Option for Native AD backend APIs to offer direct stability guarantees ?

Native AD backend APIs often provide better stability and stronger correctness guarantees than DI's layer around them.
eg: https://github.com/chalk-lab/Mooncake.jl/issues/992 - a frule!!/rrule!! inconsistency in nan_tangent_guard causes forward-mode to return NaNwhere reverse-mode returns 0.0. This kind of edge-case divergence between modes is invisible to DI, which wraps each mode independently.

Broadly the concerns are:

• Maintenance burden: each AD backend update can silently break DI's assumptions, requiring downstream fixes (eg https://github.com/JuliaDiff/DifferentiationInterface.jl/issues/986)
• Correctness: bugs like https://github.com/chalk-lab/Mooncake.jl/issues/992 may only surface after multiple layers of wrapping, making diagnosis harder.
• Performance: calling native API is almost always faster as we don't have the DI overhead. (eg https://github.com/JuliaDiff/DifferentiationInterface.jl/issues/854)

Is there a path toward DI where we can either :

• (a) call native backend APIs more directly where they exist, or
• (b) expose a "native-first" mode that bypasses the wrapper for backends that have the latest stable and correct API?

Start by reading the linked Mooncake.jl issue #992 and DifferentiationInterface.jl issues #986 and #854, then inspect how DI currently wraps backend APIs. Determine whether direct native calls or a native-first mode can preserve correctness and stability while reducing overhead. Done would require an agreed scope, supported backends, and validation criteria.