Catalog PyPI
PACKAGE EXPLORERView in registry

agentic-test-framework

PyPI

AI-powered browser testing framework using natural language and OpenAI

aiautomationbrowser-testingopenaiplaywrighttesting
Versions collected1
Direct dependencies7From release 0.1.3
Last observed20 Oct, 22:23 UTC

README

Version 0.1.3 documentation

Agentic Test Framework

An AI-powered browser testing framework that accepts natural language test descriptions and executes them using Playwright.

Quick Start

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

# Install the package
pip install agentic-test-framework

# Install Playwright browsers
playwright install

# Set up environment
cp .env.example .env
# Edit .env and add your OpenAI API key

# Run an example test
python -m agentic_test_framework "Go to example.com and take a screenshot"

Features

  • 🤖 Natural Language Tests: Write tests in plain English
  • 🌐 Browser Automation: Powered by Playwright (Chrome, Firefox, Safari)
  • 🧠 AI-Driven: Uses OpenAI to interpret test scenarios
  • 📸 Auto Screenshots: Captures screenshots on demand or for every step
  • 📊 Dual Reporting: Custom HTML reports + Playwright trace viewer
  • 🎬 Time-Travel Debugging: Playwright traces with DOM snapshots, network logs, console output
  • 🎥 Video Recording: Automatic video capture of test execution
  • ✅ Assertions: Verify conditions and extract data
  • 🔄 Smart Retries: Handles flaky elements automatically
  • 📝 ATC Format: Structured test files with YAML-like syntax

Example Tests

Command Line

# Simple navigation
agentic-test "Go to google.com and search for 'playwright testing'"

# Multi-step workflow
agentic-test "Navigate to github.com, click Sign in, type 'testuser' in username field"

# Validation
agentic-test "Go to example.com, verify the page title contains 'Example', take screenshot"

ATC File Format

Create structured test files with .atc extension:

# Login Test Suite

@config browser=chromium
@config headless=false

## Scenario: Successful Login
@tag smoke
@tag login

Go to example.com/login
Type 'testuser' into username field
Type 'password123' into password field
Click login button
Verify page contains 'Welcome'
Take a screenshot

Quick Start: Generate ATC Templates

# Create basic template
agentic-test --create tests/my_test.atc

# Create from predefined templates
agentic-test --create tests/login.atc --template login
agentic-test --create tests/shop.atc --template ecommerce
agentic-test --create tests/api.atc --template api

Available templates:

  • basic - Simple test structure
  • login - Login/authentication flows
  • ecommerce - Shopping and checkout flows
  • api - API/integration tests

Run ATC files:

# Run all scenarios
agentic-test tests/login.atc

# Run specific scenario
agentic-test tests/login.atc --scenario "Successful Login"

# Run by tag
agentic-test tests/login.atc --tag smoke

See docs/ATC_FORMAT.md for complete format specification.

Architecture

Natural Language → OpenAI Parser → Action Objects → Playwright Executor → Results

See .github/copilot-instructions.md for detailed architecture documentation.

Project Structure

agentic-test-framework/
├── agentic_test_framework/
│   ├── actions/          # Action type definitions
│   ├── parser/           # OpenAI integration
│   ├── executor/         # Playwright execution engine
│   ├── runner/           # Test orchestration
│   └── reporter/         # HTML report generation
├── config/               # Configuration files
├── examples/             # Example test scenarios
├── docs/                 # Documentation
└── tests/                # Framework tests

HTML Reports

Every test automatically generates a beautiful HTML report with:

  • ✅ Pass/fail status for each step
  • 📸 Embedded screenshots
  • 📊 Extracted data
  • ⏱️ Execution timing
  • 🎨 Color-coded results

Reports are saved to test-results/report_YYYYMMDD_HHMMSS.html

See docs/HTML_REPORTS.md for details.

Development

Running Unit Tests

The framework includes a comprehensive test suite with pytest:

# Run all tests
pytest

# Run with verbose output
pytest -v

# Run with coverage report
pytest --cov=agentic_test_framework --cov-report=html

# Run specific test file
pytest tests/test_actions.py

# Open coverage report in browser
xdg-open htmlcov/index.html  # Linux
open htmlcov/index.html       # macOS

See tests/README.md for detailed testing documentation.

License

MIT

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
0.1.330 Jan 20267

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Repository

PENDING
drfatihtekin/agentic-test-framework

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 22:23 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:58c72d77edaeacce9fe23e71847ada6ec6d1a544264dc11ec8b4aa726b32ea31