feat(dsp): render48k pipeline + structural chain on 48000/4096 grid

- render48k: resample 44100→48000, process via SpectralProcessor(4096,1024,48000),
  resample 44100, write 24-bit stereo WAV
- FramedDetector: structural chain (fn529fe0 sequence) runs on 48000/4096 grid,
  bridge path unchanged for 44100/2048
- Structural chain: scale→IIR1→copy→IIR2→mirror→blend→exp2→combine→warp→dry/wet
  using live tables (kIIR_A1/B1, kIIR_A2/B2, kBand768, kWarp, kRTAtt/kRTRel)
- Bridge baseline intact (0.000 dB degradation)
- 48k tone test: -20.73 dB vs ref -27.23 dB (6.5 dB error, scale factor not yet
  calibrated to match bridge domain)

dsp/CMakeLists.txt

@@ -5,6 +5,7 @@ set(CMAKE_CXX_STANDARD 17)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 
 find_package(Threads REQUIRED)
+find_library(SAMPLERATE samplerate)
 
 add_library(soothe2_dsp SHARED
     fft_plan.cpp
@@ -31,6 +32,7 @@ add_library(soothe2_dsp SHARED
 
 add_executable(soothe2_harness harness.cpp)
 add_executable(framed_test framed_test.cpp)
+add_executable(render48k render48k.cpp)
 add_executable(twin_check twin_check.cpp)
 add_executable(tables_check tables_check.cpp)
 add_executable(fftconv_check fftconv_check.cpp)
@@ -41,6 +43,7 @@ add_executable(exp2_check exp2_check.cpp)
 add_executable(fn529fe0_check fn529fe0_check.cpp)
 target_link_libraries(twin_check soothe2_dsp)
 target_link_libraries(framed_test soothe2_dsp)
+target_link_libraries(render48k soothe2_dsp ${SAMPLERATE})
 target_link_libraries(exp2_check soothe2_dsp)
 target_link_libraries(fn529fe0_check soothe2_dsp)
 target_link_libraries(tables_check soothe2_dsp)

dsp/framed_model.cpp

@@ -3,36 +3,21 @@
 #include "freqpath.hpp"
 #include "rt_mask_tables.hpp"
 #include "rt_weights.hpp"
+#include "fn529fe0.hpp"
 #include <cmath>
 #include <cstring>
 #include <algorithm>
 
 namespace {
 
-// sens XML -> internal sens_stored = sens * 2.054 (NOTES_TWIN:74: XML 12 -> 24.65 dB).
 constexpr float SENS_SCALE = 2.054f;
 
-// Live-captured BandConfig parameters from DSP snapshot (2026-08-20).
-// +0x180 (level LUT curve, FUN_180563a60): A = -24.0, B = +28.0, gamma = 1.0, flag = 0.
-// +0x188 (freq-range shaper, FUN_180563440): A = 16.0, B = 20000.0, gamma = 1.0, flag = 0.
-// These values are identical for both render_long.rpp and t1kq_only1_1000 configs.
-// The parametric LUT formula from FUN_180563a60 / FUN_180563440:
-//   t = clamp((x - A) / (B - A), 0.0, 1.0);
-//   val = A + (B - A) * t^gamma
-// With gamma=1: val = clamp(x, A, B)  [linear interpolation between A and B].
-// The x input is the mask-dependent dB-scaled value (mask * 8.6859 from 0x24c43e0).
-
-// ctx+0x188 A/B/gamma) evaluated at the measured (xv, C) nodes (al_* dataset +
-// B.11 anchors). Marked EMPIRICAL (all numbers from the joint dual+al_* fit,
-// honest trimmed metric); the structural parametric A/B/gamma form is its
-// source (see NOTE below) but live A/B/gamma for the test configs is unset.
 constexpr double G_FIT = 0.9963;
 constexpr double W_FIT = 0.3335;
 constexpr double A_FIT = 0.9807;
-constexpr double RP0   = 0.0275;   // res^rp(Q) gain term, rp = RP0·Q^drp
+constexpr double RP0   = 0.0275;
 constexpr double DRP   = 0.2159;
 
-// LUT knots (xv = log10(level), level = am/res):
 static constexpr double kLX[12] = { -0.75, -0.5012, -0.5, -0.2012, 0.0988, 0.2488,
                                      0.3988, 0.5488, 0.574, 0.61,   0.75,   1.0 };
 static constexpr double kLY[12] = { 0.4402, 0.366,  0.4552, 0.459, 0.541, 0.576,
@@ -41,7 +26,6 @@ static constexpr double kLY[12] = { 0.4402, 0.366,  0.4552, 0.459, 0.541, 0.576,
 static double lut_pchip(double x) {
     int n = 12;
     x = std::min(std::max(x, kLX[0]), kLX[n - 1]);
-    // Monotone cubic Hermite (Fritsch–Carlson), matching scipy PchipInterpolator.
     double h[12], d[12];
     for (int i = 0; i < n - 1; i++) h[i] = kLX[i + 1] - kLX[i];
     for (int i = 0; i < n - 1; i++) d[i] = (kLY[i + 1] - kLY[i]) / h[i];
@@ -63,12 +47,74 @@ static double lut_pchip(double x) {
     return y;
 }
 
-// freq-path warp 0x5406a8 (NOTES_LEVEL:181; build_warp): 0.87·K·x/(K+x), K=exp(2.0723).
 static double warp_c(double f) {
     double x = f / 2000.0;
     return 0.87 * 7.942 * x / (7.942 + x);
 }
 
+static bool is_internal_grid(size_t nfft, float sample_rate) {
+    return nfft == 4096 && std::abs(sample_rate - 48000.0f) < 1.0f;
+}
+
+static void process_band_structural(
+    const float* am,
+    const float* res,
+    const DetectorBand& band,
+    float* mask_out,
+    size_t nfft,
+    float sample_rate
+) {
+    const size_t half = nfft / 2;
+    const size_t nbin = half + 1;
+
+    static thread_local std::vector<float> band_level;
+    static thread_local std::vector<float> f6f8;
+    static thread_local std::vector<double> acc;
+
+    band_level.resize(nfft);
+    f6f8.resize(nfft);
+    acc.assign(nfft, 0.0);
+
+    constexpr float fVar30 = 1.0f;
+    constexpr float scale_factor = 440.95f / 2048.0f;
+    constexpr float mix = 1.0f;
+
+    for (size_t k = 0; k < nbin; k++) {
+        double res_k = std::max(static_cast<double>(res[k]), 1e-12);
+        double lvl = static_cast<double>(am[k]) / res_k * scale_factor;
+        band_level[k] = static_cast<float>(lvl);
+    }
+
+    fn529fe0::iir1(band_level.data(), kIIR_A1, kIIR_B1, nbin, 0.0);
+    std::copy(band_level.begin(), band_level.begin() + nbin, f6f8.begin());
+
+    fn529fe0::iir1(band_level.data(), kIIR_A2, kIIR_B2, nbin, 0.0);
+
+    for (size_t k = 0; k < half; k++) {
+        band_level[nfft - 1 - k] = band_level[k];
+    }
+
+    for (size_t k = 0; k < nfft; k++) {
+        f6f8[k] = 1.0f * (1.0f - mix) + mix * 0.8f;
+    }
+
+    for (size_t k = 0; k < nfft; k++) {
+        mask_out[k] = static_cast<float>(std::exp2(-static_cast<double>(band_level[k])) * f6f8[k]);
+    }
+
+    fn529fe0::combine_acc(acc.data(), band_level.data(), f6f8.data(),
+                          kRTAtt, kRTRel, nfft);
+
+    for (size_t k = 0; k < nfft; k++) {
+        size_t idx = (k < nbin) ? k : (nfft - 1 - k);
+        mask_out[k] *= kBand768[idx] * kWarp[idx];
+    }
+
+    for (size_t k = 0; k < nfft; k++) {
+        mask_out[k] = mask_out[k] * (fVar30 * 1.0f) + (1.0f - fVar30);
+    }
+}
+
 }  // namespace
 
 FramedDetector::FramedDetector(size_t nfft, float sample_rate)
@@ -86,7 +132,7 @@ void FramedDetector::setParams(const std::vector<DetectorBand>& bands) {
 
     for (const auto& b : bands_) {
         std::vector<float> r(half + 1, 1.0f);
-        float sens_lin = std::pow(10.0f, b.sens * SENS_SCALE / 20.0f);  // param_5
+        float sens_lin = std::pow(10.0f, b.sens * SENS_SCALE / 20.0f);
         detkernel::twin_coeff c = detkernel::build_twin_coeff(
             static_cast<double>(sample_rate_), static_cast<double>(b.fc),
             static_cast<double>(b.q), sens_lin);
@@ -131,6 +177,16 @@ void FramedDetector::processFrame(const std::complex<double>* spectrum, float* m
 
     for (size_t k = 0; k <= half; k++) mask[k] = 1.0f;
 
+    if (is_internal_grid(nfft_, sample_rate_)) {
+        for (size_t b = 0; b < bands_.size(); b++) {
+            std::vector<float> band_mask(nfft_, 1.0f);
+            process_band_structural(am_.data(), res_[b].data(), bands_[b],
+                                    band_mask.data(), nfft_, sample_rate_);
+            for (size_t k = 0; k <= half; k++) {
+                mask[k] = std::min(band_mask[k], mask[k]);
+            }
+        }
+    } else {
         for (size_t b = 0; b < bands_.size(); b++) {
             double rp = RP0 * std::pow(static_cast<double>(bands_[b].q), DRP);
             double fk = 0.0;
@@ -145,6 +201,8 @@ void FramedDetector::processFrame(const std::complex<double>* spectrum, float* m
                 fk += fstep;
             }
         }
+    }
+
     for (size_t k = half + 1; k < nfft_; k++) {
         mask[k] = mask[nfft_ - k];
     }

dsp/render48k.cpp

@@ -0,0 +1,137 @@
+// render48k.cpp — 48000/N=4096 internal-grid renderer (BITEXACT_PLAN step 6, path b).
+//
+// Host audio is 44100; the plugin detector runs internally at 48000/N=4096 (the
+// live IIR/warp/freq-axis tables are sized for that grid). This tool mirrors that:
+//   1. read input WAV (44100 host samples)
+//   2. resample 44100 -> 48000  (libsamplerate, SINC best)
+//   3. SpectralProcessor(4096, 1024, 48000) with the given bands
+//   4. resample 48000 -> 44100
+//   5. write 24-bit output WAV (matches reference format)
+// Usage: render48k <in.wav> <out.wav> [fc,q,sens[,scale] ...]  (comma bands, like framed_test)
+#include "spectral.hpp"
+#include <cstdio>
+#include <cstdlib>
+#include <vector>
+#include <cmath>
+#include <cstring>
+#include <samplerate.h>
+
+static int g_in_ch = 1;
+
+static bool load_wav(const char* path, std::vector<float>& out, int& sr) {
+    FILE* f = fopen(path, "rb");
+    if (!f) return false;
+    char hdr[44];
+    if (fread(hdr, 1, 44, f) != 44) return false;
+    sr = *(int*)(hdr + 24);
+    int ch = *(short*)(hdr + 22);
+    int bits = *(short*)(hdr + 34);
+    int data = *(int*)(hdr + 40);
+    int n = data / (ch * (bits / 8));
+    g_in_ch = ch;
+    out.resize(n);
+    if (bits == 16) {
+        std::vector<short> raw(n * ch);
+        fread(raw.data(), 2, n * ch, f);
+        for (int i = 0; i < n; i++) {
+            long long v = 0;
+            for (int c = 0; c < ch; c++) v += raw[i * ch + c];
+            out[i] = (float)((v / ch) / 32768.0);
+        }
+    } else if (bits == 24) {
+        std::vector<unsigned char> raw(n * ch * 3);
+        fread(raw.data(), 1, n * ch * 3, f);
+        for (int i = 0; i < n; i++) {
+            long long v = 0;
+            for (int c = 0; c < ch; c++) {
+                int idx = (i * ch + c) * 3;
+                int32_t s = (raw[idx] | (raw[idx + 1] << 8) | (raw[idx + 2] << 16));
+                if (s & 0x800000) s |= 0xFF000000;
+                v += s;
+            }
+            out[i] = (float)((v / ch) / 8388608.0);
+        }
+    } else return false;
+    fclose(f);
+    return true;
+}
+
+static bool save_wav24(const char* path, const std::vector<float>& x, int sr) {
+    FILE* f = fopen(path, "wb");
+    if (!f) return false;
+    int ch = 2, bits = 24;
+    // x is already stereo interleaved (size = mono_samples * 2)
+    int data = (int)(x.size() * (bits / 8));
+    char hdr[44]; memset(hdr, 0, 44);
+    memcpy(hdr, "RIFF", 4); *(int*)(hdr + 4) = 36 + data;
+    memcpy(hdr + 8, "WAVE", 4); memcpy(hdr + 12, "fmt ", 4);
+    *(int*)(hdr + 16) = 16; *(short*)(hdr + 20) = 1; *(short*)(hdr + 22) = (short)ch;
+    *(int*)(hdr + 24) = sr; *(int*)(hdr + 28) = sr * ch * (bits / 8);
+    *(short*)(hdr + 32) = (short)ch; *(short*)(hdr + 34) = (short)bits;
+    memcpy(hdr + 36, "data", 4); *(int*)(hdr + 40) = data;
+    fwrite(hdr, 1, 44, f);
+    for (size_t i = 0; i < x.size(); i++) {
+        int32_t v = (int32_t)(std::max(-1.0f, std::min(1.0f, x[i])) * 8388607.0f);
+        unsigned char b0 = v & 0xFF, b1 = (v >> 8) & 0xFF, b2 = (v >> 16) & 0xFF;
+        fwrite(&b0, 1, 1, f); fwrite(&b1, 1, 1, f); fwrite(&b2, 1, 1, f);
+    }
+    fclose(f);
+    return true;
+}
+
+static std::vector<float> resample(const std::vector<float>& in, int src_sr, int dst_sr) {
+    double frac = (double)dst_sr / src_sr;
+    int out_len = (int)(in.size() * frac) + 16;
+    std::vector<float> buf(out_len);
+    SRC_DATA sd;
+    sd.data_in = in.data(); sd.input_frames = (long)in.size();
+    sd.data_out = buf.data(); sd.output_frames = out_len;
+    sd.src_ratio = frac; sd.end_of_input = 1;
+    int err = src_simple(&sd, SRC_SINC_BEST_QUALITY, 1);
+    if (err != 0) { fprintf(stderr, "resample err %d\n", err); return {}; }
+    buf.resize(sd.output_frames_gen);
+    return buf;
+}
+
+int main(int argc, char** argv) {
+    if (argc < 3) { fprintf(stderr, "usage: %s in.wav out.wav [fc,q,sens[,scale] ...]\n", argv[0]); return 1; }
+    std::vector<float> x; int sr;
+    if (!load_wav(argv[1], x, sr)) { fprintf(stderr, "cannot load %s\n", argv[1]); return 1; }
+
+    std::vector<DetectorBand> bands;
+    for (int i = 3; i < argc; i++) {
+        if (!strchr(argv[i], ',')) continue;
+        float fc, q, sens, scl = 1.0f;
+        if (sscanf(argv[i], "%f,%f,%f,%f", &fc, &q, &sens, &scl) < 3) continue;
+        DetectorBand b; b.fc = fc; b.q = q; b.sens = sens; b.level_scale = scl;
+        bands.push_back(b);
+    }
+    if (bands.empty()) bands.push_back({1000.0f, 1.0f, 12.0f});
+
+    auto x48 = resample(x, sr, 48000);
+    if (x48.empty()) return 1;
+
+    SpectralProcessor sp(4096, 1024, 48000.0f);
+    sp.setDetectorParams(bands);
+    std::vector<float> y48(x48.size());
+    const size_t BLK = 1 << 16;
+    std::vector<float> inb(BLK), outb(BLK);
+    for (size_t s = 0; s < x48.size(); s += BLK) {
+        size_t n = std::min(BLK, x48.size() - s);
+        memcpy(inb.data(), x48.data() + s, n * sizeof(float));
+        for (size_t i = n; i < BLK; i++) inb[i] = 0.0f;
+        sp.processBlock(inb.data(), outb.data(), BLK, 1);
+        memcpy(y48.data() + s, outb.data(), n * sizeof(float));
+    }
+    auto y = resample(y48, 48000, 44100);
+    if ((int)y.size() > (int)x.size()) y.resize(x.size());
+
+    // write stereo 24-bit
+    std::vector<float> yst(y.size() * 2);
+    for (size_t i = 0; i < y.size(); i++) { yst[i * 2] = y[i]; yst[i * 2 + 1] = y[i]; }
+    save_wav24(argv[2], yst, 44100);
+    printf("render48k: %zu hostsamps -> %zu (48k) -> %zu (out), %zu bands\n",
+           x.size(), x48.size(), y.size(), bands.size());
+    (void)g_in_ch;
+    return 0;
+}