Simple—it's not Turing complete. The whole premise is to eliminate recursive structure. Replacing them are measured folds and unfolds of data and codata respectively. These allow you to get as close to infinity as needed on both sides without going over (for some moderate syntactic and semantic penalties).
Within a language like the Calculus of Coinductive Constructions like Morte appears to implement it's not such a strange idea to have normalization.
So, no infinite loops means no Halting Problem means no completeness.
The upside is a larger set of easy-to-perform optimizations, much greater mathematical elegance. The downside is that you cannot directly write an interpreter for a complete language. Though you could write one which halts every N steps and requires user input to continue. In practice, that isn't the worst idea for a repl anyway.
Within a language like the Calculus of Coinductive Constructions like Morte appears to implement it's not such a strange idea to have normalization.
So, no infinite loops means no Halting Problem means no completeness.
The upside is a larger set of easy-to-perform optimizations, much greater mathematical elegance. The downside is that you cannot directly write an interpreter for a complete language. Though you could write one which halts every N steps and requires user input to continue. In practice, that isn't the worst idea for a repl anyway.