test-generation-assistant

🧪 Test Generation Assistant

🎯 Overview

AI-assisted test generation and execution system that automates the complete testing workflow:

• Test Case Generation: Generate comprehensive test cases from JIRA tickets
• E2E Test Code Generation: Create executable E2E test code
• Test Execution: Run E2E tests and capture results
• PR Submission: Automatically create pull requests for generated test code
• JIRA Integration: Update JIRA tickets with test status and results

This system uses multiple specialized agents to handle each phase of the testing process, ensuring consistent and thorough test coverage for OpenShift components.

📋 Prerequisites

Before you can use this test generation system, you need to set up the following integrations:

1. Install Claude Code, Cursor, or Gemini

• Claude Code access: Follow Claude Code Install Instructions
• Cursor access: Download and install Cursor for an IDE-based experience with AI assistance
• Gemini access: Refer to Gemini documentation for AI assistance
• Important: Choose Claude Code for command-line interaction, Cursor for a full IDE experience, or Gemini for alternative AI assistance. All can be used to run the test generation system.

1.1 Install as Claude Plugin (Recommended for Teams) ⭐

ONE-COMMAND INSTALLATION - The simplest way to share with your team:

claude plugin marketplace add YOUR_USERNAME/test-generation-assistant

That's it! The plugin is now available in Claude Code with all agents and workflows.

What's included:

• ✅ All test generation agents
• ✅ Workflow orchestrator
• ✅ Configuration templates
• ✅ Automatic updates
• ✅ Team collaboration support

Complete Guide: PLUGIN_INSTALLATION.md

---

2. JIRA MCP Access

• Apply for jira-mcp-snowflake token: Refer to Jira-MCP-Snowflake-Token-Guide

• Config jira-mcp-snowflake mcp server:

  claude mcp add jira-mcp-snowflake https://jira-mcp-snowflake.mcp-playground-poc.devshift.net/sse --transport sse -H "X-Snowflake-Token: your_token_here"
  

3. DeepWiki MCP Connection

claude mcp add -s user -t http deepwiki https://mcp.deepwiki.com/mcp

4. Prepare Test Generation Rules

• Purpose: Configure rules to guide AI in generating realistic and executable test cases
• Location: config/rules/
• Content: Component-specific testing guidelines, validation criteria, and best practices

5. Configure GitHub CLI (gh)

• Purpose: Enable PR creation and GitHub repository operations
• Installation:

  # macOS
  brew install gh
  
  # Linux/Windows
  # Follow: https://cli.github.com/manual/installation
  

6. Environment Configuration

Purpose: Configure environment variables for GitHub, JIRA, and OpenShift access

Quick Setup:

# Copy example environment file
cp .env.example .env

# Edit with your credentials
nano .env

Required Variables:

• GITHUB_FORK_OWNER - Your GitHub username (for E2E test generation)
• JIRA_SERVER - JIRA server URL (default: https://issues.redhat.com)
• JIRA_TOKEN - Your JIRA authentication token

For E2E Testing:

• KUBECONFIG - Path to your OpenShift cluster kubeconfig
• TEST_PLATFORM - Target platform (AWS, Azure, GCP, etc.)

See: ENV_SETUP.md for detailed environment setup guide

7. Execution Method

CRITICAL: All agents must be executed by reading agent YAML configurations directly.

Execution Pattern:

1. Read CLAUDE.md (for Claude Code), GEMINI.md (for Gemini), or Cursor documentation (see Cursor Configuration in Prerequisites) for agent instructions
2. Read specific agent YAML config (e.g., config/agents/test_case_generation.yaml)
3. Execute each step manually using available tools
4. Verify each step before proceeding

🎛️ Workflow Orchestrator (PRIMARY ENTRY POINT)

MANDATORY: The workflow orchestrator is the PRIMARY entry point for ALL test generation requests.

CRITICAL: Before executing ANY user request, AI MUST:

1. Read config/agents/workflow_orchestrator.yaml FIRST
2. Let orchestrator identify workflow automatically
3. Execute agents in correct sequence

What is it?

A top-level agent that automatically:

• ✅ Parses user requests and identifies intent
• ✅ Matches requests to predefined workflows
• ✅ Validates prerequisites automatically
• ✅ Executes agents in correct sequence
• ✅ Handles REGENERATE mode
• ✅ Generates comprehensive execution reports

Configuration

Location: config/agents/workflow_orchestrator.yaml
Guide: config/agents/WORKFLOW_ORCHESTRATOR_GUIDE.md