What problem does it solve?
Ensures AI-performed QA activities generate consistent, evidence-backed E2E/API testing outputs and static review findings, each with traceable root-cause and followable lifecycle status.
Core Features & Use Cases
- E2E & API testing with evidence chains: Collects snapshots, screenshots, network request/response details, and console logs as required, then turns results into structured bug entries.
- Source-level root-cause tracing: Uses a semantic code search workflow (and falls back to direct file viewing) to connect observed failures to the actual implementation lines.
- Static code review with risk grading: Reviews the intended diff scope for safety, concurrency/resource safety, performance, data consistency, error handling, architectural boundaries, and documentation/test gaps, then merges and classifies conclusions.
Quick Start
Trigger a QA run by asking the AI to perform code review and E2E/API tests, then generate the report under docs/code-review with evidence and root-cause analysis.