I Built an Open-Source QA Agent Because AI Shouldn’t Grade Its Own Homework

说明与用途

MaruCheck 是一个独立的验证层，比较 AI 生成的代码与持久化的质量合同，检测语义漂移，评估风险，并回顾历史回归，确保产品符合原始需求。

问题

AI coding agents can generate both code and tests, risking semantic drift where the same misunderstanding propagates into passing tests that mask incorrect implementations.

结果

MaruCheck prevents semantic drift by enforcing a Quality Contract, performs risk‑based test selection, and recalls historical regressions, leading to more reliable AI‑generated code that truly meets product requirements.

工作流

• Define a Quality Contract for the feature
• Coding agent implements the feature
• MaruCheck scans the repo and analyzes the git diff
• Risk-based verification selects relevant tests
• MaruCheck runs tests and compares results to the contract
• If a semantic drift is detected, MaruCheck blocks the PR and reports the issue
• Developer fixes the implementation and re‑runs MaruCheck
• Repeat until all checks pass

证据

If the model misunderstands the requirement once, it can easily carry that same misunderstanding into the tests.

来源

MaruCheck verifies. If it finds something: BLOCKING ISSUE SUB-004 violated.

来源