//! Reusable numerical-gradient checking for xtrain (Phase T3+).
//!
//! Given a scalar loss `f(x)` and an analytic gradient `g`, verify that `g`
//! matches the central finite-difference estimate
//! `(f(x+ε·eᵢ) - f(x-ε·eᵢ)) / 2ε` for every element `i`, within a relative
//! tolerance. Later phases (T4 autograd) reuse this per-op: wrap each op's
//! forward as the loss, run its backward to get `g`, and `grad_check`.
//!
//! The harness is host-only and dtype-agnostic at this layer: it works on a
//! flat `&[f32]` parameter vector + shape and a closure. The closure is free to
//! push the data to the GPU and run kernels — that detail stays out of here.

pub mod finite_diff;

pub use finite_diff::{GradCheckConfig, GradCheckResult, ParamFn, grad_check};

// Tape-based autograd engine + differentiable ops (Phase T4). These call GPU
// kernels via xtrain-tensor, so they are gated behind `not(no_cuda)` (the
// per-crate convention); the grad_check harness above stays host-only.
#[cfg(not(no_cuda))]
pub mod ops;
#[cfg(not(no_cuda))]
pub mod tape;

#[cfg(not(no_cuda))]
pub use tape::Var;