no, i believe it needs to be solved in finetuning. collectively, the OSS community should be pooling local LLM resources and providing a route to models that inately choose best practices as a "full stack" engineer would see them.

in your mind, you think a harness and prompt is sufficient framing to keep the LLM output to design goals. but no matter your context size, as it grows, anomolous gradients appear that try to normalize competing patterns of development.

the only real way is directly training out unwanted crosswise options.