feat(cnn_v3): shadow→dif migration complete (ch18)

Replace raw shadow (ch18) with dif = max(0,dot(normal,KEY_LIGHT))*shadow
across all layers. Channel count stays 20, weight shapes unchanged.

- gbuf_pack.wgsl: t1.z = pack4x8unorm(mip2.g, mip2.b, dif, transp); t1.w = 0u
- gbuf_deferred.wgsl: read dif from unpack4x8unorm(t1.z).z
- gbuf_view.wgsl: revert to 4×5 grid, ch18=dif label, ch19=trns label
- tools/shaders.js: FULL_PACK_SHADER adds oct_decode + computes dif
- cnn_v3_utils.py: assemble_features() computes dif on-the-fly via oct_decode
- docs: CNN_V3.md, HOWTO.md, HOW_TO_CNN.md, GBUF_DIF_MIGRATION.md updated

handoff(Gemini): shadow→dif migration done, ready for first training pass

1 files changed, 8 insertions, 12 deletions

diff --git a/cnn_v3/shaders/gbuf_view.wgsl b/cnn_v3/shaders/gbuf_view.wgsl
index d53b6f6..6a812e6 100644
--- a/cnn_v3/shaders/gbuf_view.wgsl
+++ b/cnn_v3/shaders/gbuf_view.wgsl
@@ -1,5 +1,5 @@
-// G-buffer channel visualization — 4×6 grid of 23 feature channels.
-// Takes feat_tex0 (rgba32uint, ch 0-7 f16) and feat_tex1 (rgba32uint, ch 8-22 unorm8).
+// G-buffer channel visualization — 4×5 grid of 20 feature channels.
+// Takes feat_tex0 (rgba32uint, ch 0-7 f16) and feat_tex1 (rgba32uint, ch 8-19 unorm8).
 // Outputs tiled channel view to a standard rgba8unorm render target.
 //
 // Channel layout (row×col):
@@ -7,8 +7,7 @@
 //   Row 1: ch4(nrm.y)  ch5(depth)  ch6(dzdx)   ch7(dzdy)
 //   Row 2: ch8(matid)  ch9(prv.r)  ch10(prv.g) ch11(prv.b)
 //   Row 3: ch12(m1.r)  ch13(m1.g)  ch14(m1.b)  ch15(m2.r)
-//   Row 4: ch16(m2.g)  ch17(m2.b)  ch18(trns)  ch19(spare)
-//   Row 5: ch20(dif.r) ch21(dif.g) ch22(dif.b) ch23(spare)
+//   Row 4: ch16(m2.g)  ch17(m2.b)  ch18(dif)   ch19(trns)
 
 #include "debug/debug_print"
 
@@ -30,12 +29,12 @@ fn fs_main(@builtin(position) pos: vec4f) -> @location(0) vec4f {
     let uv  = pos.xy / u.resolution;
 
     let COLS = 4.0;
-    let ROWS = 6.0;
+    let ROWS = 5.0;
     let col  = u32(uv.x * COLS);
     let row  = u32(uv.y * ROWS);
     let ch   = row * 4u + col;
 
-    if (col >= 4u || ch == 19u || ch >= 23u) {
+    if (col >= 4u || ch >= 20u) {
         return vec4f(0.05, 0.05, 0.05, 1.0);
     }
 
@@ -72,8 +71,7 @@ fn fs_main(@builtin(position) pos: vec4f) -> @location(0) vec4f {
         var bytes: vec4f;
         if      (comp_idx == 0u) { bytes = unpack4x8unorm(t.x); }
         else if (comp_idx == 1u) { bytes = unpack4x8unorm(t.y); }
-        else if (comp_idx == 2u) { bytes = unpack4x8unorm(t.z); }
-        else                     { bytes = unpack4x8unorm(t.w); }
+        else                     { bytes = unpack4x8unorm(t.z); }
         var ba = array<f32, 4>(bytes.x, bytes.y, bytes.z, bytes.w);
         v = ba[sub];
     }
@@ -122,10 +120,8 @@ fn fs_main(@builtin(position) pos: vec4f) -> @location(0) vec4f {
         case 15u: { out = debug_str(out, pos.xy, origin, vec4u(0x6D322E72u, 0u, 0u, 0u), 4u); }          // m2.r
         case 16u: { out = debug_str(out, pos.xy, origin, vec4u(0x6D322E67u, 0u, 0u, 0u), 4u); }          // m2.g
         case 17u: { out = debug_str(out, pos.xy, origin, vec4u(0x6D322E62u, 0u, 0u, 0u), 4u); }          // m2.b
-        case 18u: { out = debug_str(out, pos.xy, origin, vec4u(0x74726E73u, 0u, 0u, 0u), 4u); }          // trns
-        case 20u: { out = debug_str(out, pos.xy, origin, vec4u(0x6469662Eu, 0x72000000u, 0u, 0u), 5u); } // dif.r
-        case 21u: { out = debug_str(out, pos.xy, origin, vec4u(0x6469662Eu, 0x67000000u, 0u, 0u), 5u); } // dif.g
-        default:  { out = debug_str(out, pos.xy, origin, vec4u(0x6469662Eu, 0x62000000u, 0u, 0u), 5u); } // dif.b
+        case 18u: { out = debug_str(out, pos.xy, origin, vec4u(0x64696600u, 0u, 0u, 0u), 3u); }          // dif
+        default:  { out = debug_str(out, pos.xy, origin, vec4u(0x74726E73u, 0u, 0u, 0u), 4u); }          // trns
     }
     return out;
 }