autopr-core 0.5.1

AI-powered Pull Request Generator & Reviewer - Automate PR titles, descriptions, and code reviews

AutoPR — AI-powered Pull Request Generator & Reviewer

AutoPR automates the repetitive parts of pull requests: it writes concise PR titles & descriptions, validates CI/tests, runs deterministic static and lint checks, and provides an AI-assisted review summary.

Quickstart

1. Install

pip install autopr-core

2. Configure your API key

AutoPR requires your own OpenAI or Anthropic API key. Run the interactive setup:

autopr configure

This will prompt you to:

• Choose a provider (openai or anthropic)
• Enter your API key (stored locally in .env, never shared)

Or set environment variables manually:

# For OpenAI
export OPENAI_API_KEY="your-openai-api-key"
export AUTOPR_PROVIDER="openai"

# For Anthropic
export ANTHROPIC_API_KEY="your-anthropic-api-key"
export AUTOPR_PROVIDER="anthropic"

3. Use AutoPR

# Generate a PR title & description
autopr gen --diff "$(git diff)" --commits "feat: add helper"

# AI-assisted code review
autopr review --diff "$(git diff)"

# Run static analysis
autopr analyze --diff "$(git diff)" --summary

Command Cheat Sheet

Command	Description
autopr configure	Interactive setup — set your AI provider and API key
autopr gen	Generate PR title and description
autopr review	Perform AI-assisted code review
autopr analyze	Run static analysis on code diffs
autopr analyze-files	Batch-analyze files in a directory
autopr ci-parse	Parse CI/test logs
autopr coverage-compare	Compare coverage reports
autopr validate-issue	Check if changes align with an issue
autopr doctor	Check system health and configuration
autopr init	Initialize AutoPR config in your repo
autopr suggest-reviewers	Suggest reviewers based on git history

Features

• AI-Powered PR Generation — Titles, descriptions, and risk assessments
• AI Code Review — Senior-engineer-level review with actionable findings
• Static Analysis — Deterministic Python code analysis (security, complexity, style)
• CI/Test Parsing — Parse pytest, unittest, and GitHub Actions logs
• Coverage Comparison — Diff coverage reports before and after changes
• Multiple LLM Providers — OpenAI and Anthropic with robust error handling
• FastAPI Backend — REST API with /generate and /review endpoints
• CLI Tool — Full-featured command-line interface

API Server

Run the FastAPI server for REST API access:

uvicorn autopr.main:app --reload --port 8000

Visit http://127.0.0.1:8000/docs for interactive API docs.

Install from Source

git clone https://github.com/surenkotian/AutoPR.git
cd AutoPR
pip install -e .
autopr configure

License

MIT