Back to Open Source Python

CodeHawk

AI-powered pull request review pipeline

CodeHawk is an AI-powered pull request review pipeline that runs in CI. A two-phase architecture separates agent analysis from deterministic posting: Phase 1 reads the diff and writes findings.json; Phase 2 validates, scores with a penalty-based star rating, posts inline comments, and gates the build. It supports Azure DevOps and GitHub, fix verification on re-push, and developer controls for intentional code.

2-phase

review architecture

ADO + GH

VCS supported

0–5★

penalty scoring

Docker

CI-ready image

How it works

What's inside

01

Phase 1: an LLM agent reads the PR diff and writes structured findings

02

Phase 2: validates, scores, posts inline comments, and gates CI

03

Fix verification on re-push — fixed, dismissed, or still-present

04

Developer controls: # cr: intentional, .codereview.md, gate thresholds

05

Model-agnostic: o3, GPT-4, Claude, Gemini, and more

06

Per-run token cost tracking and a dry-run mode that never posts