### Install Dependencies and Start Development Server

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-frontend/README.md

Run these commands to install project dependencies and start the local development server.

```bash
npm install
npm run dev
```

--------------------------------

### INSTALL Request Workflow Example

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/workflow/WORKFLOW_DEBUG_COMPLETE.md

Example of a workflow orchestration for an installation request, including user approval.

```json
{
  "type": "workflow_orchestration",
  "planned_steps": 4,
  "agents_involved": ["research", "orchestrator", "system_commands"],
  "user_approvals_needed": 1,
  "workflow_preview": [
    "1. Research: Research Installation",
    "2. Orchestrator: Create Install Plan (requires approval)",
    "3. System_Commands: Install Software",
    "4. System_Commands: Verify Installation"
  ]
}
```

--------------------------------

### Install and Test Redis

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/user-guide/04-troubleshooting.md

Install the Redis server, start the service, and verify the connection.

```bash
# Install Redis
sudo apt install redis-server  # Ubuntu/Debian
brew install redis             # macOS

# Start Redis service
sudo systemctl start redis-server

# Test connection
redis-cli ping
```

--------------------------------

### Perform Manual Quick Start

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/deployment/comprehensive_deployment_guide.md

Clone the repository and manually execute the setup and startup scripts.

```bash
# 1. Clone repository
git clone https://github.com/your-org/autobot.git
cd autobot

# 2. Run setup script
./scripts/setup/setup_agent.sh

# 3. Start AutoBot
./run_agent.sh

# 4. Access AutoBot
# Frontend: http://localhost:5173
# Backend API: http://localhost:8001
# API Documentation: http://localhost:8001/docs
```

--------------------------------

### Development Environment Setup

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/guides/CONFIGURATION_GUIDE.md

Example of a .env file for a typical development setup, specifying ports and hosts for backend, frontend, Ollama, and Redis.

```bash
# .env file for development
AUTOBOT_BACKEND_PORT=8001
AUTOBOT_FRONTEND_PORT=5173
AUTOBOT_OLLAMA_HOST=127.0.0.2
AUTOBOT_REDIS_HOST=127.0.0.7
```

--------------------------------

### Access the Setup Wizard

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/INSTALL.md

Navigate to the server IP in a web browser to initiate the configuration wizard after installation.

```text
https://<server-ip>
```

--------------------------------

### Install LibreOffice Flatpak from Flathub

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/data/file_manager_root/the_beginners_handbook.html

Example command to install the LibreOffice Flatpak application from the Flathub repository.

```bash
flatpak install flathub org.libreoffice.LibreOffice
```

--------------------------------

### Setup Local Development Environment

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/deployment/comprehensive_deployment_guide.md

Initialize the virtual environment and install necessary Python and Node.js dependencies.

```bash
# Create development environment
git clone https://github.com/your-org/autobot.git
cd autobot

# Create Python virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install Python dependencies
pip install -r requirements.txt

# Install Node.js dependencies
cd autobot-vue
npm install
cd ..
```

--------------------------------

### Install Dependencies and Run Development Server

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-backend/README.md

Installs project dependencies and starts the FastAPI development server. Ensure you are in the project root directory.

```bash
pip install -r requirements.txt
uvicorn main:app --reload --port 8001
```

--------------------------------

### Quick Start Deployment

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/DEVELOPER_SETUP.md

Commands to clone the repository and initiate either a bare-metal installation or a Docker-based development environment.

```bash
# 1. Clone repository
git clone https://github.com/your-org/AutoBot.git
cd AutoBot

# 2a. Bare-metal install (recommended for production fleet)
sudo ./install.sh
# Then complete configuration via the Setup Wizard at https://<server-ip>

# 2b. Docker install (recommended for development)
docker compose up -d --build
# Optional profiles: --profile ollama, --profile monitoring

# 3. Access development interface
# SLM Orchestration: https://<slm-manager-ip>/orchestration
# User Frontend: https://<frontend-ip>
# Backend API: https://<backend-ip>:8443/docs
# VNC Desktop: http://127.0.0.1:6080
```

--------------------------------

### Install OpenVINO and Dependencies

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/research/INTEL_NPU_WINDOWS_DEPLOYMENT_ANALYSIS.md

Setup of the virtual environment and installation of required AI/ML packages on Windows.

```powershell
# Create virtual environment
python -m venv C:\AutoBot\npu-env
C:\AutoBot\npu-env\Scripts\activate

# Install packages
pip install openvino==2025.2 openvino-tokenizers==2025.2 openvino-genai==2025.2
pip install nncf==2.14.1 onnx==1.17.0 optimum-intel==1.22.0
pip install fastapi uvicorn aiohttp redis
```

--------------------------------

### Start Services (Docker)

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/scripts/README.md

Start services managed by Docker Compose. Ensure Docker is installed and configured.

```bash
docker compose up -d
```

--------------------------------

### Initialize Environment Variables

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/architecture/Docker_Architecture_Documentation.md

Copy example environment files to their active locations before starting the services.

```bash
cp docker/env/common.env.example docker/env/common.env
cp docker/env/redis.env.example docker/env/redis.env
cp docker/env/agents.env.example docker/env/agents.env
```

--------------------------------

### Docker Compose Setup Phases

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/DEVELOPER_SETUP.md

This outlines the steps performed by Docker Compose during setup, including building containers and starting services. Optional profiles for Ollama and monitoring are mentioned.

```text
- Builds backend, frontend, and worker containers
- Starts Redis, Nginx, and supporting services
- Optional: Ollama container (--profile ollama)
- Optional: Prometheus + Grafana (--profile monitoring)
- Health checks run automatically via Docker health probes

Total Docker setup time: ~10 minutes (depending on build cache)
```

--------------------------------

### Example service management tasks

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/nssm/README.txt

Common tasks for installing, configuring, and querying services.

```shell
nssm install UT2004 c:\games\ut2004\system\ucc.exe server
```

```shell
nssm set UT2004 ObjectName games password
```

```shell
nssm set UT2004 AppStdout c:\games\ut2004\service.log
```

```shell
nssm set UT2004 AppAffinity 0
```

```shell
nssm remove UT2004 confirm
```

```shell
nssm get "Background Intelligent Transfer Service" Name
```

--------------------------------

### Development Environment .env Configuration

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/configuration/VNC_PORT_CONFIGURATION.md

Example .env file for a development setup, defining default VNC ports and API URLs.

```bash
# .env file for development
AUTOBOT_VNC_DISPLAY_PORT=5900
AUTOBOT_VNC_CONTAINER_PORT=5901
AUTOBOT_PLAYWRIGHT_VNC_URL=http://localhost:6080/vnc.html
AUTOBOT_PLAYWRIGHT_API_URL=http://localhost:3000
```

--------------------------------

### Install and Verify Ollama Service

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/guides/chat-ollama-configuration.md

These bash commands guide you through installing Ollama, starting its service, pulling a model, and verifying the installation by checking the API tags. Ensure you have `curl` and `python3` installed.

```bash
# 1. Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh

# 2. Start the service
sudo systemctl enable --now ollama

# 3. Pull a model
ollama pull qwen3.5:9b

# 4. Verify
curl -s http://127.0.0.1:11434/api/tags | python3 -m json.tool
```

--------------------------------

### Standard AutoBot Installation Commands

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-backend/resources/prompts/chat/installation_help.md

Use these commands for the initial setup of AutoBot on a Debian/Ubuntu host. The interactive install guides through the process, while the unattended option is for automation.

```bash
sudo ./install.sh
```

```bash
sudo ./install.sh --unattended
```

```bash
sudo ./install.sh --reinstall
```

--------------------------------

### Configure settings

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/mcp/tools/mcp-autobot-tracker/PRODUCTION_DEPLOYMENT.md

Initializes the configuration file from the provided example.

```bash
cp config.example.json config.json
# Edit config.json with your settings
```

--------------------------------

### Example Playbook

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-slm-backend/ansible/roles/distributed_setup/README.md

A sample playbook implementation for the distributed_setup role.

```yaml
- hosts: slm_server
  become: yes
  roles:
    - role: distributed_setup
      vars:
        coordinator_host: "172.16.168.19"
        health_check_interval: 30
        backup_schedule: "0 3 * * *"
```

--------------------------------

### Start Redis Service Request Example

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/api/REDIS_SERVICE_MANAGEMENT_API.md

Example of how to send a POST request to start the Redis service. Ensure you replace `YOUR_JWT_TOKEN` with a valid token.

```bash
curl -X POST \
  https://<backend-ip>:8443/api/services/redis/start \
  -H "Authorization: Bearer YOUR_JWT_TOKEN"
```

--------------------------------

### First-Time Setup Workflow

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-slm-backend/ansible/QUICK_START.md

A four-step workflow for initial setup, including provisioning, code syncing, service startup, and verification.

```bash
# Step 1: Provision host
ansible-playbook ansible/playbooks/provision_host.yml -e 'target_host=autobot-frontend'

# Step 2: Sync code
./scripts/utilities/sync-to-vm.sh frontend

# Step 3: Start services
ansible-playbook ansible/playbooks/manage_services.yml -e 'target_host=autobot-frontend action=start'

# Step 4: Verify
ansible-playbook ansible/playbooks/health-check.yml -e 'target_host=autobot-frontend'
```

--------------------------------

### Configure Development Environment

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/deployment/comprehensive_deployment_guide.md

Copy the example configuration file and prepare it for local development.

```bash
# Copy example configuration
cp config/config.example.yaml config/config.yaml

# Edit configuration for development
nano config/config.yaml
```

--------------------------------

### Repository Setup

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/DEVELOPER_SETUP.md

Initial steps to clone the repository and verify the directory structure.

```bash
# Clone the repository
git clone https://github.com/your-org/AutoBot.git
cd AutoBot

# Verify you're in the right location
ls -la
# You should see: install.sh, docker-compose.yml, scripts/, docs/, etc.
```

--------------------------------

### Create Windows Installer

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/BUILDING.md

Invoke the Inno Setup compiler to generate the final installer executable.

```powershell
# Build installer with Inno Setup
& "C:\Program Files (x86)\Inno Setup 6\ISCC.exe" installer\installer.iss /O"installer\output"
```

--------------------------------

### Setup Specific Components

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/scripts/README.md

Execute the setup script to configure individual components like knowledge base, Docker, or agent environment.

```bash
./setup.sh knowledge
```

```bash
./setup.sh docker
```

```bash
./setup.sh agent
```

--------------------------------

### Get Agent Terminal Session Example

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/api/AGENT_TERMINAL_API.md

Example cURL command to retrieve details for a specific session ID.

```bash
curl https://<backend-ip>:8443/api/agent-terminal/sessions/550e8400-e29b-41d4-a716-446655440000
```

--------------------------------

### Complete Initial Setup

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/scripts/README.md

Run the main setup script to configure all components of the AutoBot system.

```bash
./setup.sh
```

--------------------------------

### Install SLM Server Dependencies

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-slm-backend/QUICK_REFERENCE.md

Install necessary Python packages and run database migrations before starting the SLM server.

```bash
cd slm-server
pip install paramiko>=3.0.0
python migrations/add_events_certificates_updates_tables.py
python main.py
```

--------------------------------

### Build AutoBot NPU Worker Installer

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/PACKAGE_INFO.txt

Use this PowerShell script to build the professional installer package for the AutoBot NPU Worker. It automates dependency installation, executable creation with PyInstaller, and installer generation with Inno Setup.

```powershell
.\build.ps1
```

```powershell
.\build.ps1 -Clean
```

```powershell
.\build.ps1 -SkipDependencies
```

```powershell
.\build.ps1 -SkipPyInstaller
```

```powershell
.\build.ps1 -SkipInnoSetup
```

```powershell
.\build.ps1 -OutputDir "C:\Builds"
```

--------------------------------

### Run the Installer

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/README.md

Execute the installation script for system configuration and service deployment.

```bash
sudo ./install.sh              # Interactive install
sudo ./install.sh --unattended # Unattended (CI/automation)
```

--------------------------------

### Install Node.js 20.x LTS on Ubuntu

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/user-guide/01-installation.md

Installs Node.js version 20.x LTS using NodeSource repository setup script.

```bash
# Install Node.js 20.x LTS
curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejs
```

--------------------------------

### GET /api/entities/extract/health Response Example

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/planning/issue-55-phase2-completion-summary.md

Example JSON response for the service health check endpoint. Indicates the status of various components.

```json
{
  "status": "healthy",
  "components": {
    "entity_extractor": "healthy",
    "knowledge_extraction_agent": "healthy",
    "memory_graph": "healthy"
  },
  "timestamp": "2025-01-15T10:30:00Z"
}
```

--------------------------------

### PowerShell Installation Script

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/DEPLOYMENT_SUMMARY.md

The main installation script for the AutoBot NPU Worker. This script handles setup, dependency installation, service creation, and initial configuration. It requires administrator privileges to run.

```powershell
# scripts/install.ps1 - 300+ lines - Installation
```

--------------------------------

### Migration Examples

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/architecture/dependency_injection.md

Examples showing the transition from direct instantiation to dependency injection patterns.

```python
# Before
from src.orchestrator import Orchestrator
orchestrator = Orchestrator()  # Uses global config internally
```

```python
# After (Option 1 - Backward Compatible)
from src.orchestrator import Orchestrator
orchestrator = Orchestrator()  # Still works exactly the same
```

```python
# After (Option 2 - Explicit Dependency Injection)
from src.orchestrator import Orchestrator
from src.config import global_config_manager

orchestrator = Orchestrator(config_manager=global_config_manager)
```

```python
# After (Option 3 - FastAPI Endpoints)
from backend.dependencies import OrchestratorDep

async def my_endpoint(orchestrator: Orchestrator = OrchestratorDep):
    # Use orchestrator with all dependencies injected
    pass
```

--------------------------------

### Start Services (CLI Wrapper)

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/scripts/README.md

Initiate services using the CLI wrapper script. This is a recommended method for managing services.

```bash
scripts/start-services.sh start
```

--------------------------------

### Install PostgreSQL on SLM Server

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/archives/plans/2026-02-05-slm-user-management-implementation.md

Installs PostgreSQL, its contrib package, and development headers on the SLM server. Enables and starts the PostgreSQL service.

```bash
sudo apt update
sudo apt install -y postgresql postgresql-contrib python3-dev libpq-dev
sudo systemctl enable postgresql
sudo systemctl start postgresql
```

--------------------------------

### Installation Commands

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/DEPLOYMENT_SUMMARY.md

Steps to extract and run the installer.

```powershell
# Extract to C:\AutoBot\NPU\
```

```powershell
cd C:\AutoBot\NPU
.\scripts\install.ps1
```

--------------------------------

### Start Browser VNC Services

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/infrastructure/BROWSER_VNC_SETUP.md

Start the VNC server, websockify, and Playwright services on the Browser VM. This command is used after stopping services or during the initial setup.

```bash
ssh autobot@<browser-ip> 'sudo systemctl start browser-vnc browser-vnc-websockify browser-playwright'
```

--------------------------------

### Repository Configuration Examples

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/data/file_manager_root/the_beginners_handbook.html

Example lines for configuring free and proprietary package repositories in sources.list.

```text
deb http://deb.debian.org/debian/ bookworm main
```

```text
deb http://deb.debian.org/debian/ bookworm main contrib non-free non-free-firmware
```

--------------------------------

### Deploy Application

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/deployment/comprehensive_deployment_guide.md

Steps to clone the repository, set up the Python environment, and build the frontend for production.

```bash
# Clone application
git clone https://github.com/your-org/autobot.git /opt/autobot
cd /opt/autobot

# Set up Python environment
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# Build frontend
cd autobot-vue
npm ci --production
npm run build
cd ..

# Set up production configuration
cp config/config.production.yaml config/config.yaml
```

--------------------------------

### GitHub Actions: Install Core and Optional Voice Dependencies

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/guides/VOICE_INTERFACE_SETUP.md

GitHub Actions workflow snippet to install core Python dependencies and optionally install voice dependencies, allowing the workflow to continue if voice setup fails.

```yaml
# In your GitHub workflow
- name: Install core dependencies
  run: pip install -r requirements.txt

# Optional voice setup (may fail in CI)
- name: Install voice dependencies (optional)
  run: pip install -r requirements-voice.txt || echo "Voice dependencies skipped"
  continue-on-error: true
```

--------------------------------

### Install Intel OpenVINO Toolkit

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/user-guide/01-installation.md

Installs the OpenVINO toolkit for Intel NPUs. This involves downloading the package, extracting it, moving it to the opt directory, and sourcing the setup script.

```bash
# Download and install OpenVINO toolkit
wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2024.0/linux/l_openvino_toolkit_ubuntu20_2024.0.0.14509.34caeefd078_x86_64.tgz
tar -xzf l_openvino_toolkit_ubuntu20_2024.0.0.14509.34caeefd078_x86_64.tgz
sudo mv l_openvino_toolkit_ubuntu20_2024.0.0.14509.34caeefd078 /opt/intel/openvino_2024
echo 'source /opt/intel/openvino_2024/setupvars.sh' >> ~/.bashrc
```

--------------------------------

### Provision All Hosts

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-slm-backend/ansible/ROLE_STRUCTURE_README.md

Use this command to perform the initial setup of all hosts in the infrastructure.

```bash
ansible-playbook playbooks/provision_host.yml
```

--------------------------------

### Setup with Deployment Options

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/scripts/README.md

Configure the setup script with specific deployment options such as native VM or Docker. The `--force` option can be used to re-run setup.

```bash
./setup.sh initial --native-vm
```

```bash
./setup.sh initial --docker
```

```bash
./setup.sh knowledge --force
```

--------------------------------

### Initialize Configuration Library

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/archives/plans/2026-01-29-issue-694-config-consolidation.md

Commands to create the library directory and set permissions.

```bash
mkdir -p scripts/lib
# Write the file (done via Write tool above)
chmod +x scripts/lib/ssot-config.sh
```

--------------------------------

### Retrieve NPU pool statistics

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/archives/plans/2026-02-05-npu-worker-pool-design.md

Example JSON response for the GET /api/npu/pool/stats endpoint.

```json
{
  "total_workers": 2,
  "healthy_workers": 2,
  "total_tasks_processed": 1523,
  "active_tasks": 12,
  "avg_task_duration_ms": 245.3,
  "success_rate": 0.997
}
```

--------------------------------

### Configure Environment and Run Migrations

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/guides/PRODUCTION_READINESS_CHECKLIST.md

Steps to set environment variables, run database migrations, and start the production service.

```bash
# Environment setup
export AUTOBOT_ENV=production
export AUTOBOT_DATABASE_URL=postgresql://...
export AUTOBOT_REDIS_URL=redis://...
export AUTOBOT_SECRET_KEY=...

# Database migration
python manage.py migrate
python manage.py collectstatic

# Service startup
./run_production.sh
```

--------------------------------

### Configuration Examples

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/04-configuration.md

YAML configuration templates for minimal, production, and development environments.

```yaml
# Minimal config for local development
backend:
  server_port: 8001

llm_config:
  default_llm: "ollama_tinyllama"
  ollama:
    host: "http://localhost:11434"

memory:
  chromadb:
    enabled: true
```

```yaml
# Production configuration
backend:
  server_host: "0.0.0.0"
  server_port: 8001
  cors_origins:
    - "https://autobot.company.com"

llm_config:
  default_llm: "openai_gpt4"
  openai:
    api_key: ""  # Set via OPENAI_API_KEY env var

memory:
  redis:
    enabled: true
    host: "redis.internal"
    port: 6379
  chromadb:
    enabled: true

security:
  enable_encryption: true
  audit_log_file: "/var/log/autobot/audit.log"

logging:
  log_level: "warning"
  log_file_path: "/var/log/autobot/autobot.log"
```

```yaml
# Development configuration with debugging
backend:
  server_port: 8001

llm_config:
  default_llm: "ollama_phi2"
  task_llm_settings:
    temperature: 0.1  # More consistent for testing

ui:
  developer_mode: true

developer:
  enabled: true
  enhanced_errors: true
  debug_logging: true

logging:
  log_level: "debug"

message_display:
  show_thoughts: true
  show_json: true
  show_debug: true
```

--------------------------------

### Get System Prompts Response

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/03-api-reference.md

Example response containing all system prompts and default configurations.

```json
{
  "prompts": [
    {
      "id": "prompt_id",
      "name": "prompt_name",
      "type": "prompt_type",
      "path": "relative/path",
      "content": "Prompt content..."
    }
  ],
  "defaults": {/* default prompts object */}
}
```

--------------------------------

### Get LLM Models Response

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/03-api-reference.md

Example response containing the list of available LLM models.

```json
{
  "models": [/* model array */],
  "total_count": 10
}
```

--------------------------------

### Manual Installation Steps

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/mcp/tools/mcp-autobot-tracker/README.md

Manually install dependencies, build the project, and copy the configuration file. Ensure Node.js 18+ is installed.

```bash
# Install dependencies
npm install

# Build the project
npm run build

# Create configuration
cp config.example.json config.json
```

--------------------------------

### Setup Production Database

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/deployment/comprehensive_deployment_guide.md

Commands to initialize the PostgreSQL database and run production migrations.

```bash
# PostgreSQL setup
sudo -u postgres createuser autobot_user
sudo -u postgres createdb autobot_prod -O autobot_user
sudo -u postgres psql -c "ALTER USER autobot_user PASSWORD 'secure_password';"

# Run database migrations
export AUTOBOT_DB_PASSWORD="secure_password"
python scripts/migrate_database.py --production
```

--------------------------------

### Prepare Build Environment

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/BUILDING.md

Clone the repository and initialize a clean build environment.

```powershell
# Clone repository (if not already done)
git clone https://github.com/autobot/autobot.git
cd autobot/deployment/windows-npu-worker

# Create clean build environment
.\installer\build.ps1 -Clean
```

--------------------------------

### Get Tool Installation Command

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/guides/intelligent_agent_system.md

Retrieves the appropriate command to install a given tool based on the detected operating system and its package manager. Returns None if the tool or OS/package manager combination is not supported.

```python
    async def get_install_command(self, tool_name: str) -> Optional[str]:
        """Get the command to install a tool on this OS"""
        os_info = await self.detect_system()

        # Tool installation mappings
        install_commands = {
            OSType.LINUX: {
                "apt": {
                    "nmap": "apt install -y nmap",
                    "arp-scan": "apt install -y arp-scan",
                    "netstat": "apt install -y net-tools",
                    "ss": "apt install -y iproute2",
                    "htop": "apt install -y htop",
                    "curl": "apt install -y curl",
                    "wget": "apt install -y wget",
                    "git": "apt install -y git",
                    "python3": "apt install -y python3",
                    "pip": "apt install -y python3-pip"
                },
                "yum": {
                    "nmap": "yum install -y nmap",
                    "arp-scan": "yum install -y arp-scan",
                    "netstat": "yum install -y net-tools",
                    "htop": "yum install -y htop",
                    "curl": "yum install -y curl",
                    "wget": "yum install -y wget"
                },
                "dnf": {
                    "nmap": "dnf install -y nmap",
                    "arp-scan": "dnf install -y arp-scan",
                    "netstat": "dnf install -y net-tools",
                    "htop": "dnf install -y htop"
                },
                "pacman": {
                    "nmap": "pacman -S --noconfirm nmap",
                    "arp-scan": "pacman -S --noconfirm arp-scan",
                    "netstat": "pacman -S --noconfirm net-tools",
                    "htop": "pacman -S --noconfirm htop"
                }
            },
            OSType.MACOS: {
                "brew": {
                    "nmap": "brew install nmap",
                    "arp-scan": "brew install arp-scan",
                    "htop": "brew install htop",
                    "curl": "brew install curl",
                    "wget": "brew install wget"
                }
            },
            OSType.WINDOWS: {
                "winget": {
                    "nmap": "winget install nmap",
                    "curl": "winget install curl",
                    "wget": "winget install wget",
                    "git": "winget install git"
                }
            }
        }

        if os_info.os_type in install_commands:
            pkg_mgr = os_info.package_manager
            if pkg_mgr in install_commands[os_info.os_type]:
                return install_commands[os_info.os_type][pkg_mgr].get(tool_name)

        return None
```

--------------------------------

### Manually Install Browser VNC Services

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/infrastructure/BROWSER_VNC_SETUP.md

Use these commands for manual installation of Browser VM VNC services on the target machine. This involves copying service files, enabling them in systemd, and starting the services.

```bash
scp scripts/infrastructure/browser-*.service autobot@<browser-ip>:/tmp/
```

```bash
ssh autobot@<browser-ip>
sudo mv /tmp/browser-*.service /etc/systemd/system/
sudo chmod 644 /etc/systemd/system/browser-*.service
sudo systemctl daemon-reload
sudo systemctl enable browser-vnc browser-vnc-websockify browser-playwright
sudo systemctl start browser-vnc browser-vnc-websockify browser-playwright
```

--------------------------------

### Run Demonstration Script

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/architecture/dependency_injection.md

Execute the provided demo script to validate dependency injection components.

```bash
# Run demonstration
python test_dependency_injection_demo.py
```

--------------------------------

### Utilize Pytest Fixtures

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/testing/TEST_UTILITIES_MIGRATION_GUIDE.md

Example of using pre-configured pytest fixtures to handle test setup automatically.

```python
def test_with_fixtures(mock_config, mock_security, temp_file, test_client):
    """All setup handled by fixtures."""
    # mock_config has standard test configuration
    # mock_security is pre-configured
    # temp_file is created and auto-cleaned
    # test_client is ready for API testing
```

--------------------------------

### Start Backend Coordinator

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/architecture/DISTRIBUTED_6VM_ARCHITECTURE.md

Run this bash script to initiate the main backend API coordinator service.

```bash
bash scripts/distributed/start-coordinator.sh
```

--------------------------------

### Install Prerequisites

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-backend/code_analysis/README.md

Commands to set up Redis and required Python dependencies.

```bash
# Install Redis (required for caching)
sudo apt install redis-server
# or
docker run -d -p 6379:6379 redis:alpine

# Install Python dependencies
pip install redis aioredis numpy scikit-learn chromadb
```

--------------------------------

### Run production installation script

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/mcp/tools/mcp-autobot-tracker/PRODUCTION_DEPLOYMENT.md

Executes the automated production setup script within the tracker directory.

```bash
# Navigate to the MCP tracker directory
cd mcp-autobot-tracker

# Run the production installation script
./production-install.sh
```

--------------------------------

### Automated Software Installation Workflow

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/features/MULTIMODAL_AI_INTEGRATION.md

Demonstrates a complete multi-modal automation workflow for software installation, integrating voice command processing, web navigation, screenshot analysis, and download execution.

```python
async def automated_software_install_demo():
    """
    Demonstrate complete multi-modal automation:
    1. Voice command: "Install the latest version of VS Code"
    2. Screenshot analysis: Find download page elements
    3. Text processing: Extract installation instructions
    """    
    # Step 1: Process voice command
    voice_input = await capture_voice_command()
    voice_result = await multimodal_client.process({
        "inputs": {"audio": voice_input},
        "processing_options": {"extract_software_name": True}
    })
    
    software_name = voice_result["audio_analysis"]["extracted_entities"]["software"]
    # Result: "Visual Studio Code"
    
    # Step 2: Navigate to download page
    await browser_service.navigate(f"https://{software_name}.com/download")
    
    # Step 3: Capture and analyze screenshot
    screenshot = await browser_service.capture_screenshot()
    vision_result = await multimodal_client.process({
        "inputs": {"image": screenshot},
        "processing_options": {"detect_download_buttons": True}
    })
    
    download_button = vision_result["image_analysis"]["detected_elements"][0]
    # Result: Download button coordinates and properties
    
    # Step 4: Execute download
    await browser_service.click(download_button["coordinates"])
    
    # Step 5: Monitor download progress with multi-modal feedback
    while True:
        # Visual monitoring
        current_screen = await browser_service.capture_screenshot()
        progress_analysis = await vision_processor.detect_progress_indicators(
            current_screen
        )
        
        if progress_analysis["download_complete"]:
            break
            
        await asyncio.sleep(2)
    
    # Step 6: Generate completion report
    completion_report = await multimodal_client.generate_report({
        "task": "software_installation",
        "software": software_name,
        "success": True,
        "duration": "2 minutes 15 seconds",
        "confidence": 0.94
    })
    
    return completion_report
```

--------------------------------

### Commit .env.example Files

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/archives/plans/2026-02-05-slm-user-management-implementation.md

Stages and commits the newly created .env.example files for both SLM and the server configuration.

```bash
git add .env.example slm-server/.env.example
git commit -m "docs(config): Add PostgreSQL configuration for dual databases (#576)"
```

--------------------------------

### Get Developer Configuration Response

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/developer/03-api-reference.md

Example response showing the current state of developer mode settings.

```json
{
  "enabled": false,
  "enhanced_errors": true,
  "endpoint_suggestions": true,
  "debug_logging": false
}
```

--------------------------------

### Start Development Services

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/deployment/comprehensive_deployment_guide.md

Commands to initialize the backend, frontend, and local LLM services for development.

```bash
# Terminal 1: Start backend with auto-reload
source venv/bin/activate
python main.py --dev

# Terminal 2: Start frontend development server
cd autobot-vue
npm run dev

# Terminal 3: Start Ollama (if using local LLM)
ollama serve
```

--------------------------------

### Browse Repository Skills

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/archives/plans/2026-02-18-skills-system.md

GET endpoint to list available skills in a repository without performing an installation.

```python
@router.get("/{repo_id}/browse", summary="Browse available skills in a repo")
async def browse_repo(repo_id: str) -> Dict[str, Any]:
    """List skills available in a repo without installing them."""
    from sqlalchemy import select
    async with get_skills_engine().connect() as conn:
        row = await conn.execute(
            select(SkillRepo).where(SkillRepo.id == repo_id)
        )
        repo = row.fetchone()
    if not repo:
        raise HTTPException(404, f"Repo {repo_id} not found")
    packages = await _sync_packages(repo)
    return {"packages": [p["name"] for p in packages], "count": len(packages)}
```

--------------------------------

### Initialize Alternative VNC Session

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/testing/TEST_RESULTS_SUMMARY.md

Manual steps to start a VNC server and XFCE desktop environment as a fallback.

```bash
vncserver :1
export DISPLAY=:1
startxfce4 &
```

--------------------------------

### Manage Windows Service Lifecycle

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/research/INTEL_NPU_WINDOWS_DEPLOYMENT_ANALYSIS.md

Commands to install, start, stop, and check the status of the Windows service.

```powershell
# Install required package
pip install pywin32

# Install service
python service.py install

# Start service
python service.py start

# Check status
python service.py status

# Stop service
python service.py stop
```

--------------------------------

### Install and Deploy AutoBot

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/GETTING_STARTED_COMPLETE.md

Commands to clone the repository and deploy the backend using Ansible or the local setup script.

```bash
# 1. Clone repository
git clone <repository-url>
cd AutoBot

# 2. Deploy with Ansible (recommended for production)
cd autobot-slm-backend/ansible
ansible-playbook playbooks/deploy-full.yml

# OR: Run setup script (development/local)
./run_agent.sh

# 3. Access AutoBot
# Production frontend: https://<frontend-ip> (Frontend VM)
# Backend API: https://<backend-ip>:8443
# SLM Admin: https://<slm-manager-ip>
```

--------------------------------

### Troubleshoot Installer Build Errors

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-npu-worker/resources/windows-npu-worker/BUILDING.md

Verify Inno Setup compiler location and check for missing build artifacts.

```powershell
Test-Path "C:\Program Files (x86)\Inno Setup 6\ISCC.exe"
```

```powershell
Test-Path dist\AutoBotNPUWorker\AutoBotNPUWorker.exe
```

```powershell
.\installer\build.ps1 -Clean
```

--------------------------------

### Separate Setup for Benchmarking

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/docs/testing/PERFORMANCE_BENCHMARKS.md

Demonstrates separating setup code from the actual operation being benchmarked. Ensure setup is done before timing begins.

```python
def test_good():
    data = load_large_file()  # Setup before

    def benchmark():
        process(data)  # Only time the operation
```

--------------------------------

### Run Server with CLI Arguments

Source: https://github.com/mrveiss/autobot-ai/blob/Dev_new_gui/autobot-infrastructure/shared/mcp/tools/context7/README.md

Examples of running the server with specific transport and authentication flags.

```bash
bun run dist/index.js --transport http --port 8080
```

```bash
bun run dist/index.js --transport stdio --api-key YOUR_API_KEY
```