Some checks are pending
Bidi Control Character Guard / bidi-control-guard (push) Waiting to run
Circular Dependency Check / Check for new circular dependencies (push) Waiting to run
Citus Migration Smoke / Combined migrations on single-node Citus (push) Waiting to run
E2E Fresh Install Tests / fresh-install-e2e (push) Waiting to run
ext-v2 guardrails / Run ext-v2 guard and ESLint (push) Waiting to run
Integration Tests / Check for relevant changes (push) Waiting to run
Integration Tests / ${{ (github.event_name == 'schedule' || github.event.inputs.suite == 'full') && 'Full integration suite' || 'Tier-1 integration subset' }} (push) Blocked by required conditions
Mobile checks / Mobile lint + typecheck (push) Waiting to run
Mobile checks / Mobile unit tests (push) Waiting to run
Mobile checks / Mobile dependency audit (report) (push) Waiting to run
Mobile checks / Mobile reproducibility checks (push) Waiting to run
Secrets guard (env backups) / Ensure no tracked env backup files (push) Waiting to run
Temporal Readiness / fast-readiness (push) Waiting to run
Temporal Readiness / docker-parity (push) Waiting to run
TypeScript Type Check / Nx affected typecheck (push) Waiting to run
Unit Tests / Skipped-test budget (push) Waiting to run
Unit Tests / Nx affected unit tests (push) Waiting to run
Unit Tests / Server unit coverage (informational) (push) Waiting to run
Validate Tenant Management Schema / Check for relevant changes (push) Waiting to run
Validate Tenant Management Schema / Validate Tenant Management Schema (push) Blocked by required conditions
EE Workflows Build Guard / ee-workflows-build-guard (push) Waiting to run
Excluded: .git, node_modules, secrets/, compose.env, assemblyscript tgz Source: /opt/alga-psa on psa.joliet.tech
3.4 KiB
3.4 KiB
Getting Started
This guide will help you set up and run the AI automation platform for development.
Prerequisites
- Node.js 18+
- Docker (for Kubernetes deployment)
- Target application running with UI reflection system
Quick Start
1. Start the AI API Service
cd tools/ai-automation
npm install
npm run dev # Starts on port 4000
This starts the automation server with:
- Browser session management
- WebSocket UI state broadcasting
- Automation tool APIs
- Real-time screenshot streaming
2. Start the AI Web Service
cd tools/ai-automation/web
npm install
npm run dev # Starts on port 3000
This starts the control panel with:
- Live browser feed
- AI chat interface with tool integration
- Browser session controls (pop-out/pop-in)
- Real-time activity monitoring
3. Access the Control Panel
Open http://localhost:3000 to access the control panel.
Environment Configuration
For LLM integration, you'll need to configure environment variables. The platform supports OpenRouter for accessing various LLM models.
Create a .env file in your home directory:
# OpenRouter configuration for LLM access
CUSTOM_OPENAI_API_KEY=sk-or-v1-your-openrouter-key
CUSTOM_OPENAI_BASE_URL=https://openrouter.ai/api/v1
CUSTOM_OPENAI_MODEL=google/gemini-flash-1.5
Basic Usage
AI Automation
- Navigate to the control panel at
http://localhost:3000 - Use the chat interface to interact with the AI
- The AI has access to automation tools for browser control and codebase analysis
Example prompt:
Navigate to the companies page and help me understand the UI structure
Browser Session Control
- Pop Out: Switch to headed mode for manual intervention
- Pop In: Return to headless mode for continued automation
- Status: View current browser session information
Available Tools
The AI can use these tools:
get_ui_state- Inspect current UI stateobserve_browser- Get page contentexecute_automation_script- Run Puppeteer scriptsread_file- Read files from codebasesearch_automation_ids- Find automation IDsfind_files- Locate files by pattern
WebSocket Events
The platform broadcasts real-time updates via WebSocket:
UI_STATE_UPDATE- UI state changesscreenshot- Browser screenshotsbrowser_session_update- Session mode changes
Development Workflow
- Start both services (API and Web)
- Navigate to the control panel
- Use AI chat for intelligent automation
- Switch browser modes as needed for manual intervention
- Monitor real-time feedback and logs
Docker Development
# Build AI API service
cd tools/ai-automation
docker build -t ai-automation-api .
# Build AI Web service
cd tools/ai-automation/web
docker build -t ai-automation-web .
Troubleshooting
Common Issues
- Port conflicts: Ensure ports 3000 and 4000 are available
- WebSocket connection failed: Check that the AI API service is running
- Browser session errors: Restart the AI API service to reset browser state
- LLM authentication: Verify your API keys are correctly configured
Logs
- AI API Service logs: Check console output for automation server
- AI Web Service logs: Check Next.js console for frontend issues
- Browser session logs: Available in the control panel activity log
For more detailed troubleshooting, check the main README.md file.