> What about my proposed psychosis would make the tests go green when it implements something complex in one shot?

Nothing. That's why it's a psychosis. It has nothing to do with the reality of how language models generate words without mental reasoning.

The “something complex” is critical here - I mean specifically an implementation that requires an advanced and reasoned mental model to write. How does it oneshot those and pass comprehensive tests if it isn’t doing advanced reasoning?

Because it's a statistical model of the words used in similar problem domains.