AI generated code by Claude Sonnet, Kimi K2 0905, GLM-4.5 is not good enough to simultaneously maintain structure and implement features in complex code without doing insane things like grossly violating each SOLID principle. If you impose too much structure upon them, they fall apart as they don't truly understand the long range ramifications of their code too often. These assistants are best suited for generating highly testable snippets of code and pushing them to work in a large codebase pushes their capabilities too far, too often.