🤖 AI Summary
This study addresses the challenges of specification-code inconsistency and limited extensibility in AI-assisted software development by proposing a dual-layer engine architecture. The lower layer integrates graph theory with static analysis to perform deterministic verification, thereby preventing deviations from established specifications. The upper layer leverages a multi-agent system to collaboratively extend specifications. Furthermore, this work introduces a novel three-switch mechanism that enables eighteen distinct operational configurations, supporting a full spectrum of human-AI collaboration paradigms ranging from manual to fully unsupervised modes. By effectively balancing deterministic guarantees with the value of autonomous generation, the proposed framework ensures that code modifications remain traceable while facilitating the continuous evolution of specifications.
📝 Abstract
The Spec Growth Engine anchors AI-assisted software development in a graph of specifications that the code is coupled to. This paper describes its implementation, which serves two tasks and keeps them apart as two layers. The first layer prevents spec-code divergence: a deterministic engine validates the spec graph, compares it with the code's import graph, earns a node's verified status from recorded test evidence, and classifies every change by what it can break -- without calling a model. The second layer grows the spec with agents: an intent author, a planner and a coder, each played by its own model, extend the graph in rounds, and a deterministic rule decides after each round whether the run goes on. How much of the human's judgement is delegated is set by three independent switches -- a draft gate, a delegation for breaking changes, and the run mode -- which, with two ways of laying a project's floor, give eighteen ways to run a project. We describe each of them, the gates, requests and waivers through which agents and the human communicate, and the spectrum of operation from entirely manual work to an unsupervised run whose decisions the human reviews afterwards. Throughout, one claim holds the design together: an autonomous run is worth only as much as the deterministic instance that measures it.