#pragma once
#include <cstddef>
#include <cstdint>

// Bit-exact transcription of the soothe2 "twin" resonance filter 0x180535880
// (float sibling of the resonator 2nd-order detector core, NLS .sdk plugin).
//
// Pipeline per complex bin (all float32, op-order faithful to the disassembly):
//   z1 = conj(e^{i*theta})                 (rotor -> interleave, then 0x1800018b0 conj)
//   z2 = cplx_mul(z1, z1)                  (0x18000ad60 scalar body @0x18000ae00)
//   accA = A0; accA = fma(A1, z1, accA); accA = fma(A2, z2, accA)   (vfmadd213ss)
//   accB = B0; accB = fma(B1, z1, accB); accB = fma(B2, z2, accB)
//   out  = 2 * cplx_div(accB, accA)        (0x181a77520: rcpps + 1 Newton step)
//
// Coefficients come from FUN_180533ec0 (double pipeline) + cvtpd2ps packing
// as done in the twin prologue (stack slots +0x28..+0x40).
//
// Constants locked in Phase 1:
//   A0=B0=1+d, A1=B1=-2*cos(w0), A2=1-d, B2=1-d2,
//   d  = p*sqrtf(param_5), d2 = p/sqrtf(param_5),
//   p  = sin(w0)*0.5/Q,  w0 = max(freq,2.0)*2*pi/fs_total.
//   param_5 = 10^(sens_stored/20) with sens_stored~=24.65 dB (host-scaled ~=2*XML 12.0).

namespace detkernel {

struct cplxf {
    float re, im;
};

struct twin_coeff {
    float A[3];  // A0,A1,A2  (float32 after cvtpd2ps)
    float B[3];  // B0,B1,B2
};

// FUN_180533ec0 coefficients, packed to float32 like the twin prologue.
// sens_lin = param_5 (linear, before sqrtf) e.g. 10^(24.65/20).
twin_coeff build_twin_coeff(double fs_total, double freq, double q, float sens_lin);

// 0x181a77520 complex division, scalar form (rcpps + Newton, NaN guard).
void cplx_div_exact(const cplxf& num, const cplxf& den, cplxf& out);

// 0x18000ad60 scalar complex multiply (vfmaddsub213ps form).
void cplx_mul_exact(const cplxf& a, const cplxf& b, cplxf& out);

// Full twin evaluation for `n` bins. `z` carries unit-magnitude twiddles
// exp(+i*theta_k) (the function applies the conjugate itself).
void twin_apply(const twin_coeff& c, const cplxf* z, size_t n, cplxf* out);

}  // namespace detkernel