSTALLER_COUNT=$(security find-identity -v build.keychain | grep -c "Developer ID Installer" || echo "0")
|
||||
|
||||
if [ "$CERT_COUNT" -eq 0 ]; then
|
||||
echo "Error: No Developer ID Application certificate found"
|
||||
security find-identity -v -p codesigning build.keychain
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ "$INSTALLER_COUNT" -eq 0 ]; then
|
||||
echo "Error: No Developer ID Installer certificate found"
|
||||
security find-identity -v build.keychain
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Found $CERT_COUNT Developer ID Application certificate(s) and $INSTALLER_COUNT Developer ID Installer certificate(s)"
|
||||
echo "All required certificates verified successfully"
|
||||
|
||||
# Clean up certificate files
|
||||
rm application.p12 installer.p12
|
||||
|
||||
@@ -137,32 +153,32 @@ jobs:
|
||||
echo "Starting build process..."
|
||||
echo "Swift version: $(swift --version | head -n 1)"
|
||||
echo "Building version: $VERSION"
|
||||
|
||||
|
||||
# Ensure .release directory exists
|
||||
mkdir -p .release
|
||||
chmod 755 .release
|
||||
|
||||
|
||||
# Build the project first (redirect verbose output)
|
||||
echo "Building project..."
|
||||
swift build --configuration release > build.log 2>&1
|
||||
echo "Build completed."
|
||||
|
||||
|
||||
# Run the notarization script with LOG_LEVEL env var
|
||||
chmod +x scripts/build/build-release-notarized.sh
|
||||
cd scripts/build
|
||||
LOG_LEVEL=minimal ./build-release-notarized.sh
|
||||
|
||||
|
||||
# Return to the lume directory
|
||||
cd ../..
|
||||
|
||||
|
||||
# Debug: List what files were actually created
|
||||
echo "Files in .release directory:"
|
||||
find .release -type f -name "*.tar.gz" -o -name "*.pkg.tar.gz"
|
||||
|
||||
|
||||
# Get architecture for output filename
|
||||
ARCH=$(uname -m)
|
||||
OS_IDENTIFIER="darwin-${ARCH}"
|
||||
|
||||
|
||||
# Output paths for later use
|
||||
echo "tarball_path=.release/lume-${VERSION}-${OS_IDENTIFIER}.tar.gz" >> $GITHUB_OUTPUT
|
||||
echo "pkg_path=.release/lume-${VERSION}-${OS_IDENTIFIER}.pkg.tar.gz" >> $GITHUB_OUTPUT
|
||||
@@ -181,12 +197,12 @@ jobs:
|
||||
shasum -a 256 lume-*.tar.gz >> checksums.txt
|
||||
echo '```' >> checksums.txt
|
||||
fi
|
||||
|
||||
|
||||
checksums=$(cat checksums.txt)
|
||||
echo "checksums<<EOF" >> $GITHUB_OUTPUT
|
||||
echo "$checksums" >> $GITHUB_OUTPUT
|
||||
echo "EOF" >> $GITHUB_OUTPUT
|
||||
|
||||
|
||||
# Debug: Show all files in the release directory
|
||||
echo "All files in release directory:"
|
||||
ls -la
|
||||
@@ -197,15 +213,15 @@ jobs:
|
||||
VERSION=${{ steps.set_version.outputs.version }}
|
||||
ARCH=$(uname -m)
|
||||
OS_IDENTIFIER="darwin-${ARCH}"
|
||||
|
||||
|
||||
# Create OS-tagged symlinks
|
||||
ln -sf "lume-${VERSION}-${OS_IDENTIFIER}.tar.gz" "lume-darwin.tar.gz"
|
||||
ln -sf "lume-${VERSION}-${OS_IDENTIFIER}.pkg.tar.gz" "lume-darwin.pkg.tar.gz"
|
||||
|
||||
|
||||
# Create simple symlinks
|
||||
ln -sf "lume-${VERSION}-${OS_IDENTIFIER}.tar.gz" "lume.tar.gz"
|
||||
ln -sf "lume-${VERSION}-${OS_IDENTIFIER}.pkg.tar.gz" "lume.pkg.tar.gz"
|
||||
|
||||
|
||||
# List all files (including symlinks)
|
||||
echo "Files with symlinks in release directory:"
|
||||
ls -la
|
||||
@@ -237,10 +253,10 @@ jobs:
|
||||
./libs/lume/.release/lume.pkg.tar.gz
|
||||
body: |
|
||||
${{ steps.generate_checksums.outputs.checksums }}
|
||||
|
||||
|
||||
### Installation with script
|
||||
|
||||
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"
|
||||
```
|
||||
generate_release_notes: true
|
||||
make_latest: true
|
||||
make_latest: true
|
||||
|
||||
157
.github/workflows/publish-mcp-server.yml
vendored
157
.github/workflows/publish-mcp-server.yml
vendored
@@ -1,157 +0,0 @@
|
||||
name: Publish MCP Server Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'mcp-server-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.prepare.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
agent_version: ${{ steps.update-deps.outputs.agent_version }}
|
||||
computer_version: ${{ steps.update-deps.outputs.computer_version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/mcp-server-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for mcp-server"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Update dependencies to latest versions
|
||||
id: update-deps
|
||||
run: |
|
||||
cd libs/mcp-server
|
||||
|
||||
# Install required package for PyPI API access
|
||||
pip install requests
|
||||
|
||||
# Create a Python script for PyPI version checking
|
||||
cat > get_latest_versions.py << 'EOF'
|
||||
import requests
|
||||
import json
|
||||
import sys
|
||||
|
||||
def get_package_version(package_name, fallback="0.1.0"):
|
||||
try:
|
||||
response = requests.get(f'https://pypi.org/pypi/{package_name}/json')
|
||||
print(f"API Response Status for {package_name}: {response.status_code}", file=sys.stderr)
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"API request failed for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
data = json.loads(response.text)
|
||||
|
||||
if 'info' not in data:
|
||||
print(f"Missing 'info' key in API response for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
return data['info']['version']
|
||||
except Exception as e:
|
||||
print(f"Error fetching version for {package_name}: {str(e)}", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
# Get latest versions
|
||||
print(get_package_version('cua-agent'))
|
||||
print(get_package_version('cua-computer'))
|
||||
EOF
|
||||
|
||||
# Execute the script to get the versions
|
||||
VERSIONS=($(python get_latest_versions.py))
|
||||
LATEST_AGENT=${VERSIONS[0]}
|
||||
LATEST_COMPUTER=${VERSIONS[1]}
|
||||
|
||||
echo "Latest cua-agent version: $LATEST_AGENT"
|
||||
echo "Latest cua-computer version: $LATEST_COMPUTER"
|
||||
|
||||
# Output the versions for the next job
|
||||
echo "agent_version=$LATEST_AGENT" >> $GITHUB_OUTPUT
|
||||
echo "computer_version=$LATEST_COMPUTER" >> $GITHUB_OUTPUT
|
||||
|
||||
# Determine major version for version constraint
|
||||
AGENT_MAJOR=$(echo $LATEST_AGENT | cut -d. -f1)
|
||||
COMPUTER_MAJOR=$(echo $LATEST_COMPUTER | cut -d. -f1)
|
||||
|
||||
NEXT_AGENT_MAJOR=$((AGENT_MAJOR + 1))
|
||||
NEXT_COMPUTER_MAJOR=$((COMPUTER_MAJOR + 1))
|
||||
|
||||
# Update dependencies in pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
# Update cua-agent with all extras
|
||||
sed -i '' "s/\"cua-agent\[all\]>=.*,<.*\"/\"cua-agent[all]>=$LATEST_AGENT,<$NEXT_AGENT_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i '' "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/\"cua-agent\[all\]>=.*,<.*\"/\"cua-agent[all]>=$LATEST_AGENT,<$NEXT_AGENT_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
fi
|
||||
|
||||
# Display the updated dependencies
|
||||
echo "Updated dependencies in pyproject.toml:"
|
||||
grep -E "cua-agent|cua-computer" pyproject.toml
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "mcp-server"
|
||||
package_dir: "libs/mcp-server"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-mcp-server"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "AGENT_VERSION=${{ needs.prepare.outputs.agent_version }}" >> $GITHUB_ENV
|
||||
echo "COMPUTER_VERSION=${{ needs.prepare.outputs.computer_version }}" >> $GITHUB_ENV
|
||||
82
.github/workflows/publish-pylume.yml
vendored
82
.github/workflows/publish-pylume.yml
vendored
@@ -1,82 +0,0 @@
|
||||
name: Publish Pylume Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'pylume-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.determine-version.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
determine-version:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/pylume-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for pylume"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
validate-version:
|
||||
runs-on: macos-latest
|
||||
needs: determine-version
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Validate version
|
||||
id: validate-version
|
||||
run: |
|
||||
CODE_VERSION=$(grep '__version__' libs/pylume/pylume/__init__.py | cut -d'"' -f2)
|
||||
if [ "${{ needs.determine-version.outputs.version }}" != "$CODE_VERSION" ]; then
|
||||
echo "Version mismatch: expected $CODE_VERSION, got ${{ needs.determine-version.outputs.version }}"
|
||||
exit 1
|
||||
fi
|
||||
echo "Version validated: $CODE_VERSION"
|
||||
|
||||
publish:
|
||||
needs: determine-version
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "pylume"
|
||||
package_dir: "libs/pylume"
|
||||
version: ${{ needs.determine-version.outputs.version }}
|
||||
is_lume_package: true
|
||||
base_package_name: "pylume"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
67
.github/workflows/publish-som.yml
vendored
67
.github/workflows/publish-som.yml
vendored
@@ -1,67 +0,0 @@
|
||||
name: Publish SOM Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'som-v*'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish (without v prefix)'
|
||||
required: true
|
||||
default: '0.1.0'
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.determine-version.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
determine-version:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/som-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for som"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
publish:
|
||||
needs: determine-version
|
||||
uses: ./.github/workflows/reusable-publish.yml
|
||||
with:
|
||||
package_name: "som"
|
||||
package_dir: "libs/som"
|
||||
version: ${{ needs.determine-version.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-som"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
162
.github/workflows/pypi-publish-agent.yml
vendored
Normal file
162
.github/workflows/pypi-publish-agent.yml
vendored
Normal file
@@ -0,0 +1,162 @@
|
||||
name: Publish Agent Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "agent-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
computer_version: ${{ steps.update-deps.outputs.computer_version }}
|
||||
som_version: ${{ steps.update-deps.outputs.som_version }}
|
||||
core_version: ${{ steps.update-deps.outputs.core_version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/agent-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for agent"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.11"
|
||||
|
||||
- name: Update dependencies to latest versions
|
||||
id: update-deps
|
||||
run: |
|
||||
cd libs/python/agent
|
||||
|
||||
# Install required package for PyPI API access
|
||||
pip install requests
|
||||
|
||||
# Create a more robust Python script for PyPI version checking
|
||||
cat > get_latest_versions.py << 'EOF'
|
||||
import requests
|
||||
import json
|
||||
import sys
|
||||
|
||||
def get_package_version(package_name, fallback="0.1.0"):
|
||||
try:
|
||||
response = requests.get(f'https://pypi.org/pypi/{package_name}/json')
|
||||
print(f"API Response Status for {package_name}: {response.status_code}", file=sys.stderr)
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"API request failed for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
data = json.loads(response.text)
|
||||
|
||||
if 'info' not in data:
|
||||
print(f"Missing 'info' key in API response for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
return data['info']['version']
|
||||
except Exception as e:
|
||||
print(f"Error fetching version for {package_name}: {str(e)}", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
# Get latest versions
|
||||
print(get_package_version('cua-computer'))
|
||||
print(get_package_version('cua-som'))
|
||||
print(get_package_version('cua-core'))
|
||||
EOF
|
||||
|
||||
# Execute the script to get the versions
|
||||
VERSIONS=($(python get_latest_versions.py))
|
||||
LATEST_COMPUTER=${VERSIONS[0]}
|
||||
LATEST_SOM=${VERSIONS[1]}
|
||||
LATEST_CORE=${VERSIONS[2]}
|
||||
|
||||
echo "Latest cua-computer version: $LATEST_COMPUTER"
|
||||
echo "Latest cua-som version: $LATEST_SOM"
|
||||
echo "Latest cua-core version: $LATEST_CORE"
|
||||
|
||||
# Output the versions for the next job
|
||||
echo "computer_version=$LATEST_COMPUTER" >> $GITHUB_OUTPUT
|
||||
echo "som_version=$LATEST_SOM" >> $GITHUB_OUTPUT
|
||||
echo "core_version=$LATEST_CORE" >> $GITHUB_OUTPUT
|
||||
|
||||
# Determine major version for version constraint
|
||||
COMPUTER_MAJOR=$(echo $LATEST_COMPUTER | cut -d. -f1)
|
||||
SOM_MAJOR=$(echo $LATEST_SOM | cut -d. -f1)
|
||||
CORE_MAJOR=$(echo $LATEST_CORE | cut -d. -f1)
|
||||
|
||||
NEXT_COMPUTER_MAJOR=$((COMPUTER_MAJOR + 1))
|
||||
NEXT_SOM_MAJOR=$((SOM_MAJOR + 1))
|
||||
NEXT_CORE_MAJOR=$((CORE_MAJOR + 1))
|
||||
|
||||
# Update dependencies in pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
sed -i '' "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i '' "s/\"cua-som>=.*,<.*\"/\"cua-som>=$LATEST_SOM,<$NEXT_SOM_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i '' "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i "s/\"cua-som>=.*,<.*\"/\"cua-som>=$LATEST_SOM,<$NEXT_SOM_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
fi
|
||||
|
||||
# Display the updated dependencies
|
||||
echo "Updated dependencies in pyproject.toml:"
|
||||
grep -E "cua-computer|cua-som|cua-core" pyproject.toml
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "agent"
|
||||
package_dir: "libs/python/agent"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-agent"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "COMPUTER_VERSION=${{ needs.prepare.outputs.computer_version }}" >> $GITHUB_ENV
|
||||
echo "SOM_VERSION=${{ needs.prepare.outputs.som_version }}" >> $GITHUB_ENV
|
||||
echo "CORE_VERSION=${{ needs.prepare.outputs.core_version }}" >> $GITHUB_ENV
|
||||
80
.github/workflows/pypi-publish-computer-server.yml
vendored
Normal file
80
.github/workflows/pypi-publish-computer-server.yml
vendored
Normal file
@@ -0,0 +1,80 @@
|
||||
name: Publish Computer Server Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "computer-server-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.prepare.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/computer-server-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for computer-server"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "computer-server"
|
||||
package_dir: "libs/python/computer-server"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-computer-server"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "COMPUTER_VERSION=${{ needs.prepare.outputs.version }}" >> $GITHUB_ENV
|
||||
140
.github/workflows/pypi-publish-computer.yml
vendored
Normal file
140
.github/workflows/pypi-publish-computer.yml
vendored
Normal file
@@ -0,0 +1,140 @@
|
||||
name: Publish Computer Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "computer-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
core_version: ${{ steps.update-deps.outputs.core_version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/computer-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for computer"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.11"
|
||||
|
||||
- name: Update dependencies to latest versions
|
||||
id: update-deps
|
||||
run: |
|
||||
cd libs/python/computer
|
||||
# Install required package for PyPI API access
|
||||
pip install requests
|
||||
|
||||
# Create a more robust Python script for PyPI version checking
|
||||
cat > get_latest_versions.py << 'EOF'
|
||||
import requests
|
||||
import json
|
||||
import sys
|
||||
|
||||
def get_package_version(package_name, fallback="0.1.0"):
|
||||
try:
|
||||
response = requests.get(f'https://pypi.org/pypi/{package_name}/json')
|
||||
print(f"API Response Status for {package_name}: {response.status_code}", file=sys.stderr)
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"API request failed for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
data = json.loads(response.text)
|
||||
|
||||
if 'info' not in data:
|
||||
print(f"Missing 'info' key in API response for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
return data['info']['version']
|
||||
except Exception as e:
|
||||
print(f"Error fetching version for {package_name}: {str(e)}", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
# Get latest versions
|
||||
print(get_package_version('cua-core'))
|
||||
EOF
|
||||
|
||||
# Execute the script to get the versions
|
||||
VERSIONS=($(python get_latest_versions.py))
|
||||
LATEST_CORE=${VERSIONS[0]}
|
||||
|
||||
echo "Latest cua-core version: $LATEST_CORE"
|
||||
|
||||
# Output the versions for the next job
|
||||
echo "core_version=$LATEST_CORE" >> $GITHUB_OUTPUT
|
||||
|
||||
# Determine major version for version constraint
|
||||
CORE_MAJOR=$(echo $LATEST_CORE | cut -d. -f1)
|
||||
NEXT_CORE_MAJOR=$((CORE_MAJOR + 1))
|
||||
|
||||
# Update dependencies in pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
sed -i '' "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/\"cua-core>=.*,<.*\"/\"cua-core>=$LATEST_CORE,<$NEXT_CORE_MAJOR.0.0\"/" pyproject.toml
|
||||
fi
|
||||
|
||||
# Display the updated dependencies
|
||||
echo "Updated dependencies in pyproject.toml:"
|
||||
grep -E "cua-core" pyproject.toml
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "computer"
|
||||
package_dir: "libs/python/computer"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-computer"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "CORE_VERSION=${{ needs.prepare.outputs.core_version }}" >> $GITHUB_ENV
|
||||
63
.github/workflows/pypi-publish-core.yml
vendored
Normal file
63
.github/workflows/pypi-publish-core.yml
vendored
Normal file
@@ -0,0 +1,63 @@
|
||||
name: Publish Core Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "core-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/core-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for core"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "core"
|
||||
package_dir: "libs/python/core"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-core"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
157
.github/workflows/pypi-publish-mcp-server.yml
vendored
Normal file
157
.github/workflows/pypi-publish-mcp-server.yml
vendored
Normal file
@@ -0,0 +1,157 @@
|
||||
name: Publish MCP Server Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "mcp-server-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.prepare.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
prepare:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
agent_version: ${{ steps.update-deps.outputs.agent_version }}
|
||||
computer_version: ${{ steps.update-deps.outputs.computer_version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/mcp-server-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for mcp-server"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.11"
|
||||
|
||||
- name: Update dependencies to latest versions
|
||||
id: update-deps
|
||||
run: |
|
||||
cd libs/python/mcp-server
|
||||
|
||||
# Install required package for PyPI API access
|
||||
pip install requests
|
||||
|
||||
# Create a Python script for PyPI version checking
|
||||
cat > get_latest_versions.py << 'EOF'
|
||||
import requests
|
||||
import json
|
||||
import sys
|
||||
|
||||
def get_package_version(package_name, fallback="0.1.0"):
|
||||
try:
|
||||
response = requests.get(f'https://pypi.org/pypi/{package_name}/json')
|
||||
print(f"API Response Status for {package_name}: {response.status_code}", file=sys.stderr)
|
||||
|
||||
if response.status_code != 200:
|
||||
print(f"API request failed for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
data = json.loads(response.text)
|
||||
|
||||
if 'info' not in data:
|
||||
print(f"Missing 'info' key in API response for {package_name}, using fallback version", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
return data['info']['version']
|
||||
except Exception as e:
|
||||
print(f"Error fetching version for {package_name}: {str(e)}", file=sys.stderr)
|
||||
return fallback
|
||||
|
||||
# Get latest versions
|
||||
print(get_package_version('cua-agent'))
|
||||
print(get_package_version('cua-computer'))
|
||||
EOF
|
||||
|
||||
# Execute the script to get the versions
|
||||
VERSIONS=($(python get_latest_versions.py))
|
||||
LATEST_AGENT=${VERSIONS[0]}
|
||||
LATEST_COMPUTER=${VERSIONS[1]}
|
||||
|
||||
echo "Latest cua-agent version: $LATEST_AGENT"
|
||||
echo "Latest cua-computer version: $LATEST_COMPUTER"
|
||||
|
||||
# Output the versions for the next job
|
||||
echo "agent_version=$LATEST_AGENT" >> $GITHUB_OUTPUT
|
||||
echo "computer_version=$LATEST_COMPUTER" >> $GITHUB_OUTPUT
|
||||
|
||||
# Determine major version for version constraint
|
||||
AGENT_MAJOR=$(echo $LATEST_AGENT | cut -d. -f1)
|
||||
COMPUTER_MAJOR=$(echo $LATEST_COMPUTER | cut -d. -f1)
|
||||
|
||||
NEXT_AGENT_MAJOR=$((AGENT_MAJOR + 1))
|
||||
NEXT_COMPUTER_MAJOR=$((COMPUTER_MAJOR + 1))
|
||||
|
||||
# Update dependencies in pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
# Update cua-agent with all extras
|
||||
sed -i '' "s/\"cua-agent\[all\]>=.*,<.*\"/\"cua-agent[all]>=$LATEST_AGENT,<$NEXT_AGENT_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i '' "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/\"cua-agent\[all\]>=.*,<.*\"/\"cua-agent[all]>=$LATEST_AGENT,<$NEXT_AGENT_MAJOR.0.0\"/" pyproject.toml
|
||||
sed -i "s/\"cua-computer>=.*,<.*\"/\"cua-computer>=$LATEST_COMPUTER,<$NEXT_COMPUTER_MAJOR.0.0\"/" pyproject.toml
|
||||
fi
|
||||
|
||||
# Display the updated dependencies
|
||||
echo "Updated dependencies in pyproject.toml:"
|
||||
grep -E "cua-agent|cua-computer" pyproject.toml
|
||||
|
||||
publish:
|
||||
needs: prepare
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "mcp-server"
|
||||
package_dir: "libs/python/mcp-server"
|
||||
version: ${{ needs.prepare.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-mcp-server"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
|
||||
set-env-variables:
|
||||
needs: [prepare, publish]
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- name: Set environment variables for use in other jobs
|
||||
run: |
|
||||
echo "AGENT_VERSION=${{ needs.prepare.outputs.agent_version }}" >> $GITHUB_ENV
|
||||
echo "COMPUTER_VERSION=${{ needs.prepare.outputs.computer_version }}" >> $GITHUB_ENV
|
||||
82
.github/workflows/pypi-publish-pylume.yml
vendored
Normal file
82
.github/workflows/pypi-publish-pylume.yml
vendored
Normal file
@@ -0,0 +1,82 @@
|
||||
name: Publish Pylume Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "pylume-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.determine-version.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
determine-version:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/pylume-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for pylume"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
validate-version:
|
||||
runs-on: macos-latest
|
||||
needs: determine-version
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Validate version
|
||||
id: validate-version
|
||||
run: |
|
||||
CODE_VERSION=$(grep '__version__' libs/python/pylume/pylume/__init__.py | cut -d'"' -f2)
|
||||
if [ "${{ needs.determine-version.outputs.version }}" != "$CODE_VERSION" ]; then
|
||||
echo "Version mismatch: expected $CODE_VERSION, got ${{ needs.determine-version.outputs.version }}"
|
||||
exit 1
|
||||
fi
|
||||
echo "Version validated: $CODE_VERSION"
|
||||
|
||||
publish:
|
||||
needs: determine-version
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "pylume"
|
||||
package_dir: "libs/python/pylume"
|
||||
version: ${{ needs.determine-version.outputs.version }}
|
||||
is_lume_package: true
|
||||
base_package_name: "pylume"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
67
.github/workflows/pypi-publish-som.yml
vendored
Normal file
67
.github/workflows/pypi-publish-som.yml
vendored
Normal file
@@ -0,0 +1,67 @@
|
||||
name: Publish SOM Package
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "som-v*"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish (without v prefix)"
|
||||
required: true
|
||||
default: "0.1.0"
|
||||
workflow_call:
|
||||
inputs:
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.determine-version.outputs.version }}
|
||||
|
||||
# Adding permissions at workflow level
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
jobs:
|
||||
determine-version:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
version: ${{ steps.get-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Determine version
|
||||
id: get-version
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" == "push" ]; then
|
||||
# Extract version from tag (for package-specific tags)
|
||||
if [[ "${{ github.ref }}" =~ ^refs/tags/som-v([0-9]+\.[0-9]+\.[0-9]+) ]]; then
|
||||
VERSION=${BASH_REMATCH[1]}
|
||||
else
|
||||
echo "Invalid tag format for som"
|
||||
exit 1
|
||||
fi
|
||||
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
||||
# Use version from workflow dispatch
|
||||
VERSION=${{ github.event.inputs.version }}
|
||||
else
|
||||
# Use version from workflow_call
|
||||
VERSION=${{ inputs.version }}
|
||||
fi
|
||||
echo "VERSION=$VERSION"
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
|
||||
publish:
|
||||
needs: determine-version
|
||||
uses: ./.github/workflows/pypi-reusable-publish.yml
|
||||
with:
|
||||
package_name: "som"
|
||||
package_dir: "libs/python/som"
|
||||
version: ${{ needs.determine-version.outputs.version }}
|
||||
is_lume_package: false
|
||||
base_package_name: "cua-som"
|
||||
secrets:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
280
.github/workflows/pypi-reusable-publish.yml
vendored
Normal file
280
.github/workflows/pypi-reusable-publish.yml
vendored
Normal file
@@ -0,0 +1,280 @@
|
||||
name: Reusable Package Publish Workflow
|
||||
|
||||
on:
|
||||
workflow_call:
|
||||
inputs:
|
||||
package_name:
|
||||
description: "Name of the package (e.g. pylume, computer, agent)"
|
||||
required: true
|
||||
type: string
|
||||
package_dir:
|
||||
description: "Directory containing the package relative to workspace root (e.g. libs/python/pylume)"
|
||||
required: true
|
||||
type: string
|
||||
version:
|
||||
description: "Version to publish"
|
||||
required: true
|
||||
type: string
|
||||
is_lume_package:
|
||||
description: "Whether this package includes the lume binary"
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
base_package_name:
|
||||
description: "PyPI package name (e.g. pylume, cua-agent)"
|
||||
required: true
|
||||
type: string
|
||||
make_latest:
|
||||
description: "Whether to mark this release as latest (should only be true for lume)"
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
secrets:
|
||||
PYPI_TOKEN:
|
||||
required: true
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.build-and-publish.outputs.version }}
|
||||
|
||||
jobs:
|
||||
build-and-publish:
|
||||
runs-on: macos-latest
|
||||
permissions:
|
||||
contents: write # This permission is needed for creating releases
|
||||
outputs:
|
||||
version: ${{ steps.set-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0 # Full history for release creation
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.11"
|
||||
|
||||
- name: Create root pdm.lock file
|
||||
run: |
|
||||
# Create an empty pdm.lock file in the root
|
||||
touch pdm.lock
|
||||
|
||||
- name: Install PDM
|
||||
uses: pdm-project/setup-pdm@v3
|
||||
with:
|
||||
python-version: "3.11"
|
||||
cache: true
|
||||
|
||||
- name: Set version
|
||||
id: set-version
|
||||
run: |
|
||||
echo "VERSION=${{ inputs.version }}" >> $GITHUB_ENV
|
||||
echo "version=${{ inputs.version }}" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Initialize PDM in package directory
|
||||
run: |
|
||||
# Make sure we're working with a properly initialized PDM project
|
||||
cd ${{ inputs.package_dir }}
|
||||
|
||||
# Create pdm.lock if it doesn't exist
|
||||
if [ ! -f "pdm.lock" ]; then
|
||||
echo "No pdm.lock found, initializing PDM project..."
|
||||
pdm lock
|
||||
fi
|
||||
|
||||
- name: Set version in package
|
||||
run: |
|
||||
cd ${{ inputs.package_dir }}
|
||||
# Replace pdm bump with direct edit of pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
sed -i '' "s/version = \".*\"/version = \"$VERSION\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/version = \".*\"/version = \"$VERSION\"/" pyproject.toml
|
||||
fi
|
||||
# Verify version was updated
|
||||
echo "Updated version in pyproject.toml:"
|
||||
grep "version =" pyproject.toml
|
||||
|
||||
# Conditional step for lume binary download (only for pylume package)
|
||||
- name: Download and setup lume binary
|
||||
if: inputs.is_lume_package
|
||||
run: |
|
||||
# Create a temporary directory for extraction
|
||||
mkdir -p temp_lume
|
||||
|
||||
# Download the latest lume release directly
|
||||
echo "Downloading latest lume version..."
|
||||
curl -sL "https://github.com/trycua/lume/releases/latest/download/lume.tar.gz" -o temp_lume/lume.tar.gz
|
||||
|
||||
# Extract the tar file (ignore ownership and suppress warnings)
|
||||
cd temp_lume && tar --no-same-owner -xzf lume.tar.gz
|
||||
|
||||
# Make the binary executable
|
||||
chmod +x lume
|
||||
|
||||
# Copy the lume binary to the correct location in the pylume package
|
||||
mkdir -p "${GITHUB_WORKSPACE}/${{ inputs.package_dir }}/pylume"
|
||||
cp lume "${GITHUB_WORKSPACE}/${{ inputs.package_dir }}/pylume/lume"
|
||||
|
||||
# Verify the binary exists and is executable
|
||||
test -x "${GITHUB_WORKSPACE}/${{ inputs.package_dir }}/pylume/lume" || { echo "lume binary not found or not executable"; exit 1; }
|
||||
|
||||
# Get the version from the downloaded binary for reference
|
||||
LUME_VERSION=$(./lume --version | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' || echo "unknown")
|
||||
echo "Using lume version: $LUME_VERSION"
|
||||
|
||||
# Cleanup
|
||||
cd "${GITHUB_WORKSPACE}" && rm -rf temp_lume
|
||||
|
||||
# Save the lume version for reference
|
||||
echo "LUME_VERSION=${LUME_VERSION}" >> $GITHUB_ENV
|
||||
|
||||
- name: Build and publish
|
||||
env:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
run: |
|
||||
cd ${{ inputs.package_dir }}
|
||||
# Build with PDM
|
||||
pdm build
|
||||
|
||||
# For pylume package, verify the binary is in the wheel
|
||||
if [ "${{ inputs.is_lume_package }}" = "true" ]; then
|
||||
python -m pip install wheel
|
||||
wheel unpack dist/*.whl --dest temp_wheel
|
||||
echo "Listing contents of wheel directory:"
|
||||
find temp_wheel -type f
|
||||
test -f temp_wheel/pylume-*/pylume/lume || { echo "lume binary not found in wheel"; exit 1; }
|
||||
rm -rf temp_wheel
|
||||
echo "Publishing ${{ inputs.base_package_name }} ${VERSION} with lume ${LUME_VERSION}"
|
||||
else
|
||||
echo "Publishing ${{ inputs.base_package_name }} ${VERSION}"
|
||||
fi
|
||||
|
||||
# Install and use twine directly instead of PDM publish
|
||||
echo "Installing twine for direct publishing..."
|
||||
pip install twine
|
||||
|
||||
echo "Publishing to PyPI using twine..."
|
||||
TWINE_USERNAME="__token__" TWINE_PASSWORD="$PYPI_TOKEN" python -m twine upload dist/*
|
||||
|
||||
# Save the wheel file path for the release
|
||||
WHEEL_FILE=$(ls dist/*.whl | head -1)
|
||||
echo "WHEEL_FILE=${WHEEL_FILE}" >> $GITHUB_ENV
|
||||
|
||||
- name: Prepare Simple Release Notes
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
run: |
|
||||
# Create release notes based on package type
|
||||
echo "# ${{ inputs.base_package_name }} v${VERSION}" > release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
|
||||
if [ "${{ inputs.package_name }}" = "pylume" ]; then
|
||||
echo "## Python SDK for lume - run macOS and Linux VMs on Apple Silicon" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "This package provides Python bindings for the lume virtualization tool." >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* lume binary: v${LUME_VERSION}" >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "computer" ]; then
|
||||
echo "## Computer control library for the Computer Universal Automation (CUA) project" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* pylume: ${PYLUME_VERSION:-latest}" >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "agent" ]; then
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* cua-computer: ${COMPUTER_VERSION:-latest}" >> release_notes.md
|
||||
echo "* cua-som: ${SOM_VERSION:-latest}" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Installation Options" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "### Basic installation with Anthropic" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install cua-agent[anthropic]==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "### With SOM (recommended)" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install cua-agent[som]==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "### All features" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install cua-agent[all]==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "som" ]; then
|
||||
echo "## Computer Vision and OCR library for detecting and analyzing UI elements" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "This package provides enhanced UI understanding capabilities through computer vision and OCR." >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "computer-server" ]; then
|
||||
echo "## Computer Server for the Computer Universal Automation (CUA) project" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "A FastAPI-based server implementation for computer control." >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* cua-computer: ${COMPUTER_VERSION:-latest}" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Usage" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "# Run the server" >> release_notes.md
|
||||
echo "cua-computer-server" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "mcp-server" ]; then
|
||||
echo "## MCP Server for the Computer-Use Agent (CUA)" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "This package provides MCP (Model Context Protocol) integration for CUA agents, allowing them to be used with Claude Desktop, Cursor, and other MCP clients." >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* cua-computer: ${COMPUTER_VERSION:-latest}" >> release_notes.md
|
||||
echo "* cua-agent: ${AGENT_VERSION:-latest}" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Usage" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "# Run the MCP server directly" >> release_notes.md
|
||||
echo "cua-mcp-server" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Claude Desktop Integration" >> release_notes.md
|
||||
echo "Add to your Claude Desktop configuration (~/.config/claude-desktop/claude_desktop_config.json or OS-specific location):" >> release_notes.md
|
||||
echo '```json' >> release_notes.md
|
||||
echo '"mcpServers": {' >> release_notes.md
|
||||
echo ' "cua-agent": {' >> release_notes.md
|
||||
echo ' "command": "cua-mcp-server",' >> release_notes.md
|
||||
echo ' "args": [],' >> release_notes.md
|
||||
echo ' "env": {' >> release_notes.md
|
||||
echo ' "CUA_AGENT_LOOP": "OMNI",' >> release_notes.md
|
||||
echo ' "CUA_MODEL_PROVIDER": "ANTHROPIC",' >> release_notes.md
|
||||
echo ' "CUA_MODEL_NAME": "claude-3-opus-20240229",' >> release_notes.md
|
||||
echo ' "ANTHROPIC_API_KEY": "your-api-key",' >> release_notes.md
|
||||
echo ' "PYTHONIOENCODING": "utf-8"' >> release_notes.md
|
||||
echo ' }' >> release_notes.md
|
||||
echo ' }' >> release_notes.md
|
||||
echo '}' >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
fi
|
||||
|
||||
# Add installation section if not agent (which has its own installation section)
|
||||
if [ "${{ inputs.package_name }}" != "agent" ]; then
|
||||
echo "" >> release_notes.md
|
||||
echo "## Installation" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install ${{ inputs.base_package_name }}==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
fi
|
||||
|
||||
echo "Release notes created:"
|
||||
cat release_notes.md
|
||||
|
||||
- name: Create GitHub Release
|
||||
uses: softprops/action-gh-release@v2
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
with:
|
||||
name: "${{ inputs.base_package_name }} v${{ env.VERSION }}"
|
||||
body_path: release_notes.md
|
||||
files: ${{ inputs.package_dir }}/${{ env.WHEEL_FILE }}
|
||||
draft: false
|
||||
prerelease: false
|
||||
make_latest: ${{ inputs.package_name == 'lume' }}
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
280
.github/workflows/reusable-publish.yml
vendored
280
.github/workflows/reusable-publish.yml
vendored
@@ -1,280 +0,0 @@
|
||||
name: Reusable Package Publish Workflow
|
||||
|
||||
on:
|
||||
workflow_call:
|
||||
inputs:
|
||||
package_name:
|
||||
description: 'Name of the package (e.g. pylume, computer, agent)'
|
||||
required: true
|
||||
type: string
|
||||
package_dir:
|
||||
description: 'Directory containing the package relative to workspace root (e.g. libs/pylume)'
|
||||
required: true
|
||||
type: string
|
||||
version:
|
||||
description: 'Version to publish'
|
||||
required: true
|
||||
type: string
|
||||
is_lume_package:
|
||||
description: 'Whether this package includes the lume binary'
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
base_package_name:
|
||||
description: 'PyPI package name (e.g. pylume, cua-agent)'
|
||||
required: true
|
||||
type: string
|
||||
make_latest:
|
||||
description: 'Whether to mark this release as latest (should only be true for lume)'
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
secrets:
|
||||
PYPI_TOKEN:
|
||||
required: true
|
||||
outputs:
|
||||
version:
|
||||
description: "The version that was published"
|
||||
value: ${{ jobs.build-and-publish.outputs.version }}
|
||||
|
||||
jobs:
|
||||
build-and-publish:
|
||||
runs-on: macos-latest
|
||||
permissions:
|
||||
contents: write # This permission is needed for creating releases
|
||||
outputs:
|
||||
version: ${{ steps.set-version.outputs.version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0 # Full history for release creation
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.11'
|
||||
|
||||
- name: Create root pdm.lock file
|
||||
run: |
|
||||
# Create an empty pdm.lock file in the root
|
||||
touch pdm.lock
|
||||
|
||||
- name: Install PDM
|
||||
uses: pdm-project/setup-pdm@v3
|
||||
with:
|
||||
python-version: '3.11'
|
||||
cache: true
|
||||
|
||||
- name: Set version
|
||||
id: set-version
|
||||
run: |
|
||||
echo "VERSION=${{ inputs.version }}" >> $GITHUB_ENV
|
||||
echo "version=${{ inputs.version }}" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Initialize PDM in package directory
|
||||
run: |
|
||||
# Make sure we're working with a properly initialized PDM project
|
||||
cd ${{ inputs.package_dir }}
|
||||
|
||||
# Create pdm.lock if it doesn't exist
|
||||
if [ ! -f "pdm.lock" ]; then
|
||||
echo "No pdm.lock found, initializing PDM project..."
|
||||
pdm lock
|
||||
fi
|
||||
|
||||
- name: Set version in package
|
||||
run: |
|
||||
cd ${{ inputs.package_dir }}
|
||||
# Replace pdm bump with direct edit of pyproject.toml
|
||||
if [[ "$OSTYPE" == "darwin"* ]]; then
|
||||
# macOS version of sed needs an empty string for -i
|
||||
sed -i '' "s/version = \".*\"/version = \"$VERSION\"/" pyproject.toml
|
||||
else
|
||||
# Linux version
|
||||
sed -i "s/version = \".*\"/version = \"$VERSION\"/" pyproject.toml
|
||||
fi
|
||||
# Verify version was updated
|
||||
echo "Updated version in pyproject.toml:"
|
||||
grep "version =" pyproject.toml
|
||||
|
||||
# Conditional step for lume binary download (only for pylume package)
|
||||
- name: Download and setup lume binary
|
||||
if: inputs.is_lume_package
|
||||
run: |
|
||||
# Create a temporary directory for extraction
|
||||
mkdir -p temp_lume
|
||||
|
||||
# Download the latest lume release directly
|
||||
echo "Downloading latest lume version..."
|
||||
curl -sL "https://github.com/trycua/lume/releases/latest/download/lume.tar.gz" -o temp_lume/lume.tar.gz
|
||||
|
||||
# Extract the tar file (ignore ownership and suppress warnings)
|
||||
cd temp_lume && tar --no-same-owner -xzf lume.tar.gz
|
||||
|
||||
# Make the binary executable
|
||||
chmod +x lume
|
||||
|
||||
# Copy the lume binary to the correct location in the pylume package
|
||||
mkdir -p "${GITHUB_WORKSPACE}/${{ inputs.package_dir }}/pylume"
|
||||
cp lume "${GITHUB_WORKSPACE}/${{ inputs.package_dir }}/pylume/lume"
|
||||
|
||||
# Verify the binary exists and is executable
|
||||
test -x "${GITHUB_WORKSPACE}/${{ inputs.package_dir }}/pylume/lume" || { echo "lume binary not found or not executable"; exit 1; }
|
||||
|
||||
# Get the version from the downloaded binary for reference
|
||||
LUME_VERSION=$(./lume --version | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' || echo "unknown")
|
||||
echo "Using lume version: $LUME_VERSION"
|
||||
|
||||
# Cleanup
|
||||
cd "${GITHUB_WORKSPACE}" && rm -rf temp_lume
|
||||
|
||||
# Save the lume version for reference
|
||||
echo "LUME_VERSION=${LUME_VERSION}" >> $GITHUB_ENV
|
||||
|
||||
- name: Build and publish
|
||||
env:
|
||||
PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
|
||||
run: |
|
||||
cd ${{ inputs.package_dir }}
|
||||
# Build with PDM
|
||||
pdm build
|
||||
|
||||
# For pylume package, verify the binary is in the wheel
|
||||
if [ "${{ inputs.is_lume_package }}" = "true" ]; then
|
||||
python -m pip install wheel
|
||||
wheel unpack dist/*.whl --dest temp_wheel
|
||||
echo "Listing contents of wheel directory:"
|
||||
find temp_wheel -type f
|
||||
test -f temp_wheel/pylume-*/pylume/lume || { echo "lume binary not found in wheel"; exit 1; }
|
||||
rm -rf temp_wheel
|
||||
echo "Publishing ${{ inputs.base_package_name }} ${VERSION} with lume ${LUME_VERSION}"
|
||||
else
|
||||
echo "Publishing ${{ inputs.base_package_name }} ${VERSION}"
|
||||
fi
|
||||
|
||||
# Install and use twine directly instead of PDM publish
|
||||
echo "Installing twine for direct publishing..."
|
||||
pip install twine
|
||||
|
||||
echo "Publishing to PyPI using twine..."
|
||||
TWINE_USERNAME="__token__" TWINE_PASSWORD="$PYPI_TOKEN" python -m twine upload dist/*
|
||||
|
||||
# Save the wheel file path for the release
|
||||
WHEEL_FILE=$(ls dist/*.whl | head -1)
|
||||
echo "WHEEL_FILE=${WHEEL_FILE}" >> $GITHUB_ENV
|
||||
|
||||
- name: Prepare Simple Release Notes
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
run: |
|
||||
# Create release notes based on package type
|
||||
echo "# ${{ inputs.base_package_name }} v${VERSION}" > release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
|
||||
if [ "${{ inputs.package_name }}" = "pylume" ]; then
|
||||
echo "## Python SDK for lume - run macOS and Linux VMs on Apple Silicon" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "This package provides Python bindings for the lume virtualization tool." >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* lume binary: v${LUME_VERSION}" >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "computer" ]; then
|
||||
echo "## Computer control library for the Computer Universal Automation (CUA) project" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* pylume: ${PYLUME_VERSION:-latest}" >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "agent" ]; then
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* cua-computer: ${COMPUTER_VERSION:-latest}" >> release_notes.md
|
||||
echo "* cua-som: ${SOM_VERSION:-latest}" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Installation Options" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "### Basic installation with Anthropic" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install cua-agent[anthropic]==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "### With SOM (recommended)" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install cua-agent[som]==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "### All features" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install cua-agent[all]==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "som" ]; then
|
||||
echo "## Computer Vision and OCR library for detecting and analyzing UI elements" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "This package provides enhanced UI understanding capabilities through computer vision and OCR." >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "computer-server" ]; then
|
||||
echo "## Computer Server for the Computer Universal Automation (CUA) project" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "A FastAPI-based server implementation for computer control." >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* cua-computer: ${COMPUTER_VERSION:-latest}" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Usage" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "# Run the server" >> release_notes.md
|
||||
echo "cua-computer-server" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
elif [ "${{ inputs.package_name }}" = "mcp-server" ]; then
|
||||
echo "## MCP Server for the Computer-Use Agent (CUA)" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "This package provides MCP (Model Context Protocol) integration for CUA agents, allowing them to be used with Claude Desktop, Cursor, and other MCP clients." >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Dependencies" >> release_notes.md
|
||||
echo "* cua-computer: ${COMPUTER_VERSION:-latest}" >> release_notes.md
|
||||
echo "* cua-agent: ${AGENT_VERSION:-latest}" >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Usage" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "# Run the MCP server directly" >> release_notes.md
|
||||
echo "cua-mcp-server" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
echo "" >> release_notes.md
|
||||
echo "## Claude Desktop Integration" >> release_notes.md
|
||||
echo "Add to your Claude Desktop configuration (~/.config/claude-desktop/claude_desktop_config.json or OS-specific location):" >> release_notes.md
|
||||
echo '```json' >> release_notes.md
|
||||
echo '"mcpServers": {' >> release_notes.md
|
||||
echo ' "cua-agent": {' >> release_notes.md
|
||||
echo ' "command": "cua-mcp-server",' >> release_notes.md
|
||||
echo ' "args": [],' >> release_notes.md
|
||||
echo ' "env": {' >> release_notes.md
|
||||
echo ' "CUA_AGENT_LOOP": "OMNI",' >> release_notes.md
|
||||
echo ' "CUA_MODEL_PROVIDER": "ANTHROPIC",' >> release_notes.md
|
||||
echo ' "CUA_MODEL_NAME": "claude-3-opus-20240229",' >> release_notes.md
|
||||
echo ' "ANTHROPIC_API_KEY": "your-api-key",' >> release_notes.md
|
||||
echo ' "PYTHONIOENCODING": "utf-8"' >> release_notes.md
|
||||
echo ' }' >> release_notes.md
|
||||
echo ' }' >> release_notes.md
|
||||
echo '}' >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
fi
|
||||
|
||||
# Add installation section if not agent (which has its own installation section)
|
||||
if [ "${{ inputs.package_name }}" != "agent" ]; then
|
||||
echo "" >> release_notes.md
|
||||
echo "## Installation" >> release_notes.md
|
||||
echo '```bash' >> release_notes.md
|
||||
echo "pip install ${{ inputs.base_package_name }}==${VERSION}" >> release_notes.md
|
||||
echo '```' >> release_notes.md
|
||||
fi
|
||||
|
||||
echo "Release notes created:"
|
||||
cat release_notes.md
|
||||
|
||||
- name: Create GitHub Release
|
||||
uses: softprops/action-gh-release@v2
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
with:
|
||||
name: "${{ inputs.base_package_name }} v${{ env.VERSION }}"
|
||||
body_path: release_notes.md
|
||||
files: ${{ inputs.package_dir }}/${{ env.WHEEL_FILE }}
|
||||
draft: false
|
||||
prerelease: false
|
||||
make_latest: ${{ inputs.package_name == 'lume' }}
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
6
.gitignore
vendored
6
.gitignore
vendored
@@ -6,6 +6,10 @@ __pycache__/
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
node_modules/*
|
||||
*/node_modules
|
||||
**/node_modules
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
@@ -155,7 +159,7 @@ weights/icon_detect/model.pt
|
||||
weights/icon_detect/model.pt.zip
|
||||
weights/icon_detect/model.pt.zip.part*
|
||||
|
||||
libs/omniparser/weights/icon_detect/model.pt
|
||||
libs/python/omniparser/weights/icon_detect/model.pt
|
||||
|
||||
# Example test data and output
|
||||
examples/test_data/
|
||||
|
||||
57
.vscode/launch.json
vendored
57
.vscode/launch.json
vendored
@@ -1,5 +1,31 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "Agent UI",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/agent_ui_examples.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Computer UI",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/computer_ui_examples.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Computer Examples",
|
||||
"type": "debugpy",
|
||||
@@ -10,7 +36,7 @@
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -23,20 +49,7 @@
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Agent UI Examples",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/agent_ui_examples.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -49,7 +62,7 @@
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -71,7 +84,7 @@
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -93,27 +106,27 @@
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Computer Server",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/libs/computer-server/run_server.py",
|
||||
"program": "${workspaceFolder}/libs/python/computer-server/run_server.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": true,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer:${workspaceFolder:cua-root}/libs/python/agent:${workspaceFolder:cua-root}/libs/python/som:${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Computer Server with Args",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/libs/computer-server/run_server.py",
|
||||
"program": "${workspaceFolder}/libs/python/computer-server/run_server.py",
|
||||
"args": [
|
||||
"--host",
|
||||
"0.0.0.0",
|
||||
@@ -127,7 +140,7 @@
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer-server"
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/python/core:${workspaceFolder:cua-root}/libs/python/computer-server"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
13
.vscode/libs-ts.code-workspace
vendored
Normal file
13
.vscode/libs-ts.code-workspace
vendored
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"folders": [
|
||||
{
|
||||
"name": "libs-ts",
|
||||
"path": "../libs/typescript"
|
||||
}
|
||||
],
|
||||
"extensions": {
|
||||
"recommendations": [
|
||||
"biomejs.biome",
|
||||
]
|
||||
}
|
||||
}
|
||||
149
.vscode/py.code-workspace
vendored
149
.vscode/py.code-workspace
vendored
@@ -6,27 +6,27 @@
|
||||
},
|
||||
{
|
||||
"name": "computer",
|
||||
"path": "../libs/computer"
|
||||
"path": "../libs/python/computer"
|
||||
},
|
||||
{
|
||||
"name": "agent",
|
||||
"path": "../libs/agent"
|
||||
"path": "../libs/python/agent"
|
||||
},
|
||||
{
|
||||
"name": "som",
|
||||
"path": "../libs/som"
|
||||
"path": "../libs/python/som"
|
||||
},
|
||||
{
|
||||
"name": "computer-server",
|
||||
"path": "../libs/computer-server"
|
||||
"path": "../libs/python/computer-server"
|
||||
},
|
||||
{
|
||||
"name": "pylume",
|
||||
"path": "../libs/pylume"
|
||||
"path": "../libs/python/pylume"
|
||||
},
|
||||
{
|
||||
"name": "core",
|
||||
"path": "../libs/core"
|
||||
"path": "../libs/python/core"
|
||||
}
|
||||
],
|
||||
"settings": {
|
||||
@@ -47,11 +47,11 @@
|
||||
"libs"
|
||||
],
|
||||
"python.analysis.extraPaths": [
|
||||
"${workspaceFolder:cua-root}/libs/core",
|
||||
"${workspaceFolder:cua-root}/libs/computer",
|
||||
"${workspaceFolder:cua-root}/libs/agent",
|
||||
"${workspaceFolder:cua-root}/libs/som",
|
||||
"${workspaceFolder:cua-root}/libs/pylume",
|
||||
"${workspaceFolder:cua-root}/libs/python/core",
|
||||
"${workspaceFolder:cua-root}/libs/python/computer",
|
||||
"${workspaceFolder:cua-root}/libs/python/agent",
|
||||
"${workspaceFolder:cua-root}/libs/python/som",
|
||||
"${workspaceFolder:cua-root}/libs/python/pylume",
|
||||
"${workspaceFolder:cua-root}/.vscode/typings"
|
||||
],
|
||||
"python.envFile": "${workspaceFolder:cua-root}/.env",
|
||||
@@ -99,11 +99,11 @@
|
||||
}
|
||||
],
|
||||
"python.autoComplete.extraPaths": [
|
||||
"${workspaceFolder:cua-root}/libs/core",
|
||||
"${workspaceFolder:cua-root}/libs/computer",
|
||||
"${workspaceFolder:cua-root}/libs/agent",
|
||||
"${workspaceFolder:cua-root}/libs/som",
|
||||
"${workspaceFolder:cua-root}/libs/pylume"
|
||||
"${workspaceFolder:cua-root}/libs/python/core",
|
||||
"${workspaceFolder:cua-root}/libs/python/computer",
|
||||
"${workspaceFolder:cua-root}/libs/python/agent",
|
||||
"${workspaceFolder:cua-root}/libs/python/som",
|
||||
"${workspaceFolder:cua-root}/libs/python/pylume"
|
||||
],
|
||||
"python.languageServer": "None",
|
||||
"[python]": {
|
||||
@@ -118,8 +118,8 @@
|
||||
"examples/agent_examples.py": "python"
|
||||
},
|
||||
"python.interpreterPaths": {
|
||||
"examples/computer_examples.py": "${workspaceFolder}/libs/computer/.venv/bin/python",
|
||||
"examples/agent_examples.py": "${workspaceFolder}/libs/agent/.venv/bin/python"
|
||||
"examples/computer_examples.py": "${workspaceFolder}/libs/python/computer/.venv/bin/python",
|
||||
"examples/agent_examples.py": "${workspaceFolder}/libs/python/agent/.venv/bin/python"
|
||||
}
|
||||
},
|
||||
"tasks": {
|
||||
@@ -148,119 +148,6 @@
|
||||
}
|
||||
]
|
||||
},
|
||||
"launch": {
|
||||
"version": "0.2.0",
|
||||
"configurations": [
|
||||
{
|
||||
"name": "Run Computer Examples",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/computer_examples.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": true,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Agent Examples",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/agent_examples.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run PyLume Examples",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/pylume_examples.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": true,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "SOM: Run Experiments (No OCR)",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/som_examples.py",
|
||||
"args": [
|
||||
"examples/test_data",
|
||||
"--output-dir", "examples/output",
|
||||
"--ocr", "none",
|
||||
"--mode", "experiment"
|
||||
],
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "SOM: Run Experiments (EasyOCR)",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "examples/som_examples.py",
|
||||
"args": [
|
||||
"examples/test_data",
|
||||
"--output-dir", "examples/output",
|
||||
"--ocr", "easyocr",
|
||||
"--mode", "experiment"
|
||||
],
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Computer Server",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/libs/computer-server/run_server.py",
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": true,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer:${workspaceFolder:cua-root}/libs/agent:${workspaceFolder:cua-root}/libs/som:${workspaceFolder:cua-root}/libs/pylume"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Run Computer Server with Args",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/libs/computer-server/run_server.py",
|
||||
"args": [
|
||||
"--host", "0.0.0.0",
|
||||
"--port", "8000",
|
||||
"--log-level", "debug"
|
||||
],
|
||||
"console": "integratedTerminal",
|
||||
"justMyCode": false,
|
||||
"python": "${workspaceFolder:cua-root}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder:cua-root}",
|
||||
"env": {
|
||||
"PYTHONPATH": "${workspaceFolder:cua-root}/libs/core:${workspaceFolder:cua-root}/libs/computer-server"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"compounds": [
|
||||
{
|
||||
"name": "Run Computer Examples + Server",
|
||||
|
||||
86
COMPATIBILITY.md
Normal file
86
COMPATIBILITY.md
Normal file
@@ -0,0 +1,86 @@
|
||||
# C/ua Compatibility Matrix
|
||||
|
||||
## Table of Contents
|
||||
- [Host OS Compatibility](#host-os-compatibility)
|
||||
- [macOS Host](#macos-host)
|
||||
- [Ubuntu/Linux Host](#ubuntulinux-host)
|
||||
- [Windows Host](#windows-host)
|
||||
- [VM Emulation Support](#vm-emulation-support)
|
||||
- [Model Provider Compatibility](#model-provider-compatibility)
|
||||
|
||||
---
|
||||
|
||||
## Host OS Compatibility
|
||||
|
||||
*This section shows compatibility based on your **host operating system** (the OS you're running C/ua on).*
|
||||
|
||||
### macOS Host
|
||||
|
||||
| Installation Method | Requirements | Lume | Cloud | Notes |
|
||||
|-------------------|-------------|------|-------|-------|
|
||||
| **playground-docker.sh** | Docker Desktop | ✅ Full | ✅ Full | Recommended for quick setup |
|
||||
| **Dev Container** | VS Code/WindSurf + Docker | ✅ Full | ✅ Full | Best for development |
|
||||
| **PyPI packages** | Python 3.12+ | ✅ Full | ✅ Full | Most flexible |
|
||||
|
||||
**macOS Host Requirements:**
|
||||
- macOS 15+ (Sequoia) for local VM support
|
||||
- Apple Silicon (M1/M2/M3/M4) recommended for best performance
|
||||
- Docker Desktop for containerized installations
|
||||
|
||||
---
|
||||
|
||||
### Ubuntu/Linux Host
|
||||
|
||||
| Installation Method | Requirements | Lume | Cloud | Notes |
|
||||
|-------------------|-------------|------|-------|-------|
|
||||
| **playground-docker.sh** | Docker Engine | ✅ Full | ✅ Full | Recommended for quick setup |
|
||||
| **Dev Container** | VS Code/WindSurf + Docker | ✅ Full | ✅ Full | Best for development |
|
||||
| **PyPI packages** | Python 3.12+ | ✅ Full | ✅ Full | Most flexible |
|
||||
|
||||
**Ubuntu/Linux Host Requirements:**
|
||||
- Ubuntu 20.04+ or equivalent Linux distribution
|
||||
- Docker Engine or Docker Desktop
|
||||
- Python 3.12+ for PyPI installation
|
||||
|
||||
---
|
||||
|
||||
### Windows Host
|
||||
|
||||
| Installation Method | Requirements | Lume | Winsandbox | Cloud | Notes |
|
||||
|-------------------|-------------|------|------------|-------|-------|
|
||||
| **playground-docker.sh** | Docker Desktop + WSL2 | ❌ Not supported | ❌ Not supported | ✅ Full | Requires WSL2 |
|
||||
| **Dev Container** | VS Code/WindSurf + Docker + WSL2 | ❌ Not supported | ❌ Not supported | ✅ Full | Requires WSL2 |
|
||||
| **PyPI packages** | Python 3.12+ | ❌ Not supported | ✅ Full | ✅ Full | |
|
||||
|
||||
**Windows Host Requirements:**
|
||||
- Windows 10/11 with WSL2 enabled for shell script execution
|
||||
- Docker Desktop with WSL2 backend
|
||||
- Windows Sandbox feature enabled (for Winsandbox support)
|
||||
- Python 3.12+ installed in WSL2 or Windows
|
||||
- **Note**: Lume CLI is not available on Windows - use Cloud or Winsandbox providers
|
||||
|
||||
---
|
||||
|
||||
## VM Emulation Support
|
||||
|
||||
*This section shows which **virtual machine operating systems** each provider can emulate.*
|
||||
|
||||
| Provider | macOS VM | Ubuntu/Linux VM | Windows VM | Notes |
|
||||
|----------|----------|-----------------|------------|-------|
|
||||
| **Lume** | ✅ Full support | ⚠️ Limited support | ⚠️ Limited support | macOS: native; Ubuntu/Linux/Windows: need custom image |
|
||||
| **Cloud** | 🚧 Coming soon | ✅ Full support | 🚧 Coming soon | Currently Ubuntu only, macOS/Windows in development |
|
||||
| **Winsandbox** | ❌ Not supported | ❌ Not supported | ✅ Windows only | Windows 10/11 environments only |
|
||||
|
||||
---
|
||||
|
||||
## Model Provider Compatibility
|
||||
|
||||
*This section shows which **AI model providers** are supported on each host operating system.*
|
||||
|
||||
| Provider | macOS Host | Ubuntu/Linux Host | Windows Host | Notes |
|
||||
|----------|------------|-------------------|--------------|-------|
|
||||
| **Anthropic** | ✅ Full support | ✅ Full support | ✅ Full support | Cloud-based API |
|
||||
| **OpenAI** | ✅ Full support | ✅ Full support | ✅ Full support | Cloud-based API |
|
||||
| **Ollama** | ✅ Full support | ✅ Full support | ✅ Full support | Local model serving |
|
||||
| **OpenAI Compatible** | ✅ Full support | ✅ Full support | ✅ Full support | Any OpenAI-compatible API endpoint |
|
||||
| **MLX VLM** | ✅ macOS only | ❌ Not supported | ❌ Not supported | Apple Silicon required. PyPI installation only. |
|
||||
@@ -1,11 +1,11 @@
|
||||
FROM python:3.11-slim
|
||||
FROM python:3.12-slim
|
||||
|
||||
# Set environment variables
|
||||
ENV PYTHONUNBUFFERED=1 \
|
||||
PYTHONDONTWRITEBYTECODE=1 \
|
||||
PIP_NO_CACHE_DIR=1 \
|
||||
PIP_DISABLE_PIP_VERSION_CHECK=1 \
|
||||
PYTHONPATH="/app/libs/core:/app/libs/computer:/app/libs/agent:/app/libs/som:/app/libs/pylume:/app/libs/computer-server"
|
||||
PYTHONPATH="/app/libs/python/core:/app/libs/python/computer:/app/libs/python/agent:/app/libs/python/som:/app/libs/python/pylume:/app/libs/python/computer-server:/app/libs/python/mcp-server"
|
||||
|
||||
# Install system dependencies for ARM architecture
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
@@ -21,6 +21,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
iputils-ping \
|
||||
net-tools \
|
||||
sed \
|
||||
xxd \
|
||||
&& apt-get clean \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
|
||||
137
README.md
137
README.md
@@ -51,71 +51,72 @@
|
||||
|
||||
**Need to automate desktop tasks? Launch the Computer-Use Agent UI with a single command.**
|
||||
|
||||
### Option 1: Fully-managed install (recommended)
|
||||
### Option 1: Fully-managed install with Docker (recommended)
|
||||
|
||||
*I want to be totally guided in the process*
|
||||
*Docker-based guided install for quick use*
|
||||
|
||||
**macOS/Linux/Windows (via WSL):**
|
||||
|
||||
```bash
|
||||
# Requires Python 3.11+
|
||||
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/scripts/playground.sh)"
|
||||
# Requires Docker
|
||||
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/scripts/playground-docker.sh)"
|
||||
```
|
||||
|
||||
This script will:
|
||||
|
||||
- Ask if you want to use local VMs or C/ua Cloud Containers
|
||||
- Install necessary dependencies (Lume CLI for local VMs)
|
||||
- Download VM images if needed
|
||||
- Install Python packages
|
||||
- Launch the Computer-Use Agent UI
|
||||
|
||||
### Option 2: Key manual steps
|
||||
|
||||
<details>
|
||||
<summary>If you are skeptical running one-install scripts</summary>
|
||||
|
||||
**For C/ua Agent UI (any system, cloud VMs only):**
|
||||
|
||||
```bash
|
||||
# Requires Python 3.11+ and C/ua API key
|
||||
pip install -U "cua-computer[all]" "cua-agent[all]"
|
||||
python -m agent.ui.gradio.app
|
||||
```
|
||||
|
||||
**For Local macOS/Linux VMs (Apple Silicon only):**
|
||||
|
||||
```bash
|
||||
# 1. Install Lume CLI
|
||||
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"
|
||||
|
||||
# 2. Pull macOS image
|
||||
lume pull macos-sequoia-cua:latest
|
||||
|
||||
# 3. Start VM
|
||||
lume run macos-sequoia-cua:latest
|
||||
|
||||
# 4. Install packages and launch UI
|
||||
pip install -U "cua-computer[all]" "cua-agent[all]"
|
||||
python -m agent.ui.gradio.app
|
||||
```
|
||||
|
||||
</details>
|
||||
This script will guide you through setup using Docker containers and launch the Computer-Use Agent UI.
|
||||
|
||||
---
|
||||
|
||||
*How it works: Computer module provides secure desktops (Lume CLI locally, [C/ua Cloud Containers](https://trycua.com) remotely), Agent module provides local/API agents with OpenAI AgentResponse format and [trajectory tracing](https://trycua.com/trajectory-viewer).*
|
||||
### Option 2: [Dev Container](./.devcontainer/README.md)
|
||||
|
||||
### Supported [Agent Loops](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops)
|
||||
*Best for contributors and development*
|
||||
|
||||
- [UITARS-1.5](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Run locally on Apple Silicon with MLX, or use cloud providers
|
||||
- [OpenAI CUA](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Use OpenAI's Computer-Use Preview model
|
||||
- [Anthropic CUA](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Use Anthropic's Computer-Use capabilities
|
||||
- [OmniParser-v2.0](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Control UI with [Set-of-Marks prompting](https://som-gpt4v.github.io/) using any vision model
|
||||
This repository includes a [Dev Container](./.devcontainer/README.md) configuration that simplifies setup to a few steps:
|
||||
|
||||
# 💻 Developer Guide
|
||||
1. **Install the Dev Containers extension ([VS Code](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) or [WindSurf](https://docs.windsurf.com/windsurf/advanced#dev-containers-beta))**
|
||||
2. **Open the repository in the Dev Container:**
|
||||
- Press `Ctrl+Shift+P` (or `⌘+Shift+P` on macOS)
|
||||
- Select `Dev Containers: Clone Repository in Container Volume...` and paste the repository URL: `https://github.com/trycua/cua.git` (if not cloned) or `Dev Containers: Open Folder in Container...` (if git cloned).
|
||||
> **Note**: On WindSurf, the post install hook might not run automatically. If so, run `/bin/bash .devcontainer/post-install.sh` manually.
|
||||
3. **Open the VS Code workspace:** Once the post-install.sh is done running, open the `.vscode/py.code-workspace` workspace and press 
|
||||
.
|
||||
4. **Run the Agent UI example:** Click 
|
||||
to start the Gradio UI. If prompted to install **debugpy (Python Debugger)** to enable remote debugging, select 'Yes' to proceed.
|
||||
5. **Access the Gradio UI:** The Gradio UI will be available at `http://localhost:7860` and will automatically forward to your host machine.
|
||||
|
||||
Follow these steps to use C/ua in your own code. See [Developer Guide](https://docs.trycua.com/home/developer-guide) for building from source.
|
||||
---
|
||||
|
||||
### Option 3: PyPI
|
||||
|
||||
*Direct Python package installation*
|
||||
|
||||
```bash
|
||||
# conda create -yn cua python==3.12
|
||||
|
||||
pip install -U "cua-computer[all]" "cua-agent[all]"
|
||||
python -m agent.ui # Start the agent UI
|
||||
```
|
||||
|
||||
Or check out the [Usage Guide](#-usage-guide) to learn how to use our Python SDK in your own code.
|
||||
|
||||
---
|
||||
|
||||
## Supported [Agent Loops](https://github.com/trycua/cua/blob/main/libs/python/agent/README.md#agent-loops)
|
||||
|
||||
- [UITARS-1.5](https://github.com/trycua/cua/blob/main/libs/python/agent/README.md#agent-loops) - Run locally on Apple Silicon with MLX, or use cloud providers
|
||||
- [OpenAI CUA](https://github.com/trycua/cua/blob/main/libs/python/agent/README.md#agent-loops) - Use OpenAI's Computer-Use Preview model
|
||||
- [Anthropic CUA](https://github.com/trycua/cua/blob/main/libs/python/agent/README.md#agent-loops) - Use Anthropic's Computer-Use capabilities
|
||||
- [OmniParser-v2.0](https://github.com/trycua/cua/blob/main/libs/python/agent/README.md#agent-loops) - Control UI with [Set-of-Marks prompting](https://som-gpt4v.github.io/) using any vision model
|
||||
|
||||
## 🖥️ Compatibility
|
||||
|
||||
For detailed compatibility information including host OS support, VM emulation capabilities, and model provider compatibility, see the [Compatibility Matrix](./COMPATIBILITY.md).
|
||||
|
||||
<br/>
|
||||
<br/>
|
||||
|
||||
# 🐍 Usage Guide
|
||||
|
||||
Follow these steps to use C/ua in your own Python code. See [Developer Guide](./docs/Developer-Guide.md) for building from source.
|
||||
|
||||
### Step 1: Install Lume CLI
|
||||
|
||||
@@ -227,8 +228,8 @@ docker run -it --rm \
|
||||
|
||||
## Resources
|
||||
|
||||
- [How to use the MCP Server with Claude Desktop or other MCP clients](./libs/mcp-server/README.md) - One of the easiest ways to get started with C/ua
|
||||
- [How to use OpenAI Computer-Use, Anthropic, OmniParser, or UI-TARS for your Computer-Use Agent](./libs/agent/README.md)
|
||||
- [How to use the MCP Server with Claude Desktop or other MCP clients](./libs/python/mcp-server/README.md) - One of the easiest ways to get started with C/ua
|
||||
- [How to use OpenAI Computer-Use, Anthropic, OmniParser, or UI-TARS for your Computer-Use Agent](./libs/python/agent/README.md)
|
||||
- [How to use Lume CLI for managing desktops](./libs/lume/README.md)
|
||||
- [Training Computer-Use Models: Collecting Human Trajectories with C/ua (Part 1)](https://www.trycua.com/blog/training-computer-use-models-trajectories-1)
|
||||
- [Build Your Own Operator on macOS (Part 1)](https://www.trycua.com/blog/build-your-own-operator-on-macos-1)
|
||||
@@ -239,13 +240,14 @@ docker run -it --rm \
|
||||
|--------|-------------|---------------|
|
||||
| [**Lume**](./libs/lume/README.md) | VM management for macOS/Linux using Apple's Virtualization.Framework | `curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh \| bash` |
|
||||
| [**Lumier**](./libs/lumier/README.md) | Docker interface for macOS and Linux VMs | `docker pull trycua/lumier:latest` |
|
||||
| [**Computer**](./libs/computer/README.md) | Interface for controlling virtual machines | `pip install "cua-computer[all]"` |
|
||||
| [**Agent**](./libs/agent/README.md) | AI agent framework for automating tasks | `pip install "cua-agent[all]"` |
|
||||
| [**MCP Server**](./libs/mcp-server/README.md) | MCP server for using CUA with Claude Desktop | `pip install cua-mcp-server` |
|
||||
| [**SOM**](./libs/som/README.md) | Self-of-Mark library for Agent | `pip install cua-som` |
|
||||
| [**PyLume**](./libs/pylume/README.md) | Python bindings for Lume | `pip install pylume` |
|
||||
| [**Computer Server**](./libs/computer-server/README.md) | Server component for Computer | `pip install cua-computer-server` |
|
||||
| [**Core**](./libs/core/README.md) | Core utilities | `pip install cua-core` |
|
||||
| [**Computer (Python)**](./libs/python/computer/README.md) | Python Interface for controlling virtual machines | `pip install "cua-computer[all]"` |
|
||||
| [**Computer (Typescript)**](./libs/typescript/computer/README.md) | Typescript Interface for controlling virtual machines | `npm install @trycua/computer` |
|
||||
| [**Agent**](./libs/python/agent/README.md) | AI agent framework for automating tasks | `pip install "cua-agent[all]"` |
|
||||
| [**MCP Server**](./libs/python/mcp-server/README.md) | MCP server for using CUA with Claude Desktop | `pip install cua-mcp-server` |
|
||||
| [**SOM**](./libs/python/som/README.md) | Self-of-Mark library for Agent | `pip install cua-som` |
|
||||
| [**Computer Server**](./libs/python/computer-server/README.md) | Server component for Computer | `pip install cua-computer-server` |
|
||||
| [**Core (Python)**](./libs/python/core/README.md) | Python Core utilities | `pip install cua-core` |
|
||||
| [**Core (Typescript)**](./libs/typescript/core/README.md) | Typescript Core utilities | `npm install @trycua/core` |
|
||||
|
||||
## Computer Interface Reference
|
||||
|
||||
@@ -253,7 +255,8 @@ For complete examples, see [computer_examples.py](./examples/computer_examples.p
|
||||
|
||||
```python
|
||||
# Shell Actions
|
||||
await computer.interface.run_command(cmd) # Run shell command
|
||||
result = await computer.interface.run_command(cmd) # Run shell command
|
||||
# result.stdout, result.stderr, result.returncode
|
||||
|
||||
# Mouse Actions
|
||||
await computer.interface.left_click(x, y) # Left click at coordinates
|
||||
@@ -288,8 +291,8 @@ await computer.interface.copy_to_clipboard() # Get clipboard content
|
||||
# File System Operations
|
||||
await computer.interface.file_exists(path) # Check if file exists
|
||||
await computer.interface.directory_exists(path) # Check if directory exists
|
||||
await computer.interface.read_text(path) # Read file content
|
||||
await computer.interface.write_text(path, content) # Write file content
|
||||
await computer.interface.read_text(path, encoding="utf-8") # Read file content
|
||||
await computer.interface.write_text(path, content, encoding="utf-8") # Write file content
|
||||
await computer.interface.read_bytes(path) # Read file content as bytes
|
||||
await computer.interface.write_bytes(path, content) # Write file content as bytes
|
||||
await computer.interface.delete_file(path) # Delete file
|
||||
@@ -399,14 +402,6 @@ Thank you to all our supporters!
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://ricterz.me"><img src="https://avatars.githubusercontent.com/u/5282759?v=4?s=100" width="100px;" alt="Ricter Zheng"/><br /><sub><b>Ricter Zheng</b></sub></a><br /><a href="#code-RicterZ" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://www.trytruffle.ai/"><img src="https://avatars.githubusercontent.com/u/50844303?v=4?s=100" width="100px;" alt="Rahul Karajgikar"/><br /><sub><b>Rahul Karajgikar</b></sub></a><br /><a href="#code-rahulkarajgikar" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://github.com/trospix"><img src="https://avatars.githubusercontent.com/u/81363696?v=4?s=100" width="100px;" alt="trospix"/><br /><sub><b>trospix</b></sub></a><br /><a href="#code-trospix" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://wavee.world/invitation/b96d00e6-b802-4a1b-8a66-2e3854a01ffd"><img src="https://avatars.githubusercontent.com/u/22633385?v=4?s=100" width="100px;" alt="Ikko Eltociear Ashimine"/><br /><sub><b>Ikko Eltociear Ashimine</b></sub></a><br /><a href="#code-eltociear" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://github.com/dp221125"><img src="https://avatars.githubusercontent.com/u/10572119?v=4?s=100" width="100px;" alt="한석호(MilKyo)"/><br /><sub><b>한석호(MilKyo)</b></sub></a><br /><a href="#code-dp221125" title="Code">💻</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://www.encona.com/"><img src="https://avatars.githubusercontent.com/u/891558?v=4?s=100" width="100px;" alt="Rahim Nathwani"/><br /><sub><b>Rahim Nathwani</b></sub></a><br /><a href="#code-rahimnathwani" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://mjspeck.github.io/"><img src="https://avatars.githubusercontent.com/u/20689127?v=4?s=100" width="100px;" alt="Matt Speck"/><br /><sub><b>Matt Speck</b></sub></a><br /><a href="#code-mjspeck" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://github.com/FinnBorge"><img src="https://avatars.githubusercontent.com/u/9272726?v=4?s=100" width="100px;" alt="FinnBorge"/><br /><sub><b>FinnBorge</b></sub></a><br /><a href="#code-FinnBorge" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://github.com/jklapacz"><img src="https://avatars.githubusercontent.com/u/5343758?v=4?s=100" width="100px;" alt="Jakub Klapacz"/><br /><sub><b>Jakub Klapacz</b></sub></a><br /><a href="#code-jklapacz" title="Code">💻</a></td>
|
||||
<td align="center" valign="top" width="14.28%"><a href="https://github.com/evnsnclr"><img src="https://avatars.githubusercontent.com/u/139897548?v=4?s=100" width="100px;" alt="Evan smith"/><br /><sub><b>Evan smith</b></sub></a><br /><a href="#code-evnsnclr" title="Code">💻</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
||||
293
docs/Developer-Guide.md
Normal file
293
docs/Developer-Guide.md
Normal file
@@ -0,0 +1,293 @@
|
||||
# Getting Started
|
||||
|
||||
## Project Structure
|
||||
|
||||
The project is organized as a monorepo with these main packages:
|
||||
|
||||
### Python
|
||||
- `libs/python/core/` - Base package with telemetry support
|
||||
- `libs/python/computer/` - Computer-use interface (CUI) library
|
||||
- `libs/python/agent/` - AI agent library with multi-provider support
|
||||
- `libs/python/som/` - Set-of-Mark parser
|
||||
- `libs/python/computer-server/` - Server component for VM
|
||||
- `libs/python/pylume/` - Python bindings for Lume
|
||||
|
||||
### TypeScript
|
||||
- `libs/typescript/computer/` - Computer-use interface (CUI) library
|
||||
- `libs/typescript/agent/` - AI agent library with multi-provider support
|
||||
|
||||
### Other
|
||||
- `libs/lume/` - Lume CLI
|
||||
|
||||
Each package has its own virtual environment and dependencies, managed through PDM.
|
||||
|
||||
## Local Development Setup
|
||||
|
||||
1. Install Lume CLI:
|
||||
|
||||
```bash
|
||||
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"
|
||||
```
|
||||
|
||||
2. Clone the repository:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/trycua/cua.git
|
||||
cd cua
|
||||
```
|
||||
|
||||
3. Create a `.env.local` file in the root directory with your API keys:
|
||||
|
||||
```bash
|
||||
# Required for Anthropic provider
|
||||
ANTHROPIC_API_KEY=your_anthropic_key_here
|
||||
|
||||
# Required for OpenAI provider
|
||||
OPENAI_API_KEY=your_openai_key_here
|
||||
```
|
||||
|
||||
4. Open the workspace in VSCode or Cursor:
|
||||
|
||||
```bash
|
||||
# For Cua Python development
|
||||
code .vscode/py.code-workspace
|
||||
|
||||
# For Lume (Swift) development
|
||||
code .vscode/lume.code-workspace
|
||||
```
|
||||
|
||||
Using the workspace file is strongly recommended as it:
|
||||
|
||||
- Sets up correct Python environments for each package
|
||||
- Configures proper import paths
|
||||
- Enables debugging configurations
|
||||
- Maintains consistent settings across packages
|
||||
|
||||
## Lume Development
|
||||
|
||||
Refer to the [Lume README](../libs/lume/docs/Development.md) for instructions on how to develop the Lume CLI.
|
||||
|
||||
## Python Development
|
||||
|
||||
There are two ways to install Lume:
|
||||
|
||||
### Run the build script
|
||||
|
||||
Run the build script to set up all packages:
|
||||
|
||||
```bash
|
||||
./scripts/build.sh
|
||||
```
|
||||
|
||||
The build script creates a shared virtual environment for all packages. The workspace configuration automatically handles import paths with the correct Python path settings.
|
||||
|
||||
This will:
|
||||
|
||||
- Create a virtual environment for the project
|
||||
- Install all packages in development mode
|
||||
- Set up the correct Python path
|
||||
- Install development tools
|
||||
|
||||
### Install with PDM
|
||||
|
||||
If PDM is not already installed, you can follow the installation instructions [here](https://pdm-project.org/en/latest/#installation).
|
||||
|
||||
To install with PDM, simply run:
|
||||
|
||||
```console
|
||||
pdm install -G:all
|
||||
```
|
||||
|
||||
This installs all the dependencies for development, testing, and building the docs. If you'd only like development dependencies, you can run:
|
||||
|
||||
```console
|
||||
pdm install -d
|
||||
```
|
||||
|
||||
## Running Examples
|
||||
|
||||
The Python workspace includes launch configurations for all packages:
|
||||
|
||||
- "Run Computer Examples" - Runs computer examples
|
||||
- "Run Computer API Server" - Runs the computer-server
|
||||
- "Run Agent Examples" - Runs agent examples
|
||||
- "SOM" configurations - Various settings for running SOM
|
||||
|
||||
To run examples from VSCode / Cursor:
|
||||
|
||||
1. Press F5 or use the Run/Debug view
|
||||
2. Select the desired configuration
|
||||
|
||||
The workspace also includes compound launch configurations:
|
||||
|
||||
- "Run Computer Examples + Server" - Runs both the Computer Examples and Server simultaneously
|
||||
|
||||
## Docker Development Environment
|
||||
|
||||
As an alternative to installing directly on your host machine, you can use Docker for development. This approach has several advantages:
|
||||
|
||||
### Prerequisites
|
||||
|
||||
- Docker installed on your machine
|
||||
- Lume server running on your host (port 7777): `lume serve`
|
||||
|
||||
### Setup and Usage
|
||||
|
||||
1. Build the development Docker image:
|
||||
|
||||
```bash
|
||||
./scripts/run-docker-dev.sh build
|
||||
```
|
||||
|
||||
2. Run an example in the container:
|
||||
|
||||
```bash
|
||||
./scripts/run-docker-dev.sh run computer_examples.py
|
||||
```
|
||||
|
||||
3. Get an interactive shell in the container:
|
||||
|
||||
```bash
|
||||
./scripts/run-docker-dev.sh run --interactive
|
||||
```
|
||||
|
||||
4. Stop any running containers:
|
||||
|
||||
```bash
|
||||
./scripts/run-docker-dev.sh stop
|
||||
```
|
||||
|
||||
### How it Works
|
||||
|
||||
The Docker development environment:
|
||||
|
||||
- Installs all required Python dependencies in the container
|
||||
- Mounts your source code from the host at runtime
|
||||
- Automatically configures the connection to use host.docker.internal:7777 for accessing the Lume server on your host machine
|
||||
- Preserves your code changes without requiring rebuilds (source code is mounted as a volume)
|
||||
|
||||
> **Note**: The Docker container doesn't include the macOS-specific Lume executable. Instead, it connects to the Lume server running on your host machine via host.docker.internal:7777. Make sure to start the Lume server on your host before running examples in the container.
|
||||
|
||||
## Cleanup and Reset
|
||||
|
||||
If you need to clean up the environment (non-docker) and start fresh:
|
||||
|
||||
```bash
|
||||
./scripts/cleanup.sh
|
||||
```
|
||||
|
||||
This will:
|
||||
|
||||
- Remove all virtual environments
|
||||
- Clean Python cache files and directories
|
||||
- Remove build artifacts
|
||||
- Clean PDM-related files
|
||||
- Reset environment configurations
|
||||
|
||||
## Code Formatting Standards
|
||||
|
||||
The cua project follows strict code formatting standards to ensure consistency across all packages.
|
||||
|
||||
### Python Code Formatting
|
||||
|
||||
#### Tools
|
||||
|
||||
The project uses the following tools for code formatting and linting:
|
||||
|
||||
- **[Black](https://black.readthedocs.io/)**: Code formatter
|
||||
- **[Ruff](https://beta.ruff.rs/docs/)**: Fast linter and formatter
|
||||
- **[MyPy](https://mypy.readthedocs.io/)**: Static type checker
|
||||
|
||||
These tools are automatically installed when you set up the development environment using the `./scripts/build.sh` script.
|
||||
|
||||
#### Configuration
|
||||
|
||||
The formatting configuration is defined in the root `pyproject.toml` file:
|
||||
|
||||
```toml
|
||||
[tool.black]
|
||||
line-length = 100
|
||||
target-version = ["py311"]
|
||||
|
||||
[tool.ruff]
|
||||
line-length = 100
|
||||
target-version = "py311"
|
||||
select = ["E", "F", "B", "I"]
|
||||
fix = true
|
||||
|
||||
[tool.ruff.format]
|
||||
docstring-code-format = true
|
||||
|
||||
[tool.mypy]
|
||||
strict = true
|
||||
python_version = "3.11"
|
||||
ignore_missing_imports = true
|
||||
disallow_untyped_defs = true
|
||||
check_untyped_defs = true
|
||||
warn_return_any = true
|
||||
show_error_codes = true
|
||||
warn_unused_ignores = false
|
||||
```
|
||||
|
||||
#### Key Formatting Rules
|
||||
|
||||
- **Line Length**: Maximum of 100 characters
|
||||
- **Python Version**: Code should be compatible with Python 3.11+
|
||||
- **Imports**: Automatically sorted (using Ruff's "I" rule)
|
||||
- **Type Hints**: Required for all function definitions (strict mypy mode)
|
||||
|
||||
#### IDE Integration
|
||||
|
||||
The repository includes VSCode workspace configurations that enable automatic formatting. When you open the workspace files (as recommended in the setup instructions), the correct formatting settings are automatically applied.
|
||||
|
||||
Python-specific settings in the workspace files:
|
||||
|
||||
```json
|
||||
"[python]": {
|
||||
"editor.formatOnSave": true,
|
||||
"editor.defaultFormatter": "ms-python.black-formatter",
|
||||
"editor.codeActionsOnSave": {
|
||||
"source.organizeImports": "explicit"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Recommended VS Code extensions:
|
||||
|
||||
- Black Formatter (ms-python.black-formatter)
|
||||
- Ruff (charliermarsh.ruff)
|
||||
- Pylance (ms-python.vscode-pylance)
|
||||
|
||||
#### Manual Formatting
|
||||
|
||||
To manually format code:
|
||||
|
||||
```bash
|
||||
# Format all Python files using Black
|
||||
pdm run black .
|
||||
|
||||
# Run Ruff linter with auto-fix
|
||||
pdm run ruff check --fix .
|
||||
|
||||
# Run type checking with MyPy
|
||||
pdm run mypy .
|
||||
```
|
||||
|
||||
#### Pre-commit Validation
|
||||
|
||||
Before submitting a pull request, ensure your code passes all formatting checks:
|
||||
|
||||
```bash
|
||||
# Run all checks
|
||||
pdm run black --check .
|
||||
pdm run ruff check .
|
||||
pdm run mypy .
|
||||
```
|
||||
|
||||
### Swift Code (Lume)
|
||||
|
||||
For Swift code in the `libs/lume` directory:
|
||||
|
||||
- Follow the [Swift API Design Guidelines](https://www.swift.org/documentation/api-design-guidelines/)
|
||||
- Use SwiftFormat for consistent formatting
|
||||
- Code will be automatically formatted on save when using the lume workspace
|
||||
@@ -18,4 +18,8 @@ from agent.ui.gradio.app import create_gradio_ui
|
||||
if __name__ == "__main__":
|
||||
print("Launching Computer-Use Agent Gradio UI with advanced features...")
|
||||
app = create_gradio_ui()
|
||||
app.launch(share=False)
|
||||
app.launch(
|
||||
share=False,
|
||||
server_name="0.0.0.0",
|
||||
server_port=7860,
|
||||
)
|
||||
|
||||
3
examples/computer-example-ts/.env.example
Normal file
3
examples/computer-example-ts/.env.example
Normal file
@@ -0,0 +1,3 @@
|
||||
OPENAI_KEY=
|
||||
CUA_KEY=
|
||||
CUA_CONTAINER_NAME=
|
||||
3
examples/computer-example-ts/.gitignore
vendored
Normal file
3
examples/computer-example-ts/.gitignore
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
node_modules
|
||||
.DS_Store
|
||||
.env
|
||||
7
examples/computer-example-ts/.prettierrc
Normal file
7
examples/computer-example-ts/.prettierrc
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"useTabs": false,
|
||||
"semi": true,
|
||||
"singleQuote": true,
|
||||
"trailingComma": "es5",
|
||||
"bracketSpacing": true
|
||||
}
|
||||
47
examples/computer-example-ts/README.md
Normal file
47
examples/computer-example-ts/README.md
Normal file
@@ -0,0 +1,47 @@
|
||||
# cua-cloud-openai Example
|
||||
|
||||
This example demonstrates how to control a c/ua Cloud container using the OpenAI `computer-use-preview` model and the `@trycua/computer` TypeScript library.
|
||||
|
||||
## Overview
|
||||
|
||||
- Connects to a c/ua Cloud container via the `@trycua/computer` library
|
||||
- Sends screenshots and instructions to OpenAI's computer-use model
|
||||
- Executes AI-generated actions (clicks, typing, etc.) inside the container
|
||||
- Designed for Linux containers, but can be adapted for other OS types
|
||||
|
||||
## Getting Started
|
||||
|
||||
1. **Install dependencies:**
|
||||
|
||||
```bash
|
||||
npm install
|
||||
```
|
||||
|
||||
2. **Set up environment variables:**
|
||||
Create a `.env` file with the following variables:
|
||||
- `OPENAI_KEY` — your OpenAI API key
|
||||
- `CUA_KEY` — your c/ua Cloud API key
|
||||
- `CUA_CONTAINER_NAME` — the name of your provisioned container
|
||||
|
||||
3. **Run the example:**
|
||||
|
||||
```bash
|
||||
npx tsx src/index.ts
|
||||
```
|
||||
|
||||
## Files
|
||||
|
||||
- `src/index.ts` — Main example script
|
||||
- `src/helpers.ts` — Helper for executing actions on the container
|
||||
|
||||
## Further Reading
|
||||
|
||||
For a step-by-step tutorial and more detailed explanation, see the accompanying blog post:
|
||||
|
||||
➡️ [Controlling a c/ua Cloud Container with JavaScript](https://placeholder-url-to-blog-post.com)
|
||||
|
||||
_(This link will be updated once the article is published.)_
|
||||
|
||||
---
|
||||
|
||||
If you have questions or issues, please open an issue or contact the maintainers.
|
||||
25
examples/computer-example-ts/package.json
Normal file
25
examples/computer-example-ts/package.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"name": "computer-example-ts",
|
||||
"version": "1.0.0",
|
||||
"description": "",
|
||||
"type": "module",
|
||||
"main": "index.js",
|
||||
"scripts": {
|
||||
"dev": "tsx watch src/index.ts",
|
||||
"start": "tsx src/index.ts"
|
||||
},
|
||||
"keywords": [],
|
||||
"author": "",
|
||||
"license": "MIT",
|
||||
"packageManager": "pnpm@10.12.3",
|
||||
"dependencies": {
|
||||
"@trycua/computer": "^0.1.3",
|
||||
"dotenv": "^16.5.0",
|
||||
"openai": "^5.7.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^22.15.33",
|
||||
"tsx": "^4.20.3",
|
||||
"typescript": "^5.8.3"
|
||||
}
|
||||
}
|
||||
507
examples/computer-example-ts/pnpm-lock.yaml
generated
Normal file
507
examples/computer-example-ts/pnpm-lock.yaml
generated
Normal file
@@ -0,0 +1,507 @@
|
||||
lockfileVersion: '9.0'
|
||||
|
||||
settings:
|
||||
autoInstallPeers: true
|
||||
excludeLinksFromLockfile: false
|
||||
|
||||
importers:
|
||||
|
||||
.:
|
||||
dependencies:
|
||||
'@trycua/computer':
|
||||
specifier: ^0.1.3
|
||||
version: 0.1.3
|
||||
dotenv:
|
||||
specifier: ^16.5.0
|
||||
version: 16.6.1
|
||||
openai:
|
||||
specifier: ^5.7.0
|
||||
version: 5.8.2(ws@8.18.3)
|
||||
devDependencies:
|
||||
'@types/node':
|
||||
specifier: ^22.15.33
|
||||
version: 22.16.0
|
||||
tsx:
|
||||
specifier: ^4.20.3
|
||||
version: 4.20.3
|
||||
typescript:
|
||||
specifier: ^5.8.3
|
||||
version: 5.8.3
|
||||
|
||||
packages:
|
||||
|
||||
'@esbuild/aix-ppc64@0.25.5':
|
||||
resolution: {integrity: sha512-9o3TMmpmftaCMepOdA5k/yDw8SfInyzWWTjYTFCX3kPSDJMROQTb8jg+h9Cnwnmm1vOzvxN7gIfB5V2ewpjtGA==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [ppc64]
|
||||
os: [aix]
|
||||
|
||||
'@esbuild/android-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-VGzGhj4lJO+TVGV1v8ntCZWJktV7SGCs3Pn1GRWI1SBFtRALoomm8k5E9Pmwg3HOAal2VDc2F9+PM/rEY6oIDg==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [android]
|
||||
|
||||
'@esbuild/android-arm@0.25.5':
|
||||
resolution: {integrity: sha512-AdJKSPeEHgi7/ZhuIPtcQKr5RQdo6OO2IL87JkianiMYMPbCtot9fxPbrMiBADOWWm3T2si9stAiVsGbTQFkbA==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm]
|
||||
os: [android]
|
||||
|
||||
'@esbuild/android-x64@0.25.5':
|
||||
resolution: {integrity: sha512-D2GyJT1kjvO//drbRT3Hib9XPwQeWd9vZoBJn+bu/lVsOZ13cqNdDeqIF/xQ5/VmWvMduP6AmXvylO/PIc2isw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [android]
|
||||
|
||||
'@esbuild/darwin-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-GtaBgammVvdF7aPIgH2jxMDdivezgFu6iKpmT+48+F8Hhg5J/sfnDieg0aeG/jfSvkYQU2/pceFPDKlqZzwnfQ==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [darwin]
|
||||
|
||||
'@esbuild/darwin-x64@0.25.5':
|
||||
resolution: {integrity: sha512-1iT4FVL0dJ76/q1wd7XDsXrSW+oLoquptvh4CLR4kITDtqi2e/xwXwdCVH8hVHU43wgJdsq7Gxuzcs6Iq/7bxQ==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [darwin]
|
||||
|
||||
'@esbuild/freebsd-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-nk4tGP3JThz4La38Uy/gzyXtpkPW8zSAmoUhK9xKKXdBCzKODMc2adkB2+8om9BDYugz+uGV7sLmpTYzvmz6Sw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [freebsd]
|
||||
|
||||
'@esbuild/freebsd-x64@0.25.5':
|
||||
resolution: {integrity: sha512-PrikaNjiXdR2laW6OIjlbeuCPrPaAl0IwPIaRv+SMV8CiM8i2LqVUHFC1+8eORgWyY7yhQY+2U2fA55mBzReaw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [freebsd]
|
||||
|
||||
'@esbuild/linux-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-Z9kfb1v6ZlGbWj8EJk9T6czVEjjq2ntSYLY2cw6pAZl4oKtfgQuS4HOq41M/BcoLPzrUbNd+R4BXFyH//nHxVg==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-arm@0.25.5':
|
||||
resolution: {integrity: sha512-cPzojwW2okgh7ZlRpcBEtsX7WBuqbLrNXqLU89GxWbNt6uIg78ET82qifUy3W6OVww6ZWobWub5oqZOVtwolfw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-ia32@0.25.5':
|
||||
resolution: {integrity: sha512-sQ7l00M8bSv36GLV95BVAdhJ2QsIbCuCjh/uYrWiMQSUuV+LpXwIqhgJDcvMTj+VsQmqAHL2yYaasENvJ7CDKA==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [ia32]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-loong64@0.25.5':
|
||||
resolution: {integrity: sha512-0ur7ae16hDUC4OL5iEnDb0tZHDxYmuQyhKhsPBV8f99f6Z9KQM02g33f93rNH5A30agMS46u2HP6qTdEt6Q1kg==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [loong64]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-mips64el@0.25.5':
|
||||
resolution: {integrity: sha512-kB/66P1OsHO5zLz0i6X0RxlQ+3cu0mkxS3TKFvkb5lin6uwZ/ttOkP3Z8lfR9mJOBk14ZwZ9182SIIWFGNmqmg==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [mips64el]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-ppc64@0.25.5':
|
||||
resolution: {integrity: sha512-UZCmJ7r9X2fe2D6jBmkLBMQetXPXIsZjQJCjgwpVDz+YMcS6oFR27alkgGv3Oqkv07bxdvw7fyB71/olceJhkQ==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [ppc64]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-riscv64@0.25.5':
|
||||
resolution: {integrity: sha512-kTxwu4mLyeOlsVIFPfQo+fQJAV9mh24xL+y+Bm6ej067sYANjyEw1dNHmvoqxJUCMnkBdKpvOn0Ahql6+4VyeA==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [riscv64]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-s390x@0.25.5':
|
||||
resolution: {integrity: sha512-K2dSKTKfmdh78uJ3NcWFiqyRrimfdinS5ErLSn3vluHNeHVnBAFWC8a4X5N+7FgVE1EjXS1QDZbpqZBjfrqMTQ==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [s390x]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/linux-x64@0.25.5':
|
||||
resolution: {integrity: sha512-uhj8N2obKTE6pSZ+aMUbqq+1nXxNjZIIjCjGLfsWvVpy7gKCOL6rsY1MhRh9zLtUtAI7vpgLMK6DxjO8Qm9lJw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [linux]
|
||||
|
||||
'@esbuild/netbsd-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-pwHtMP9viAy1oHPvgxtOv+OkduK5ugofNTVDilIzBLpoWAM16r7b/mxBvfpuQDpRQFMfuVr5aLcn4yveGvBZvw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [netbsd]
|
||||
|
||||
'@esbuild/netbsd-x64@0.25.5':
|
||||
resolution: {integrity: sha512-WOb5fKrvVTRMfWFNCroYWWklbnXH0Q5rZppjq0vQIdlsQKuw6mdSihwSo4RV/YdQ5UCKKvBy7/0ZZYLBZKIbwQ==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [netbsd]
|
||||
|
||||
'@esbuild/openbsd-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-7A208+uQKgTxHd0G0uqZO8UjK2R0DDb4fDmERtARjSHWxqMTye4Erz4zZafx7Di9Cv+lNHYuncAkiGFySoD+Mw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [openbsd]
|
||||
|
||||
'@esbuild/openbsd-x64@0.25.5':
|
||||
resolution: {integrity: sha512-G4hE405ErTWraiZ8UiSoesH8DaCsMm0Cay4fsFWOOUcz8b8rC6uCvnagr+gnioEjWn0wC+o1/TAHt+It+MpIMg==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [openbsd]
|
||||
|
||||
'@esbuild/sunos-x64@0.25.5':
|
||||
resolution: {integrity: sha512-l+azKShMy7FxzY0Rj4RCt5VD/q8mG/e+mDivgspo+yL8zW7qEwctQ6YqKX34DTEleFAvCIUviCFX1SDZRSyMQA==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [sunos]
|
||||
|
||||
'@esbuild/win32-arm64@0.25.5':
|
||||
resolution: {integrity: sha512-O2S7SNZzdcFG7eFKgvwUEZ2VG9D/sn/eIiz8XRZ1Q/DO5a3s76Xv0mdBzVM5j5R639lXQmPmSo0iRpHqUUrsxw==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [arm64]
|
||||
os: [win32]
|
||||
|
||||
'@esbuild/win32-ia32@0.25.5':
|
||||
resolution: {integrity: sha512-onOJ02pqs9h1iMJ1PQphR+VZv8qBMQ77Klcsqv9CNW2w6yLqoURLcgERAIurY6QE63bbLuqgP9ATqajFLK5AMQ==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [ia32]
|
||||
os: [win32]
|
||||
|
||||
'@esbuild/win32-x64@0.25.5':
|
||||
resolution: {integrity: sha512-TXv6YnJ8ZMVdX+SXWVBo/0p8LTcrUYngpWjvm91TMjjBQii7Oz11Lw5lbDV5Y0TzuhSJHwiH4hEtC1I42mMS0g==}
|
||||
engines: {node: '>=18'}
|
||||
cpu: [x64]
|
||||
os: [win32]
|
||||
|
||||
'@trycua/computer@0.1.3':
|
||||
resolution: {integrity: sha512-RTDgULV6wQJuTsiwhei9aQO6YQSM1TBQqOCDUPHUbTIjtRqzMvMdwtcKAKxZZptzJcBX14bWtbucY65Wu6IEFg==}
|
||||
|
||||
'@trycua/core@0.1.3':
|
||||
resolution: {integrity: sha512-sv7BEajJyZ+JNxrOdhao4qCOtRrh+S0XYf64ehAT4UAhLC73Kep06bGa/Uel0Ow5xGXXrg0aiVBL7zO9+/w4/Q==}
|
||||
|
||||
'@types/node@22.16.0':
|
||||
resolution: {integrity: sha512-B2egV9wALML1JCpv3VQoQ+yesQKAmNMBIAY7OteVrikcOcAkWm+dGL6qpeCktPjAv6N1JLnhbNiqS35UpFyBsQ==}
|
||||
|
||||
'@types/uuid@10.0.0':
|
||||
resolution: {integrity: sha512-7gqG38EyHgyP1S+7+xomFtL+ZNHcKv6DwNaCZmJmo1vgMugyF3TCnXVg4t1uk89mLNwnLtnY3TpOpCOyp1/xHQ==}
|
||||
|
||||
atomic-sleep@1.0.0:
|
||||
resolution: {integrity: sha512-kNOjDqAh7px0XWNI+4QbzoiR/nTkHAWNud2uvnJquD1/x5a7EQZMJT0AczqK0Qn67oY/TTQ1LbUKajZpp3I9tQ==}
|
||||
engines: {node: '>=8.0.0'}
|
||||
|
||||
dotenv@16.6.1:
|
||||
resolution: {integrity: sha512-uBq4egWHTcTt33a72vpSG0z3HnPuIl6NqYcTrKEg2azoEyl2hpW0zqlxysq2pK9HlDIHyHyakeYaYnSAwd8bow==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
esbuild@0.25.5:
|
||||
resolution: {integrity: sha512-P8OtKZRv/5J5hhz0cUAdu/cLuPIKXpQl1R9pZtvmHWQvrAUVd0UNIPT4IB4W3rNOqVO0rlqHmCIbSwxh/c9yUQ==}
|
||||
engines: {node: '>=18'}
|
||||
hasBin: true
|
||||
|
||||
fast-redact@3.5.0:
|
||||
resolution: {integrity: sha512-dwsoQlS7h9hMeYUq1W++23NDcBLV4KqONnITDV9DjfS3q1SgDGVrBdvvTLUotWtPSD7asWDV9/CmsZPy8Hf70A==}
|
||||
engines: {node: '>=6'}
|
||||
|
||||
fsevents@2.3.3:
|
||||
resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==}
|
||||
engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
|
||||
os: [darwin]
|
||||
|
||||
get-tsconfig@4.10.1:
|
||||
resolution: {integrity: sha512-auHyJ4AgMz7vgS8Hp3N6HXSmlMdUyhSUrfBF16w153rxtLIEOE+HGqaBppczZvnHLqQJfiHotCYpNhl0lUROFQ==}
|
||||
|
||||
on-exit-leak-free@2.1.2:
|
||||
resolution: {integrity: sha512-0eJJY6hXLGf1udHwfNftBqH+g73EU4B504nZeKpz1sYRKafAghwxEJunB2O7rDZkL4PGfsMVnTXZ2EjibbqcsA==}
|
||||
engines: {node: '>=14.0.0'}
|
||||
|
||||
openai@5.8.2:
|
||||
resolution: {integrity: sha512-8C+nzoHYgyYOXhHGN6r0fcb4SznuEn1R7YZMvlqDbnCuE0FM2mm3T1HiYW6WIcMS/F1Of2up/cSPjLPaWt0X9Q==}
|
||||
hasBin: true
|
||||
peerDependencies:
|
||||
ws: ^8.18.0
|
||||
zod: ^3.23.8
|
||||
peerDependenciesMeta:
|
||||
ws:
|
||||
optional: true
|
||||
zod:
|
||||
optional: true
|
||||
|
||||
pino-abstract-transport@2.0.0:
|
||||
resolution: {integrity: sha512-F63x5tizV6WCh4R6RHyi2Ml+M70DNRXt/+HANowMflpgGFMAym/VKm6G7ZOQRjqN7XbGxK1Lg9t6ZrtzOaivMw==}
|
||||
|
||||
pino-std-serializers@7.0.0:
|
||||
resolution: {integrity: sha512-e906FRY0+tV27iq4juKzSYPbUj2do2X2JX4EzSca1631EB2QJQUqGbDuERal7LCtOpxl6x3+nvo9NPZcmjkiFA==}
|
||||
|
||||
pino@9.7.0:
|
||||
resolution: {integrity: sha512-vnMCM6xZTb1WDmLvtG2lE/2p+t9hDEIvTWJsu6FejkE62vB7gDhvzrpFR4Cw2to+9JNQxVnkAKVPA1KPB98vWg==}
|
||||
hasBin: true
|
||||
|
||||
posthog-node@5.1.1:
|
||||
resolution: {integrity: sha512-6VISkNdxO24ehXiDA4dugyCSIV7lpGVaEu5kn/dlAj+SJ1lgcDru9PQ8p/+GSXsXVxohd1t7kHL2JKc9NoGb0w==}
|
||||
engines: {node: '>=20'}
|
||||
|
||||
process-warning@5.0.0:
|
||||
resolution: {integrity: sha512-a39t9ApHNx2L4+HBnQKqxxHNs1r7KF+Intd8Q/g1bUh6q0WIp9voPXJ/x0j+ZL45KF1pJd9+q2jLIRMfvEshkA==}
|
||||
|
||||
quick-format-unescaped@4.0.4:
|
||||
resolution: {integrity: sha512-tYC1Q1hgyRuHgloV/YXs2w15unPVh8qfu/qCTfhTYamaw7fyhumKa2yGpdSo87vY32rIclj+4fWYQXUMs9EHvg==}
|
||||
|
||||
real-require@0.2.0:
|
||||
resolution: {integrity: sha512-57frrGM/OCTLqLOAh0mhVA9VBMHd+9U7Zb2THMGdBUoZVOtGbJzjxsYGDJ3A9AYYCP4hn6y1TVbaOfzWtm5GFg==}
|
||||
engines: {node: '>= 12.13.0'}
|
||||
|
||||
resolve-pkg-maps@1.0.0:
|
||||
resolution: {integrity: sha512-seS2Tj26TBVOC2NIc2rOe2y2ZO7efxITtLZcGSOnHHNOQ7CkiUBfw0Iw2ck6xkIhPwLhKNLS8BO+hEpngQlqzw==}
|
||||
|
||||
safe-stable-stringify@2.5.0:
|
||||
resolution: {integrity: sha512-b3rppTKm9T+PsVCBEOUR46GWI7fdOs00VKZ1+9c1EWDaDMvjQc6tUwuFyIprgGgTcWoVHSKrU8H31ZHA2e0RHA==}
|
||||
engines: {node: '>=10'}
|
||||
|
||||
sonic-boom@4.2.0:
|
||||
resolution: {integrity: sha512-INb7TM37/mAcsGmc9hyyI6+QR3rR1zVRu36B0NeGXKnOOLiZOfER5SA+N7X7k3yUYRzLWafduTDvJAfDswwEww==}
|
||||
|
||||
split2@4.2.0:
|
||||
resolution: {integrity: sha512-UcjcJOWknrNkF6PLX83qcHM6KHgVKNkV62Y8a5uYDVv9ydGQVwAHMKqHdJje1VTWpljG0WYpCDhrCdAOYH4TWg==}
|
||||
engines: {node: '>= 10.x'}
|
||||
|
||||
thread-stream@3.1.0:
|
||||
resolution: {integrity: sha512-OqyPZ9u96VohAyMfJykzmivOrY2wfMSf3C5TtFJVgN+Hm6aj+voFhlK+kZEIv2FBh1X6Xp3DlnCOfEQ3B2J86A==}
|
||||
|
||||
tsx@4.20.3:
|
||||
resolution: {integrity: sha512-qjbnuR9Tr+FJOMBqJCW5ehvIo/buZq7vH7qD7JziU98h6l3qGy0a/yPFjwO+y0/T7GFpNgNAvEcPPVfyT8rrPQ==}
|
||||
engines: {node: '>=18.0.0'}
|
||||
hasBin: true
|
||||
|
||||
typescript@5.8.3:
|
||||
resolution: {integrity: sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==}
|
||||
engines: {node: '>=14.17'}
|
||||
hasBin: true
|
||||
|
||||
undici-types@6.21.0:
|
||||
resolution: {integrity: sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ==}
|
||||
|
||||
uuid@11.1.0:
|
||||
resolution: {integrity: sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A==}
|
||||
hasBin: true
|
||||
|
||||
ws@8.18.3:
|
||||
resolution: {integrity: sha512-PEIGCY5tSlUt50cqyMXfCzX+oOPqN0vuGqWzbcJ2xvnkzkq46oOpz7dQaTDBdfICb4N14+GARUDw2XV2N4tvzg==}
|
||||
engines: {node: '>=10.0.0'}
|
||||
peerDependencies:
|
||||
bufferutil: ^4.0.1
|
||||
utf-8-validate: '>=5.0.2'
|
||||
peerDependenciesMeta:
|
||||
bufferutil:
|
||||
optional: true
|
||||
utf-8-validate:
|
||||
optional: true
|
||||
|
||||
snapshots:
|
||||
|
||||
'@esbuild/aix-ppc64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/android-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/android-arm@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/android-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/darwin-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/darwin-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/freebsd-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/freebsd-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-arm@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-ia32@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-loong64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-mips64el@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-ppc64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-riscv64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-s390x@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/linux-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/netbsd-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/netbsd-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/openbsd-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/openbsd-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/sunos-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/win32-arm64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/win32-ia32@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@esbuild/win32-x64@0.25.5':
|
||||
optional: true
|
||||
|
||||
'@trycua/computer@0.1.3':
|
||||
dependencies:
|
||||
'@trycua/core': 0.1.3
|
||||
pino: 9.7.0
|
||||
ws: 8.18.3
|
||||
transitivePeerDependencies:
|
||||
- bufferutil
|
||||
- utf-8-validate
|
||||
|
||||
'@trycua/core@0.1.3':
|
||||
dependencies:
|
||||
'@types/uuid': 10.0.0
|
||||
pino: 9.7.0
|
||||
posthog-node: 5.1.1
|
||||
uuid: 11.1.0
|
||||
|
||||
'@types/node@22.16.0':
|
||||
dependencies:
|
||||
undici-types: 6.21.0
|
||||
|
||||
'@types/uuid@10.0.0': {}
|
||||
|
||||
atomic-sleep@1.0.0: {}
|
||||
|
||||
dotenv@16.6.1: {}
|
||||
|
||||
esbuild@0.25.5:
|
||||
optionalDependencies:
|
||||
'@esbuild/aix-ppc64': 0.25.5
|
||||
'@esbuild/android-arm': 0.25.5
|
||||
'@esbuild/android-arm64': 0.25.5
|
||||
'@esbuild/android-x64': 0.25.5
|
||||
'@esbuild/darwin-arm64': 0.25.5
|
||||
'@esbuild/darwin-x64': 0.25.5
|
||||
'@esbuild/freebsd-arm64': 0.25.5
|
||||
'@esbuild/freebsd-x64': 0.25.5
|
||||
'@esbuild/linux-arm': 0.25.5
|
||||
'@esbuild/linux-arm64': 0.25.5
|
||||
'@esbuild/linux-ia32': 0.25.5
|
||||
'@esbuild/linux-loong64': 0.25.5
|
||||
'@esbuild/linux-mips64el': 0.25.5
|
||||
'@esbuild/linux-ppc64': 0.25.5
|
||||
'@esbuild/linux-riscv64': 0.25.5
|
||||
'@esbuild/linux-s390x': 0.25.5
|
||||
'@esbuild/linux-x64': 0.25.5
|
||||
'@esbuild/netbsd-arm64': 0.25.5
|
||||
'@esbuild/netbsd-x64': 0.25.5
|
||||
'@esbuild/openbsd-arm64': 0.25.5
|
||||
'@esbuild/openbsd-x64': 0.25.5
|
||||
'@esbuild/sunos-x64': 0.25.5
|
||||
'@esbuild/win32-arm64': 0.25.5
|
||||
'@esbuild/win32-ia32': 0.25.5
|
||||
'@esbuild/win32-x64': 0.25.5
|
||||
|
||||
fast-redact@3.5.0: {}
|
||||
|
||||
fsevents@2.3.3:
|
||||
optional: true
|
||||
|
||||
get-tsconfig@4.10.1:
|
||||
dependencies:
|
||||
resolve-pkg-maps: 1.0.0
|
||||
|
||||
on-exit-leak-free@2.1.2: {}
|
||||
|
||||
openai@5.8.2(ws@8.18.3):
|
||||
optionalDependencies:
|
||||
ws: 8.18.3
|
||||
|
||||
pino-abstract-transport@2.0.0:
|
||||
dependencies:
|
||||
split2: 4.2.0
|
||||
|
||||
pino-std-serializers@7.0.0: {}
|
||||
|
||||
pino@9.7.0:
|
||||
dependencies:
|
||||
atomic-sleep: 1.0.0
|
||||
fast-redact: 3.5.0
|
||||
on-exit-leak-free: 2.1.2
|
||||
pino-abstract-transport: 2.0.0
|
||||
pino-std-serializers: 7.0.0
|
||||
process-warning: 5.0.0
|
||||
quick-format-unescaped: 4.0.4
|
||||
real-require: 0.2.0
|
||||
safe-stable-stringify: 2.5.0
|
||||
sonic-boom: 4.2.0
|
||||
thread-stream: 3.1.0
|
||||
|
||||
posthog-node@5.1.1: {}
|
||||
|
||||
process-warning@5.0.0: {}
|
||||
|
||||
quick-format-unescaped@4.0.4: {}
|
||||
|
||||
real-require@0.2.0: {}
|
||||
|
||||
resolve-pkg-maps@1.0.0: {}
|
||||
|
||||
safe-stable-stringify@2.5.0: {}
|
||||
|
||||
sonic-boom@4.2.0:
|
||||
dependencies:
|
||||
atomic-sleep: 1.0.0
|
||||
|
||||
split2@4.2.0: {}
|
||||
|
||||
thread-stream@3.1.0:
|
||||
dependencies:
|
||||
real-require: 0.2.0
|
||||
|
||||
tsx@4.20.3:
|
||||
dependencies:
|
||||
esbuild: 0.25.5
|
||||
get-tsconfig: 4.10.1
|
||||
optionalDependencies:
|
||||
fsevents: 2.3.3
|
||||
|
||||
typescript@5.8.3: {}
|
||||
|
||||
undici-types@6.21.0: {}
|
||||
|
||||
uuid@11.1.0: {}
|
||||
|
||||
ws@8.18.3: {}
|
||||
63
examples/computer-example-ts/src/helpers.ts
Normal file
63
examples/computer-example-ts/src/helpers.ts
Normal file
@@ -0,0 +1,63 @@
|
||||
import type { Computer } from "@trycua/computer";
|
||||
import type OpenAI from "openai";
|
||||
|
||||
export async function executeAction(
|
||||
computer: Computer,
|
||||
action: OpenAI.Responses.ResponseComputerToolCall["action"],
|
||||
) {
|
||||
switch (action.type) {
|
||||
case "click": {
|
||||
const { x, y, button } = action;
|
||||
console.log(`Executing click at (${x}, ${y}) with button '${button}'.`);
|
||||
await computer.interface.moveCursor(x, y);
|
||||
if (button === "right") await computer.interface.rightClick();
|
||||
else await computer.interface.leftClick();
|
||||
break;
|
||||
}
|
||||
case "type":
|
||||
{
|
||||
const { text } = action;
|
||||
console.log(`Typing text: ${text}`);
|
||||
await computer.interface.typeText(text);
|
||||
}
|
||||
break;
|
||||
case "scroll": {
|
||||
const { x: locX, y: locY, scroll_x, scroll_y } = action;
|
||||
console.log(
|
||||
`Scrolling at (${locX}, ${locY}) with offsets (scroll_x=${scroll_x}, scroll_y=${scroll_y}).`,
|
||||
);
|
||||
await computer.interface.moveCursor(locX, locY);
|
||||
await computer.interface.scroll(scroll_x, scroll_y);
|
||||
break;
|
||||
}
|
||||
case "keypress": {
|
||||
const { keys } = action;
|
||||
for (const key of keys) {
|
||||
console.log(`Pressing key: ${key}.`);
|
||||
// Map common key names to CUA equivalents
|
||||
if (key.toLowerCase() === "enter") {
|
||||
await computer.interface.pressKey("return");
|
||||
} else if (key.toLowerCase() === "space") {
|
||||
await computer.interface.pressKey("space");
|
||||
} else {
|
||||
await computer.interface.pressKey(key);
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
case "wait": {
|
||||
console.log(`Waiting for 3 seconds.`);
|
||||
await new Promise((resolve) => setTimeout(resolve, 3 * 1000));
|
||||
break;
|
||||
}
|
||||
case "screenshot": {
|
||||
console.log("Taking screenshot.");
|
||||
// This is handled automatically in the main loop, but we can take an extra one if requested
|
||||
const screenshot = await computer.interface.screenshot();
|
||||
return screenshot;
|
||||
}
|
||||
default:
|
||||
console.log(`Unrecognized action: ${action.type}`);
|
||||
break;
|
||||
}
|
||||
}
|
||||
104
examples/computer-example-ts/src/index.ts
Normal file
104
examples/computer-example-ts/src/index.ts
Normal file
@@ -0,0 +1,104 @@
|
||||
import { Computer, OSType } from "@trycua/computer";
|
||||
import OpenAI from "openai";
|
||||
import { executeAction } from "./helpers";
|
||||
|
||||
import "dotenv/config";
|
||||
|
||||
const openai = new OpenAI({ apiKey: process.env.OPENAI_KEY });
|
||||
|
||||
const COMPUTER_USE_PROMPT = "Open firefox and go to trycua.com";
|
||||
|
||||
// Initialize the Computer Connection
|
||||
const computer = new Computer({
|
||||
apiKey: process.env.CUA_KEY!,
|
||||
name: process.env.CUA_CONTAINER_NAME!,
|
||||
osType: OSType.LINUX,
|
||||
});
|
||||
|
||||
await computer.run();
|
||||
// Take the initial screenshot
|
||||
const screenshot = await computer.interface.screenshot();
|
||||
const screenshotBase64 = screenshot.toString("base64");
|
||||
|
||||
// Setup openai config for computer use
|
||||
const computerUseConfig: OpenAI.Responses.ResponseCreateParamsNonStreaming = {
|
||||
model: "computer-use-preview",
|
||||
tools: [
|
||||
{
|
||||
type: "computer_use_preview",
|
||||
display_width: 1024,
|
||||
display_height: 768,
|
||||
environment: "linux", // we're using a linux vm
|
||||
},
|
||||
],
|
||||
truncation: "auto",
|
||||
};
|
||||
|
||||
// Send initial screenshot to the openai computer use model
|
||||
let res = await openai.responses.create({
|
||||
...computerUseConfig,
|
||||
input: [
|
||||
{
|
||||
role: "user",
|
||||
content: [
|
||||
// what we want the ai to do
|
||||
{ type: "input_text", text: COMPUTER_USE_PROMPT },
|
||||
// current screenshot of the vm
|
||||
{
|
||||
type: "input_image",
|
||||
image_url: `data:image/png;base64,${screenshotBase64}`,
|
||||
detail: "auto",
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
});
|
||||
|
||||
// Loop until there are no more computer use actions.
|
||||
while (true) {
|
||||
const computerCalls = res.output.filter((o) => o.type === "computer_call");
|
||||
if (computerCalls.length < 1) {
|
||||
console.log("No more computer calls. Loop complete.");
|
||||
break;
|
||||
}
|
||||
// Get the first call
|
||||
const call = computerCalls[0];
|
||||
const action = call.action;
|
||||
console.log("Received action from OpenAI Responses API:", action);
|
||||
let ackChecks: OpenAI.Responses.ResponseComputerToolCall.PendingSafetyCheck[] =
|
||||
[];
|
||||
if (call.pending_safety_checks.length > 0) {
|
||||
console.log("Safety checks pending:", call.pending_safety_checks);
|
||||
// In a real implementation, you would want to get user confirmation here
|
||||
ackChecks = call.pending_safety_checks;
|
||||
}
|
||||
|
||||
// Execute the action in the container
|
||||
await executeAction(computer, action);
|
||||
// Wait for changes to process within the container (1sec)
|
||||
await new Promise((resolve) => setTimeout(resolve, 1000));
|
||||
|
||||
// Capture new screenshot
|
||||
const newScreenshot = await computer.interface.screenshot();
|
||||
const newScreenshotBase64 = newScreenshot.toString("base64");
|
||||
|
||||
// Screenshot back as computer_call_output
|
||||
|
||||
res = await openai.responses.create({
|
||||
...computerUseConfig,
|
||||
previous_response_id: res.id,
|
||||
input: [
|
||||
{
|
||||
type: "computer_call_output",
|
||||
call_id: call.call_id,
|
||||
acknowledged_safety_checks: ackChecks,
|
||||
output: {
|
||||
type: "computer_screenshot",
|
||||
image_url: `data:image/png;base64,${newScreenshotBase64}`,
|
||||
},
|
||||
},
|
||||
],
|
||||
});
|
||||
}
|
||||
|
||||
process.exit();
|
||||
29
examples/computer-example-ts/tsconfig.json
Normal file
29
examples/computer-example-ts/tsconfig.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"target": "esnext",
|
||||
"lib": [
|
||||
"es2023"
|
||||
],
|
||||
"moduleDetection": "force",
|
||||
"module": "preserve",
|
||||
"moduleResolution": "bundler",
|
||||
"allowImportingTsExtensions": true,
|
||||
"resolveJsonModule": true,
|
||||
"types": [
|
||||
"node"
|
||||
],
|
||||
"allowSyntheticDefaultImports": true,
|
||||
"strict": true,
|
||||
"noUnusedLocals": true,
|
||||
"declaration": true,
|
||||
"emitDeclarationOnly": true,
|
||||
"esModuleInterop": true,
|
||||
"isolatedModules": true,
|
||||
"verbatimModuleSyntax": true,
|
||||
"skipLibCheck": true,
|
||||
"outDir": "build",
|
||||
},
|
||||
"include": [
|
||||
"src"
|
||||
]
|
||||
}
|
||||
@@ -18,7 +18,11 @@ from computer.ui.gradio.app import create_gradio_ui
|
||||
if __name__ == "__main__":
|
||||
print("Launching Computer Interface Gradio UI with advanced features...")
|
||||
app = create_gradio_ui()
|
||||
app.launch(share=False)
|
||||
app.launch(
|
||||
share=False,
|
||||
server_name="0.0.0.0",
|
||||
server_port=7860,
|
||||
)
|
||||
|
||||
# Optional: Using the saved dataset
|
||||
# import datasets
|
||||
|
||||
51
examples/winsandbox_example.py
Normal file
51
examples/winsandbox_example.py
Normal file
@@ -0,0 +1,51 @@
|
||||
"""Example of using the Windows Sandbox computer provider.
|
||||
|
||||
Learn more at: https://learn.microsoft.com/en-us/windows/security/application-security/application-isolation/windows-sandbox/
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from computer import Computer
|
||||
|
||||
async def main():
|
||||
"""Test the Windows Sandbox provider."""
|
||||
|
||||
# Create a computer instance using Windows Sandbox
|
||||
computer = Computer(
|
||||
provider_type="winsandbox",
|
||||
os_type="windows",
|
||||
memory="4GB",
|
||||
# ephemeral=True, # Always true for Windows Sandbox
|
||||
)
|
||||
|
||||
try:
|
||||
print("Starting Windows Sandbox...")
|
||||
await computer.run()
|
||||
|
||||
print("Windows Sandbox is ready!")
|
||||
print(f"IP Address: {await computer.get_ip()}")
|
||||
|
||||
# Test basic functionality
|
||||
print("Testing basic functionality...")
|
||||
screenshot = await computer.interface.screenshot()
|
||||
print(f"Screenshot taken: {len(screenshot)} bytes")
|
||||
|
||||
# Test running a command
|
||||
print("Testing command execution...")
|
||||
stdout, stderr = await computer.interface.run_command("echo Hello from Windows Sandbox!")
|
||||
print(f"Command output: {stdout}")
|
||||
|
||||
print("Press any key to continue...")
|
||||
input()
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
finally:
|
||||
print("Stopping Windows Sandbox...")
|
||||
await computer.stop()
|
||||
print("Windows Sandbox stopped.")
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -1,688 +0,0 @@
|
||||
import asyncio
|
||||
import json
|
||||
import time
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
from PIL import Image
|
||||
|
||||
import websockets
|
||||
|
||||
from ..logger import Logger, LogLevel
|
||||
from .base import BaseComputerInterface
|
||||
from ..utils import decode_base64_image, encode_base64_image, bytes_to_image, draw_box, resize_image
|
||||
from .models import Key, KeyType, MouseButton
|
||||
|
||||
|
||||
class LinuxComputerInterface(BaseComputerInterface):
|
||||
"""Interface for Linux."""
|
||||
|
||||
def __init__(self, ip_address: str, username: str = "lume", password: str = "lume", api_key: Optional[str] = None, vm_name: Optional[str] = None):
|
||||
super().__init__(ip_address, username, password, api_key, vm_name)
|
||||
self._ws = None
|
||||
self._reconnect_task = None
|
||||
self._closed = False
|
||||
self._last_ping = 0
|
||||
self._ping_interval = 5 # Send ping every 5 seconds
|
||||
self._ping_timeout = 120 # Wait 120 seconds for pong response
|
||||
self._reconnect_delay = 1 # Start with 1 second delay
|
||||
self._max_reconnect_delay = 30 # Maximum delay between reconnection attempts
|
||||
self._log_connection_attempts = True # Flag to control connection attempt logging
|
||||
self._authenticated = False # Track authentication status
|
||||
self._command_lock = asyncio.Lock() # Lock to ensure only one command at a time
|
||||
|
||||
# Set logger name for Linux interface
|
||||
self.logger = Logger("cua.interface.linux", LogLevel.NORMAL)
|
||||
|
||||
@property
|
||||
def ws_uri(self) -> str:
|
||||
"""Get the WebSocket URI using the current IP address.
|
||||
|
||||
Returns:
|
||||
WebSocket URI for the Computer API Server
|
||||
"""
|
||||
protocol = "wss" if self.api_key else "ws"
|
||||
port = "8443" if self.api_key else "8000"
|
||||
return f"{protocol}://{self.ip_address}:{port}/ws"
|
||||
|
||||
async def _keep_alive(self):
|
||||
"""Keep the WebSocket connection alive with automatic reconnection."""
|
||||
retry_count = 0
|
||||
max_log_attempts = 1 # Only log the first attempt at INFO level
|
||||
log_interval = 500 # Then log every 500th attempt (significantly increased from 30)
|
||||
last_warning_time = 0
|
||||
min_warning_interval = 30 # Minimum seconds between connection lost warnings
|
||||
min_retry_delay = 0.5 # Minimum delay between connection attempts (500ms)
|
||||
|
||||
while not self._closed:
|
||||
try:
|
||||
if self._ws is None or (
|
||||
self._ws and self._ws.state == websockets.protocol.State.CLOSED
|
||||
):
|
||||
try:
|
||||
retry_count += 1
|
||||
|
||||
# Add a minimum delay between connection attempts to avoid flooding
|
||||
if retry_count > 1:
|
||||
await asyncio.sleep(min_retry_delay)
|
||||
|
||||
# Only log the first attempt at INFO level, then every Nth attempt
|
||||
if retry_count == 1:
|
||||
self.logger.info(f"Attempting WebSocket connection to {self.ws_uri}")
|
||||
elif retry_count % log_interval == 0:
|
||||
self.logger.info(
|
||||
f"Still attempting WebSocket connection (attempt {retry_count})..."
|
||||
)
|
||||
else:
|
||||
# All other attempts are logged at DEBUG level
|
||||
self.logger.debug(
|
||||
f"Attempting WebSocket connection to {self.ws_uri} (attempt {retry_count})"
|
||||
)
|
||||
|
||||
self._ws = await asyncio.wait_for(
|
||||
websockets.connect(
|
||||
self.ws_uri,
|
||||
max_size=1024 * 1024 * 10, # 10MB limit
|
||||
max_queue=32,
|
||||
ping_interval=self._ping_interval,
|
||||
ping_timeout=self._ping_timeout,
|
||||
close_timeout=5,
|
||||
compression=None, # Disable compression to reduce overhead
|
||||
),
|
||||
timeout=120,
|
||||
)
|
||||
self.logger.info("WebSocket connection established")
|
||||
|
||||
# Authentication will be handled by the first command that needs it
|
||||
# Don't do authentication here to avoid recv conflicts
|
||||
|
||||
self._reconnect_delay = 1 # Reset reconnect delay on successful connection
|
||||
self._last_ping = time.time()
|
||||
retry_count = 0 # Reset retry count on successful connection
|
||||
self._authenticated = False # Reset auth status on new connection
|
||||
|
||||
except (asyncio.TimeoutError, websockets.exceptions.WebSocketException) as e:
|
||||
next_retry = self._reconnect_delay
|
||||
|
||||
# Only log the first error at WARNING level, then every Nth attempt
|
||||
if retry_count == 1:
|
||||
self.logger.warning(
|
||||
f"Computer API Server not ready yet. Will retry automatically."
|
||||
)
|
||||
elif retry_count % log_interval == 0:
|
||||
self.logger.warning(
|
||||
f"Still waiting for Computer API Server (attempt {retry_count})..."
|
||||
)
|
||||
else:
|
||||
# All other errors are logged at DEBUG level
|
||||
self.logger.debug(f"Connection attempt {retry_count} failed: {e}")
|
||||
|
||||
if self._ws:
|
||||
try:
|
||||
await self._ws.close()
|
||||
except:
|
||||
pass
|
||||
self._ws = None
|
||||
|
||||
# Regular ping to check connection
|
||||
if self._ws and self._ws.state == websockets.protocol.State.OPEN:
|
||||
try:
|
||||
if time.time() - self._last_ping >= self._ping_interval:
|
||||
pong_waiter = await self._ws.ping()
|
||||
await asyncio.wait_for(pong_waiter, timeout=self._ping_timeout)
|
||||
self._last_ping = time.time()
|
||||
except Exception as e:
|
||||
self.logger.debug(f"Ping failed: {e}")
|
||||
if self._ws:
|
||||
try:
|
||||
await self._ws.close()
|
||||
except:
|
||||
pass
|
||||
self._ws = None
|
||||
continue
|
||||
|
||||
await asyncio.sleep(1)
|
||||
|
||||
except Exception as e:
|
||||
current_time = time.time()
|
||||
# Only log connection lost warnings at most once every min_warning_interval seconds
|
||||
if current_time - last_warning_time >= min_warning_interval:
|
||||
self.logger.warning(
|
||||
f"Computer API Server connection lost. Will retry automatically."
|
||||
)
|
||||
last_warning_time = current_time
|
||||
else:
|
||||
# Log at debug level instead
|
||||
self.logger.debug(f"Connection lost: {e}")
|
||||
|
||||
if self._ws:
|
||||
try:
|
||||
await self._ws.close()
|
||||
except:
|
||||
pass
|
||||
self._ws = None
|
||||
|
||||
async def _ensure_connection(self):
|
||||
"""Ensure WebSocket connection is established."""
|
||||
if self._reconnect_task is None or self._reconnect_task.done():
|
||||
self._reconnect_task = asyncio.create_task(self._keep_alive())
|
||||
|
||||
retry_count = 0
|
||||
max_retries = 5
|
||||
|
||||
while retry_count < max_retries:
|
||||
try:
|
||||
if self._ws and self._ws.state == websockets.protocol.State.OPEN:
|
||||
return
|
||||
retry_count += 1
|
||||
await asyncio.sleep(1)
|
||||
except Exception as e:
|
||||
# Only log at ERROR level for the last retry attempt
|
||||
if retry_count == max_retries - 1:
|
||||
self.logger.error(
|
||||
f"Persistent connection check error after {retry_count} attempts: {e}"
|
||||
)
|
||||
else:
|
||||
self.logger.debug(f"Connection check error (attempt {retry_count}): {e}")
|
||||
retry_count += 1
|
||||
await asyncio.sleep(1)
|
||||
continue
|
||||
|
||||
raise ConnectionError("Failed to establish WebSocket connection after multiple retries")
|
||||
|
||||
async def _send_command(self, command: str, params: Optional[Dict] = None) -> Dict[str, Any]:
|
||||
"""Send command through WebSocket."""
|
||||
max_retries = 3
|
||||
retry_count = 0
|
||||
last_error = None
|
||||
|
||||
# Acquire lock to ensure only one command is processed at a time
|
||||
async with self._command_lock:
|
||||
self.logger.debug(f"Acquired lock for command: {command}")
|
||||
while retry_count < max_retries:
|
||||
try:
|
||||
await self._ensure_connection()
|
||||
if not self._ws:
|
||||
raise ConnectionError("WebSocket connection is not established")
|
||||
|
||||
# Handle authentication if needed
|
||||
if self.api_key and self.vm_name and not self._authenticated:
|
||||
self.logger.info("Performing authentication handshake...")
|
||||
auth_message = {
|
||||
"command": "authenticate",
|
||||
"params": {
|
||||
"api_key": self.api_key,
|
||||
"container_name": self.vm_name
|
||||
}
|
||||
}
|
||||
await self._ws.send(json.dumps(auth_message))
|
||||
|
||||
# Wait for authentication response
|
||||
auth_response = await asyncio.wait_for(self._ws.recv(), timeout=10)
|
||||
auth_result = json.loads(auth_response)
|
||||
|
||||
if not auth_result.get("success"):
|
||||
error_msg = auth_result.get("error", "Authentication failed")
|
||||
self.logger.error(f"Authentication failed: {error_msg}")
|
||||
self._authenticated = False
|
||||
raise ConnectionError(f"Authentication failed: {error_msg}")
|
||||
|
||||
self.logger.info("Authentication successful")
|
||||
self._authenticated = True
|
||||
|
||||
message = {"command": command, "params": params or {}}
|
||||
await self._ws.send(json.dumps(message))
|
||||
response = await asyncio.wait_for(self._ws.recv(), timeout=30)
|
||||
self.logger.debug(f"Completed command: {command}")
|
||||
return json.loads(response)
|
||||
except Exception as e:
|
||||
last_error = e
|
||||
retry_count += 1
|
||||
if retry_count < max_retries:
|
||||
# Only log at debug level for intermediate retries
|
||||
self.logger.debug(
|
||||
f"Command '{command}' failed (attempt {retry_count}/{max_retries}): {e}"
|
||||
)
|
||||
await asyncio.sleep(1)
|
||||
continue
|
||||
else:
|
||||
# Only log at error level for the final failure
|
||||
self.logger.error(
|
||||
f"Failed to send command '{command}' after {max_retries} retries"
|
||||
)
|
||||
self.logger.debug(f"Command failure details: {e}")
|
||||
raise last_error if last_error else RuntimeError("Failed to send command")
|
||||
|
||||
async def wait_for_ready(self, timeout: int = 60, interval: float = 1.0):
|
||||
"""Wait for WebSocket connection to become available."""
|
||||
start_time = time.time()
|
||||
last_error = None
|
||||
attempt_count = 0
|
||||
progress_interval = 10 # Log progress every 10 seconds
|
||||
last_progress_time = start_time
|
||||
|
||||
# Disable detailed logging for connection attempts
|
||||
self._log_connection_attempts = False
|
||||
|
||||
try:
|
||||
self.logger.info(
|
||||
f"Waiting for Computer API Server to be ready (timeout: {timeout}s)..."
|
||||
)
|
||||
|
||||
# Start the keep-alive task if it's not already running
|
||||
if self._reconnect_task is None or self._reconnect_task.done():
|
||||
self._reconnect_task = asyncio.create_task(self._keep_alive())
|
||||
|
||||
# Wait for the connection to be established
|
||||
while time.time() - start_time < timeout:
|
||||
try:
|
||||
attempt_count += 1
|
||||
current_time = time.time()
|
||||
|
||||
# Log progress periodically without flooding logs
|
||||
if current_time - last_progress_time >= progress_interval:
|
||||
elapsed = current_time - start_time
|
||||
self.logger.info(
|
||||
f"Still waiting for Computer API Server... (elapsed: {elapsed:.1f}s, attempts: {attempt_count})"
|
||||
)
|
||||
last_progress_time = current_time
|
||||
|
||||
# Check if we have a connection
|
||||
if self._ws and self._ws.state == websockets.protocol.State.OPEN:
|
||||
# Test the connection with a simple command
|
||||
try:
|
||||
await self._send_command("get_screen_size")
|
||||
elapsed = time.time() - start_time
|
||||
self.logger.info(
|
||||
f"Computer API Server is ready (after {elapsed:.1f}s, {attempt_count} attempts)"
|
||||
)
|
||||
return # Connection is fully working
|
||||
except Exception as e:
|
||||
last_error = e
|
||||
self.logger.debug(f"Connection test failed: {e}")
|
||||
|
||||
# Wait before trying again
|
||||
await asyncio.sleep(interval)
|
||||
|
||||
except Exception as e:
|
||||
last_error = e
|
||||
self.logger.debug(f"Connection attempt {attempt_count} failed: {e}")
|
||||
await asyncio.sleep(interval)
|
||||
|
||||
# If we get here, we've timed out
|
||||
error_msg = f"Could not connect to {self.ip_address} after {timeout} seconds"
|
||||
if last_error:
|
||||
error_msg += f": {str(last_error)}"
|
||||
self.logger.error(error_msg)
|
||||
raise TimeoutError(error_msg)
|
||||
finally:
|
||||
# Reset to default logging behavior
|
||||
self._log_connection_attempts = False
|
||||
|
||||
def close(self):
|
||||
"""Close WebSocket connection.
|
||||
|
||||
Note: In host computer server mode, we leave the connection open
|
||||
to allow other clients to connect to the same server. The server
|
||||
will handle cleaning up idle connections.
|
||||
"""
|
||||
# Only cancel the reconnect task
|
||||
if self._reconnect_task:
|
||||
self._reconnect_task.cancel()
|
||||
|
||||
# Don't set closed flag or close websocket by default
|
||||
# This allows the server to stay connected for other clients
|
||||
# self._closed = True
|
||||
# if self._ws:
|
||||
# asyncio.create_task(self._ws.close())
|
||||
# self._ws = None
|
||||
|
||||
def force_close(self):
|
||||
"""Force close the WebSocket connection.
|
||||
|
||||
This method should be called when you want to completely
|
||||
shut down the connection, not just for regular cleanup.
|
||||
"""
|
||||
self._closed = True
|
||||
if self._reconnect_task:
|
||||
self._reconnect_task.cancel()
|
||||
if self._ws:
|
||||
asyncio.create_task(self._ws.close())
|
||||
self._ws = None
|
||||
|
||||
# Mouse Actions
|
||||
async def mouse_down(self, x: Optional[int] = None, y: Optional[int] = None, button: str = "left") -> None:
|
||||
await self._send_command("mouse_down", {"x": x, "y": y, "button": button})
|
||||
|
||||
async def mouse_up(self, x: Optional[int] = None, y: Optional[int] = None, button: str = "left") -> None:
|
||||
await self._send_command("mouse_up", {"x": x, "y": y, "button": button})
|
||||
|
||||
async def left_click(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
|
||||
await self._send_command("left_click", {"x": x, "y": y})
|
||||
|
||||
async def right_click(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
|
||||
await self._send_command("right_click", {"x": x, "y": y})
|
||||
|
||||
async def double_click(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
|
||||
await self._send_command("double_click", {"x": x, "y": y})
|
||||
|
||||
async def move_cursor(self, x: int, y: int) -> None:
|
||||
await self._send_command("move_cursor", {"x": x, "y": y})
|
||||
|
||||
async def drag_to(self, x: int, y: int, button: "MouseButton" = "left", duration: float = 0.5) -> None:
|
||||
await self._send_command(
|
||||
"drag_to", {"x": x, "y": y, "button": button, "duration": duration}
|
||||
)
|
||||
|
||||
async def drag(self, path: List[Tuple[int, int]], button: "MouseButton" = "left", duration: float = 0.5) -> None:
|
||||
await self._send_command(
|
||||
"drag", {"path": path, "button": button, "duration": duration}
|
||||
)
|
||||
|
||||
# Keyboard Actions
|
||||
async def key_down(self, key: "KeyType") -> None:
|
||||
await self._send_command("key_down", {"key": key})
|
||||
|
||||
async def key_up(self, key: "KeyType") -> None:
|
||||
await self._send_command("key_up", {"key": key})
|
||||
|
||||
async def type_text(self, text: str) -> None:
|
||||
# Temporary fix for https://github.com/trycua/cua/issues/165
|
||||
# Check if text contains Unicode characters
|
||||
if any(ord(char) > 127 for char in text):
|
||||
# For Unicode text, use clipboard and paste
|
||||
await self.set_clipboard(text)
|
||||
await self.hotkey(Key.COMMAND, 'v')
|
||||
else:
|
||||
# For ASCII text, use the regular typing method
|
||||
await self._send_command("type_text", {"text": text})
|
||||
|
||||
async def press(self, key: "KeyType") -> None:
|
||||
"""Press a single key.
|
||||
|
||||
Args:
|
||||
key: The key to press. Can be any of:
|
||||
- A Key enum value (recommended), e.g. Key.PAGE_DOWN
|
||||
- A direct key value string, e.g. 'pagedown'
|
||||
- A single character string, e.g. 'a'
|
||||
|
||||
Examples:
|
||||
```python
|
||||
# Using enum (recommended)
|
||||
await interface.press(Key.PAGE_DOWN)
|
||||
await interface.press(Key.ENTER)
|
||||
|
||||
# Using direct values
|
||||
await interface.press('pagedown')
|
||||
await interface.press('enter')
|
||||
|
||||
# Using single characters
|
||||
await interface.press('a')
|
||||
```
|
||||
|
||||
Raises:
|
||||
ValueError: If the key type is invalid or the key is not recognized
|
||||
"""
|
||||
if isinstance(key, Key):
|
||||
actual_key = key.value
|
||||
elif isinstance(key, str):
|
||||
# Try to convert to enum if it matches a known key
|
||||
key_or_enum = Key.from_string(key)
|
||||
actual_key = key_or_enum.value if isinstance(key_or_enum, Key) else key_or_enum
|
||||
else:
|
||||
raise ValueError(f"Invalid key type: {type(key)}. Must be Key enum or string.")
|
||||
|
||||
await self._send_command("press_key", {"key": actual_key})
|
||||
|
||||
async def press_key(self, key: "KeyType") -> None:
|
||||
"""DEPRECATED: Use press() instead.
|
||||
|
||||
This method is kept for backward compatibility but will be removed in a future version.
|
||||
Please use the press() method instead.
|
||||
"""
|
||||
await self.press(key)
|
||||
|
||||
async def hotkey(self, *keys: "KeyType") -> None:
|
||||
"""Press multiple keys simultaneously.
|
||||
|
||||
Args:
|
||||
*keys: Multiple keys to press simultaneously. Each key can be any of:
|
||||
- A Key enum value (recommended), e.g. Key.COMMAND
|
||||
- A direct key value string, e.g. 'command'
|
||||
- A single character string, e.g. 'a'
|
||||
|
||||
Examples:
|
||||
```python
|
||||
# Using enums (recommended)
|
||||
await interface.hotkey(Key.COMMAND, Key.C) # Copy
|
||||
await interface.hotkey(Key.COMMAND, Key.V) # Paste
|
||||
|
||||
# Using mixed formats
|
||||
await interface.hotkey(Key.COMMAND, 'a') # Select all
|
||||
```
|
||||
|
||||
Raises:
|
||||
ValueError: If any key type is invalid or not recognized
|
||||
"""
|
||||
actual_keys = []
|
||||
for key in keys:
|
||||
if isinstance(key, Key):
|
||||
actual_keys.append(key.value)
|
||||
elif isinstance(key, str):
|
||||
# Try to convert to enum if it matches a known key
|
||||
key_or_enum = Key.from_string(key)
|
||||
actual_keys.append(key_or_enum.value if isinstance(key_or_enum, Key) else key_or_enum)
|
||||
else:
|
||||
raise ValueError(f"Invalid key type: {type(key)}. Must be Key enum or string.")
|
||||
|
||||
await self._send_command("hotkey", {"keys": actual_keys})
|
||||
|
||||
# Scrolling Actions
|
||||
async def scroll(self, x: int, y: int) -> None:
|
||||
await self._send_command("scroll", {"x": x, "y": y})
|
||||
|
||||
async def scroll_down(self, clicks: int = 1) -> None:
|
||||
await self._send_command("scroll_down", {"clicks": clicks})
|
||||
|
||||
async def scroll_up(self, clicks: int = 1) -> None:
|
||||
await self._send_command("scroll_up", {"clicks": clicks})
|
||||
|
||||
# Screen Actions
|
||||
async def screenshot(
|
||||
self,
|
||||
boxes: Optional[List[Tuple[int, int, int, int]]] = None,
|
||||
box_color: str = "#FF0000",
|
||||
box_thickness: int = 2,
|
||||
scale_factor: float = 1.0,
|
||||
) -> bytes:
|
||||
"""Take a screenshot with optional box drawing and scaling.
|
||||
|
||||
Args:
|
||||
boxes: Optional list of (x, y, width, height) tuples defining boxes to draw in screen coordinates
|
||||
box_color: Color of the boxes in hex format (default: "#FF0000" red)
|
||||
box_thickness: Thickness of the box borders in pixels (default: 2)
|
||||
scale_factor: Factor to scale the final image by (default: 1.0)
|
||||
Use > 1.0 to enlarge, < 1.0 to shrink (e.g., 0.5 for half size, 2.0 for double)
|
||||
|
||||
Returns:
|
||||
bytes: The screenshot image data, optionally with boxes drawn on it and scaled
|
||||
"""
|
||||
result = await self._send_command("screenshot")
|
||||
if not result.get("image_data"):
|
||||
raise RuntimeError("Failed to take screenshot")
|
||||
|
||||
screenshot = decode_base64_image(result["image_data"])
|
||||
|
||||
if boxes:
|
||||
# Get the natural scaling between screen and screenshot
|
||||
screen_size = await self.get_screen_size()
|
||||
screenshot_width, screenshot_height = bytes_to_image(screenshot).size
|
||||
width_scale = screenshot_width / screen_size["width"]
|
||||
height_scale = screenshot_height / screen_size["height"]
|
||||
|
||||
# Scale box coordinates from screen space to screenshot space
|
||||
for box in boxes:
|
||||
scaled_box = (
|
||||
int(box[0] * width_scale), # x
|
||||
int(box[1] * height_scale), # y
|
||||
int(box[2] * width_scale), # width
|
||||
int(box[3] * height_scale), # height
|
||||
)
|
||||
screenshot = draw_box(
|
||||
screenshot,
|
||||
x=scaled_box[0],
|
||||
y=scaled_box[1],
|
||||
width=scaled_box[2],
|
||||
height=scaled_box[3],
|
||||
color=box_color,
|
||||
thickness=box_thickness,
|
||||
)
|
||||
|
||||
if scale_factor != 1.0:
|
||||
screenshot = resize_image(screenshot, scale_factor)
|
||||
|
||||
return screenshot
|
||||
|
||||
async def get_screen_size(self) -> Dict[str, int]:
|
||||
result = await self._send_command("get_screen_size")
|
||||
if result["success"] and result["size"]:
|
||||
return result["size"]
|
||||
raise RuntimeError("Failed to get screen size")
|
||||
|
||||
async def get_cursor_position(self) -> Dict[str, int]:
|
||||
result = await self._send_command("get_cursor_position")
|
||||
if result["success"] and result["position"]:
|
||||
return result["position"]
|
||||
raise RuntimeError("Failed to get cursor position")
|
||||
|
||||
# Clipboard Actions
|
||||
async def copy_to_clipboard(self) -> str:
|
||||
result = await self._send_command("copy_to_clipboard")
|
||||
if result["success"] and result["content"]:
|
||||
return result["content"]
|
||||
raise RuntimeError("Failed to get clipboard content")
|
||||
|
||||
async def set_clipboard(self, text: str) -> None:
|
||||
await self._send_command("set_clipboard", {"text": text})
|
||||
|
||||
# File System Actions
|
||||
async def file_exists(self, path: str) -> bool:
|
||||
result = await self._send_command("file_exists", {"path": path})
|
||||
return result.get("exists", False)
|
||||
|
||||
async def directory_exists(self, path: str) -> bool:
|
||||
result = await self._send_command("directory_exists", {"path": path})
|
||||
return result.get("exists", False)
|
||||
|
||||
async def list_dir(self, path: str) -> list[str]:
|
||||
result = await self._send_command("list_dir", {"path": path})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to list directory"))
|
||||
return result.get("files", [])
|
||||
|
||||
async def read_text(self, path: str) -> str:
|
||||
result = await self._send_command("read_text", {"path": path})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to read file"))
|
||||
return result.get("content", "")
|
||||
|
||||
async def write_text(self, path: str, content: str) -> None:
|
||||
result = await self._send_command("write_text", {"path": path, "content": content})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to write file"))
|
||||
|
||||
async def read_bytes(self, path: str) -> bytes:
|
||||
result = await self._send_command("read_bytes", {"path": path})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to read file"))
|
||||
content_b64 = result.get("content_b64", "")
|
||||
return decode_base64_image(content_b64)
|
||||
|
||||
async def write_bytes(self, path: str, content: bytes) -> None:
|
||||
result = await self._send_command("write_bytes", {"path": path, "content_b64": encode_base64_image(content)})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to write file"))
|
||||
|
||||
async def delete_file(self, path: str) -> None:
|
||||
result = await self._send_command("delete_file", {"path": path})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to delete file"))
|
||||
|
||||
async def create_dir(self, path: str) -> None:
|
||||
result = await self._send_command("create_dir", {"path": path})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to create directory"))
|
||||
|
||||
async def delete_dir(self, path: str) -> None:
|
||||
result = await self._send_command("delete_dir", {"path": path})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to delete directory"))
|
||||
|
||||
async def run_command(self, command: str) -> Tuple[str, str]:
|
||||
result = await self._send_command("run_command", {"command": command})
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to run command"))
|
||||
return result.get("stdout", ""), result.get("stderr", "")
|
||||
|
||||
# Accessibility Actions
|
||||
async def get_accessibility_tree(self) -> Dict[str, Any]:
|
||||
"""Get the accessibility tree of the current screen."""
|
||||
result = await self._send_command("get_accessibility_tree")
|
||||
if not result.get("success", False):
|
||||
raise RuntimeError(result.get("error", "Failed to get accessibility tree"))
|
||||
return result
|
||||
|
||||
async def get_active_window_bounds(self) -> Dict[str, int]:
|
||||
"""Get the bounds of the currently active window."""
|
||||
result = await self._send_command("get_active_window_bounds")
|
||||
if result["success"] and result["bounds"]:
|
||||
return result["bounds"]
|
||||
raise RuntimeError("Failed to get active window bounds")
|
||||
|
||||
async def to_screen_coordinates(self, x: float, y: float) -> tuple[float, float]:
|
||||
"""Convert screenshot coordinates to screen coordinates.
|
||||
|
||||
Args:
|
||||
x: X coordinate in screenshot space
|
||||
y: Y coordinate in screenshot space
|
||||
|
||||
Returns:
|
||||
tuple[float, float]: (x, y) coordinates in screen space
|
||||
"""
|
||||
screen_size = await self.get_screen_size()
|
||||
screenshot = await self.screenshot()
|
||||
screenshot_img = bytes_to_image(screenshot)
|
||||
screenshot_width, screenshot_height = screenshot_img.size
|
||||
|
||||
# Calculate scaling factors
|
||||
width_scale = screen_size["width"] / screenshot_width
|
||||
height_scale = screen_size["height"] / screenshot_height
|
||||
|
||||
# Convert coordinates
|
||||
screen_x = x * width_scale
|
||||
screen_y = y * height_scale
|
||||
|
||||
return screen_x, screen_y
|
||||
|
||||
async def to_screenshot_coordinates(self, x: float, y: float) -> tuple[float, float]:
|
||||
"""Convert screen coordinates to screenshot coordinates.
|
||||
|
||||
Args:
|
||||
x: X coordinate in screen space
|
||||
y: Y coordinate in screen space
|
||||
|
||||
Returns:
|
||||
tuple[float, float]: (x, y) coordinates in screenshot space
|
||||
"""
|
||||
screen_size = await self.get_screen_size()
|
||||
screenshot = await self.screenshot()
|
||||
screenshot_img = bytes_to_image(screenshot)
|
||||
screenshot_width, screenshot_height = screenshot_img.size
|
||||
|
||||
# Calculate scaling factors
|
||||
width_scale = screenshot_width / screen_size["width"]
|
||||
height_scale = screenshot_height / screen_size["height"]
|
||||
|
||||
# Convert coordinates
|
||||
screenshot_x = x * width_scale
|
||||
screenshot_y = y * height_scale
|
||||
|
||||
return screenshot_x, screenshot_y
|
||||
@@ -72,12 +72,23 @@ cp -f .build/release/lume "$TEMP_ROOT/usr/local/bin/"
|
||||
|
||||
# Build the installer package
|
||||
log "essential" "Building installer package..."
|
||||
pkgbuild --root "$TEMP_ROOT" \
|
||||
if ! pkgbuild --root "$TEMP_ROOT" \
|
||||
--identifier "com.trycua.lume" \
|
||||
--version "1.0" \
|
||||
--install-location "/" \
|
||||
--sign "$CERT_INSTALLER_NAME" \
|
||||
./.release/lume.pkg 2> /dev/null
|
||||
./.release/lume.pkg; then
|
||||
log "error" "Failed to build installer package"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify the package was created
|
||||
if [ ! -f "./.release/lume.pkg" ]; then
|
||||
log "error" "Package file ./.release/lume.pkg was not created"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "essential" "Package created successfully"
|
||||
|
||||
# Submit for notarization using stored credentials
|
||||
log "essential" "Submitting for notarization..."
|
||||
@@ -89,24 +100,33 @@ if [ "$LOG_LEVEL" = "minimal" ] || [ "$LOG_LEVEL" = "none" ]; then
|
||||
--password "${APP_SPECIFIC_PASSWORD}" \
|
||||
--wait 2>&1)
|
||||
|
||||
# Just show success or failure
|
||||
# Check if notarization was successful
|
||||
if echo "$NOTARY_OUTPUT" | grep -q "status: Accepted"; then
|
||||
log "essential" "Notarization successful!"
|
||||
else
|
||||
log "error" "Notarization failed. Please check logs."
|
||||
log "error" "Notarization output:"
|
||||
echo "$NOTARY_OUTPUT"
|
||||
exit 1
|
||||
fi
|
||||
else
|
||||
# Normal verbose output
|
||||
xcrun notarytool submit ./.release/lume.pkg \
|
||||
if ! xcrun notarytool submit ./.release/lume.pkg \
|
||||
--apple-id "${APPLE_ID}" \
|
||||
--team-id "${TEAM_ID}" \
|
||||
--password "${APP_SPECIFIC_PASSWORD}" \
|
||||
--wait
|
||||
--wait; then
|
||||
log "error" "Notarization failed"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
# Staple the notarization ticket
|
||||
log "essential" "Stapling notarization ticket..."
|
||||
xcrun stapler staple ./.release/lume.pkg > /dev/null 2>&1
|
||||
if ! xcrun stapler staple ./.release/lume.pkg > /dev/null 2>&1; then
|
||||
log "error" "Failed to staple notarization ticket"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Create temporary directory for package extraction
|
||||
EXTRACT_ROOT=$(mktemp -d)
|
||||
|
||||
@@ -34,10 +34,7 @@ pip install "cua-agent[anthropic]" # Anthropic Cua Loop
|
||||
pip install "cua-agent[uitars]" # UI-Tars support
|
||||
pip install "cua-agent[omni]" # Cua Loop based on OmniParser (includes Ollama for local models)
|
||||
pip install "cua-agent[ui]" # Gradio UI for the agent
|
||||
|
||||
# For local UI-TARS with MLX support, you need to manually install mlx-vlm:
|
||||
pip install "cua-agent[uitars-mlx]"
|
||||
pip install git+https://github.com/ddupont808/mlx-vlm.git@stable/fix/qwen2-position-id # PR: https://github.com/Blaizzy/mlx-vlm/pull/349
|
||||
pip install "cua-agent[uitars-mlx]" # MLX UI-Tars support
|
||||
```
|
||||
|
||||
## Run
|
||||
@@ -6,7 +6,7 @@ import logging
|
||||
__version__ = "0.1.0"
|
||||
|
||||
# Initialize logging
|
||||
logger = logging.getLogger("cua.agent")
|
||||
logger = logging.getLogger("agent")
|
||||
|
||||
# Initialize telemetry when the package is imported
|
||||
try:
|
||||
@@ -11,10 +11,8 @@ from .types import AgentResponse
|
||||
from .factory import LoopFactory
|
||||
from .provider_config import DEFAULT_MODELS, ENV_VARS
|
||||
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ComputerAgent:
|
||||
"""A computer agent that can perform automated tasks using natural language instructions."""
|
||||
|
||||
@@ -81,16 +81,27 @@ class StandardMessageManager:
|
||||
if not self.config.num_images_to_keep:
|
||||
return messages
|
||||
|
||||
# Find user messages with images
|
||||
# Find messages with images (both user messages and tool call outputs)
|
||||
image_messages = []
|
||||
for msg in messages:
|
||||
has_image = False
|
||||
|
||||
# Check user messages with images
|
||||
if msg["role"] == "user" and isinstance(msg["content"], list):
|
||||
has_image = any(
|
||||
item.get("type") == "image_url" or item.get("type") == "image"
|
||||
for item in msg["content"]
|
||||
)
|
||||
if has_image:
|
||||
image_messages.append(msg)
|
||||
|
||||
# Check assistant messages with tool calls that have images
|
||||
elif msg["role"] == "assistant" and isinstance(msg["content"], list):
|
||||
for item in msg["content"]:
|
||||
if item.get("type") == "tool_result" and "base64_image" in item:
|
||||
has_image = True
|
||||
break
|
||||
|
||||
if has_image:
|
||||
image_messages.append(msg)
|
||||
|
||||
# If we don't have more images than the limit, return all messages
|
||||
if len(image_messages) <= self.config.num_images_to_keep:
|
||||
@@ -100,13 +111,35 @@ class StandardMessageManager:
|
||||
images_to_keep = image_messages[-self.config.num_images_to_keep :]
|
||||
images_to_remove = image_messages[: -self.config.num_images_to_keep]
|
||||
|
||||
# Create a new message list without the older images
|
||||
# Create a new message list, removing images from older messages
|
||||
result = []
|
||||
for msg in messages:
|
||||
if msg in images_to_remove:
|
||||
# Skip this message
|
||||
continue
|
||||
result.append(msg)
|
||||
# Remove images from this message but keep the text content
|
||||
if msg["role"] == "user" and isinstance(msg["content"], list):
|
||||
# Keep only text content, remove images
|
||||
new_content = [
|
||||
item for item in msg["content"]
|
||||
if item.get("type") not in ["image_url", "image"]
|
||||
]
|
||||
if new_content: # Only add if there's still content
|
||||
result.append({"role": msg["role"], "content": new_content})
|
||||
elif msg["role"] == "assistant" and isinstance(msg["content"], list):
|
||||
# Remove base64_image from tool_result items
|
||||
new_content = []
|
||||
for item in msg["content"]:
|
||||
if item.get("type") == "tool_result" and "base64_image" in item:
|
||||
# Create a copy without the base64_image
|
||||
new_item = {k: v for k, v in item.items() if k != "base64_image"}
|
||||
new_content.append(new_item)
|
||||
else:
|
||||
new_content.append(item)
|
||||
result.append({"role": msg["role"], "content": new_content})
|
||||
else:
|
||||
# For other message types, keep as is
|
||||
result.append(msg)
|
||||
else:
|
||||
result.append(msg)
|
||||
|
||||
return result
|
||||
|
||||
@@ -34,7 +34,7 @@ flush = _default_flush
|
||||
is_telemetry_enabled = _default_is_telemetry_enabled
|
||||
is_telemetry_globally_disabled = _default_is_telemetry_globally_disabled
|
||||
|
||||
logger = logging.getLogger("cua.agent.telemetry")
|
||||
logger = logging.getLogger("agent.telemetry")
|
||||
|
||||
try:
|
||||
# Import from core telemetry
|
||||
@@ -50,8 +50,8 @@ class BashTool(BaseBashTool, BaseAnthropicTool):
|
||||
|
||||
try:
|
||||
async with asyncio.timeout(self._timeout):
|
||||
stdout, stderr = await self.computer.interface.run_command(command)
|
||||
return CLIResult(output=stdout or "", error=stderr or "")
|
||||
result = await self.computer.interface.run_command(command)
|
||||
return CLIResult(output=result.stdout or "", error=result.stderr or "")
|
||||
except asyncio.TimeoutError as e:
|
||||
raise ToolError(f"Command timed out after {self._timeout} seconds") from e
|
||||
except Exception as e:
|
||||
@@ -205,26 +205,6 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
self.logger.info(f" Coordinates: ({x}, {y})")
|
||||
|
||||
try:
|
||||
# Take pre-action screenshot to get current dimensions
|
||||
pre_screenshot = await self.computer.interface.screenshot()
|
||||
pre_img = Image.open(io.BytesIO(pre_screenshot))
|
||||
|
||||
# Scale image to match screen dimensions if needed
|
||||
if pre_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling image from {pre_img.size} to {self.width}x{self.height} to match screen dimensions"
|
||||
)
|
||||
if not isinstance(self.width, int) or not isinstance(self.height, int):
|
||||
raise ToolError("Screen dimensions must be integers")
|
||||
size = (int(self.width), int(self.height))
|
||||
pre_img = pre_img.resize(size, Image.Resampling.LANCZOS)
|
||||
# Save the scaled image back to bytes
|
||||
buffer = io.BytesIO()
|
||||
pre_img.save(buffer, format="PNG")
|
||||
pre_screenshot = buffer.getvalue()
|
||||
|
||||
self.logger.info(f" Current dimensions: {pre_img.width}x{pre_img.height}")
|
||||
|
||||
# Perform the click action
|
||||
if action == "left_click":
|
||||
self.logger.info(f"Clicking at ({x}, {y})")
|
||||
@@ -242,45 +222,14 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
# Wait briefly for any UI changes
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Take and save post-action screenshot
|
||||
post_screenshot = await self.computer.interface.screenshot()
|
||||
post_img = Image.open(io.BytesIO(post_screenshot))
|
||||
|
||||
# Scale post-action image if needed
|
||||
if post_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling post-action image from {post_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
post_img = post_img.resize(
|
||||
(self.width, self.height), Image.Resampling.LANCZOS
|
||||
)
|
||||
buffer = io.BytesIO()
|
||||
post_img.save(buffer, format="PNG")
|
||||
post_screenshot = buffer.getvalue()
|
||||
|
||||
return ToolResult(
|
||||
output=f"Performed {action} at ({x}, {y})",
|
||||
base64_image=base64.b64encode(post_screenshot).decode(),
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error during {action} action: {str(e)}")
|
||||
raise ToolError(f"Failed to perform {action}: {str(e)}")
|
||||
else:
|
||||
try:
|
||||
# Take pre-action screenshot
|
||||
pre_screenshot = await self.computer.interface.screenshot()
|
||||
pre_img = Image.open(io.BytesIO(pre_screenshot))
|
||||
|
||||
# Scale image if needed
|
||||
if pre_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling image from {pre_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
if not isinstance(self.width, int) or not isinstance(self.height, int):
|
||||
raise ToolError("Screen dimensions must be integers")
|
||||
size = (int(self.width), int(self.height))
|
||||
pre_img = pre_img.resize(size, Image.Resampling.LANCZOS)
|
||||
|
||||
# Perform the click action
|
||||
if action == "left_click":
|
||||
self.logger.info("Performing left click at current position")
|
||||
@@ -295,25 +244,8 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
# Wait briefly for any UI changes
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Take post-action screenshot
|
||||
post_screenshot = await self.computer.interface.screenshot()
|
||||
post_img = Image.open(io.BytesIO(post_screenshot))
|
||||
|
||||
# Scale post-action image if needed
|
||||
if post_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling post-action image from {post_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
post_img = post_img.resize(
|
||||
(self.width, self.height), Image.Resampling.LANCZOS
|
||||
)
|
||||
buffer = io.BytesIO()
|
||||
post_img.save(buffer, format="PNG")
|
||||
post_screenshot = buffer.getvalue()
|
||||
|
||||
return ToolResult(
|
||||
output=f"Performed {action} at current position",
|
||||
base64_image=base64.b64encode(post_screenshot).decode(),
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error during {action} action: {str(e)}")
|
||||
@@ -328,20 +260,6 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
raise ToolError(f"{text} must be a string")
|
||||
|
||||
try:
|
||||
# Take pre-action screenshot
|
||||
pre_screenshot = await self.computer.interface.screenshot()
|
||||
pre_img = Image.open(io.BytesIO(pre_screenshot))
|
||||
|
||||
# Scale image if needed
|
||||
if pre_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling image from {pre_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
if not isinstance(self.width, int) or not isinstance(self.height, int):
|
||||
raise ToolError("Screen dimensions must be integers")
|
||||
size = (int(self.width), int(self.height))
|
||||
pre_img = pre_img.resize(size, Image.Resampling.LANCZOS)
|
||||
|
||||
if action == "key":
|
||||
# Special handling for page up/down on macOS
|
||||
if text.lower() in ["pagedown", "page_down", "page down"]:
|
||||
@@ -378,25 +296,8 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
# Wait briefly for UI changes
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Take post-action screenshot
|
||||
post_screenshot = await self.computer.interface.screenshot()
|
||||
post_img = Image.open(io.BytesIO(post_screenshot))
|
||||
|
||||
# Scale post-action image if needed
|
||||
if post_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling post-action image from {post_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
post_img = post_img.resize(
|
||||
(self.width, self.height), Image.Resampling.LANCZOS
|
||||
)
|
||||
buffer = io.BytesIO()
|
||||
post_img.save(buffer, format="PNG")
|
||||
post_screenshot = buffer.getvalue()
|
||||
|
||||
return ToolResult(
|
||||
output=f"Pressed key: {output_text}",
|
||||
base64_image=base64.b64encode(post_screenshot).decode(),
|
||||
)
|
||||
|
||||
elif action == "type":
|
||||
@@ -406,66 +307,13 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
# Wait briefly for UI changes
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Take post-action screenshot
|
||||
post_screenshot = await self.computer.interface.screenshot()
|
||||
post_img = Image.open(io.BytesIO(post_screenshot))
|
||||
|
||||
# Scale post-action image if needed
|
||||
if post_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling post-action image from {post_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
post_img = post_img.resize(
|
||||
(self.width, self.height), Image.Resampling.LANCZOS
|
||||
)
|
||||
buffer = io.BytesIO()
|
||||
post_img.save(buffer, format="PNG")
|
||||
post_screenshot = buffer.getvalue()
|
||||
|
||||
return ToolResult(
|
||||
output=f"Typed text: {text}",
|
||||
base64_image=base64.b64encode(post_screenshot).decode(),
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error during {action} action: {str(e)}")
|
||||
raise ToolError(f"Failed to perform {action}: {str(e)}")
|
||||
|
||||
elif action in ("screenshot", "cursor_position"):
|
||||
if text is not None:
|
||||
raise ToolError(f"text is not accepted for {action}")
|
||||
if coordinate is not None:
|
||||
raise ToolError(f"coordinate is not accepted for {action}")
|
||||
|
||||
try:
|
||||
if action == "screenshot":
|
||||
# Take screenshot
|
||||
screenshot = await self.computer.interface.screenshot()
|
||||
img = Image.open(io.BytesIO(screenshot))
|
||||
|
||||
# Scale image if needed
|
||||
if img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling image from {img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
if not isinstance(self.width, int) or not isinstance(self.height, int):
|
||||
raise ToolError("Screen dimensions must be integers")
|
||||
size = (int(self.width), int(self.height))
|
||||
img = img.resize(size, Image.Resampling.LANCZOS)
|
||||
buffer = io.BytesIO()
|
||||
img.save(buffer, format="PNG")
|
||||
screenshot = buffer.getvalue()
|
||||
|
||||
return ToolResult(base64_image=base64.b64encode(screenshot).decode())
|
||||
|
||||
elif action == "cursor_position":
|
||||
pos = await self.computer.interface.get_cursor_position()
|
||||
x, y = pos # Unpack the tuple
|
||||
return ToolResult(output=f"X={int(x)},Y={int(y)}")
|
||||
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error during {action} action: {str(e)}")
|
||||
raise ToolError(f"Failed to perform {action}: {str(e)}")
|
||||
|
||||
elif action == "scroll":
|
||||
# Implement scroll action
|
||||
direction = kwargs.get("direction", "down")
|
||||
@@ -487,28 +335,20 @@ class ComputerTool(BaseComputerTool, BaseAnthropicTool):
|
||||
# Wait briefly for UI changes
|
||||
await asyncio.sleep(0.5)
|
||||
|
||||
# Take post-action screenshot
|
||||
post_screenshot = await self.computer.interface.screenshot()
|
||||
post_img = Image.open(io.BytesIO(post_screenshot))
|
||||
|
||||
# Scale post-action image if needed
|
||||
if post_img.size != (self.width, self.height):
|
||||
self.logger.info(
|
||||
f"Scaling post-action image from {post_img.size} to {self.width}x{self.height}"
|
||||
)
|
||||
post_img = post_img.resize((self.width, self.height), Image.Resampling.LANCZOS)
|
||||
buffer = io.BytesIO()
|
||||
post_img.save(buffer, format="PNG")
|
||||
post_screenshot = buffer.getvalue()
|
||||
|
||||
return ToolResult(
|
||||
output=f"Scrolled {direction} by {amount} steps",
|
||||
base64_image=base64.b64encode(post_screenshot).decode(),
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error during scroll action: {str(e)}")
|
||||
raise ToolError(f"Failed to perform scroll: {str(e)}")
|
||||
|
||||
elif action == "screenshot":
|
||||
# Take screenshot
|
||||
return await self.screenshot()
|
||||
elif action == "cursor_position":
|
||||
pos = await self.computer.interface.get_cursor_position()
|
||||
x, y = pos # Unpack the tuple
|
||||
return ToolResult(output=f"X={int(x)},Y={int(y)}")
|
||||
raise ToolError(f"Invalid action: {action}")
|
||||
|
||||
async def screenshot(self):
|
||||
@@ -95,13 +95,13 @@ class EditTool(BaseEditTool, BaseAnthropicTool):
|
||||
result = await self.computer.interface.run_command(
|
||||
f'[ -e "{str(path)}" ] && echo "exists" || echo "not exists"'
|
||||
)
|
||||
exists = result[0].strip() == "exists"
|
||||
exists = result.stdout.strip() == "exists"
|
||||
|
||||
if exists:
|
||||
result = await self.computer.interface.run_command(
|
||||
f'[ -d "{str(path)}" ] && echo "dir" || echo "file"'
|
||||
)
|
||||
is_dir = result[0].strip() == "dir"
|
||||
is_dir = result.stdout.strip() == "dir"
|
||||
else:
|
||||
is_dir = False
|
||||
|
||||
@@ -126,7 +126,7 @@ class EditTool(BaseEditTool, BaseAnthropicTool):
|
||||
result = await self.computer.interface.run_command(
|
||||
f'[ -d "{str(path)}" ] && echo "dir" || echo "file"'
|
||||
)
|
||||
is_dir = result[0].strip() == "dir"
|
||||
is_dir = result.stdout.strip() == "dir"
|
||||
|
||||
if is_dir:
|
||||
if view_range:
|
||||
@@ -136,7 +136,7 @@ class EditTool(BaseEditTool, BaseAnthropicTool):
|
||||
|
||||
# List directory contents using ls
|
||||
result = await self.computer.interface.run_command(f'ls -la "{str(path)}"')
|
||||
contents = result[0]
|
||||
contents = result.stdout
|
||||
if contents:
|
||||
stdout = f"Here's the files and directories in {path}:\n{contents}\n"
|
||||
else:
|
||||
@@ -272,9 +272,9 @@ class EditTool(BaseEditTool, BaseAnthropicTool):
|
||||
"""Read the content of a file using cat command."""
|
||||
try:
|
||||
result = await self.computer.interface.run_command(f'cat "{str(path)}"')
|
||||
if result[1]: # If there's stderr output
|
||||
raise ToolError(f"Error reading file: {result[1]}")
|
||||
return result[0]
|
||||
if result.stderr: # If there's stderr output
|
||||
raise ToolError(f"Error reading file: {result.stderr}")
|
||||
return result.stdout
|
||||
except Exception as e:
|
||||
raise ToolError(f"Failed to read {path}: {str(e)}")
|
||||
|
||||
@@ -291,8 +291,8 @@ class EditTool(BaseEditTool, BaseAnthropicTool):
|
||||
{content}
|
||||
EOFCUA"""
|
||||
result = await self.computer.interface.run_command(cmd)
|
||||
if result[1]: # If there's stderr output
|
||||
raise ToolError(f"Error writing file: {result[1]}")
|
||||
if result.stderr: # If there's stderr output
|
||||
raise ToolError(f"Error writing file: {result.stderr}")
|
||||
except Exception as e:
|
||||
raise ToolError(f"Failed to write to {path}: {str(e)}")
|
||||
|
||||
@@ -26,10 +26,8 @@ from .api_handler import OmniAPIHandler
|
||||
from .tools.manager import ToolManager
|
||||
from .tools import ToolResult
|
||||
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def extract_data(input_string: str, data_type: str) -> str:
|
||||
"""Extract content from code blocks."""
|
||||
pattern = f"```{data_type}" + r"(.*?)(```|$)"
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user