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, 4 insertions, 4 deletions

diff --git a/cnn_v3/shaders/gbuf_pack.wgsl b/cnn_v3/shaders/gbuf_pack.wgsl
index dd8d73b..777b4e5 100644
--- a/cnn_v3/shaders/gbuf_pack.wgsl
+++ b/cnn_v3/shaders/gbuf_pack.wgsl
@@ -106,13 +106,13 @@ fn pack_features(@builtin(global_invocation_id) id: vec3u) {
     // Texture 1: 4 u32, each = pack4x8unorm of four u8 values
     // [0] mat_id | prev.r | prev.g | prev.b
     // [1] mip1.r | mip1.g | mip1.b | mip2.r
-    // [2] mip2.g | mip2.b | transp | (spare)
-    // [3] dif.r | dif.g | dif.b | (spare)  — dif = diffuse*shadow (scalar, stored in all 3)
+    // [2] mip2.g | mip2.b | dif    | transp   — ch18=dif, ch19=transp
+    // [3] spare
     let t1 = vec4u(
         pack4x8unorm(vec4f(mat_id_u8, prev.r, prev.g, prev.b)),
         pack4x8unorm(vec4f(mip1.r, mip1.g, mip1.b, mip2.r)),
-        pack4x8unorm(vec4f(mip2.g, mip2.b, transp, 0.0)),
-        pack4x8unorm(vec4f(dif, dif, dif, 0.0))
+        pack4x8unorm(vec4f(mip2.g, mip2.b, dif, transp)),
+        0u
     );
     textureStore(feat_tex1, coord, t1);
 }