fix: move light data from UBO to push constants — fixes std140 layout issue

Root cause: GLSL std140 layout adds padding after mat4 for vec4 fields,
causing light data to be read at wrong offsets → NaN/artifacts.

Fix:
- UBO back to 64 bytes (mat4 vp only)
- Light data (pos + color, 32 bytes) sent via push constants at offset 64
- Two push constant ranges: Vertex (0-64, model) + Fragment (64-96, light)
- Both vertex and fragment shaders read from same push_constant block
- PBR shader fully restored with Cook-Torrance BRDF
- Dynamic point light follows physics ball

src/Engine.Graphics.Vulkan/Shaders/triangle.frag

@@ -10,22 +10,97 @@ layout(set = 0, binding = 0) uniform CameraUBO {
     mat4 vp;
 };
 
+layout(push_constant) uniform PC {
+    mat4 model;
+    vec4 lightPos;
+    vec4 lightColor;
+} pc;
+
+const vec3 AMBIENT = vec3(0.01, 0.01, 0.02);
+const float PI = 3.14159265359;
+
+float distributionGGX(vec3 N, vec3 H, float roughness)
+{
+    float a = roughness * roughness;
+    float a2 = a * a;
+    float NdotH = max(dot(N, H), 0.0);
+    float NdotH2 = NdotH * NdotH;
+    float num = a2;
+    float denom = NdotH2 * (a2 - 1.0) + 1.0;
+    denom = PI * denom * denom;
+    return num / denom;
+}
+
+float geometrySchlickGGX(float NdotV, float roughness)
+{
+    float r = roughness + 1.0;
+    float k = (r * r) / 8.0;
+    return NdotV / (NdotV * (1.0 - k) + k);
+}
+
+float geometrySmith(vec3 N, vec3 V, vec3 L, float roughness)
+{
+    float NdotV = max(dot(N, V), 0.0);
+    float NdotL = max(dot(N, L), 0.0);
+    return geometrySchlickGGX(NdotV, roughness) * geometrySchlickGGX(NdotL, roughness);
+}
+
+vec3 fresnelSchlick(float cosTheta, vec3 F0)
+{
+    return F0 + (1.0 - F0) * pow(clamp(1.0 - cosTheta, 0.0, 1.0), 5.0);
+}
+
+vec3 acesTonemap(vec3 color)
+{
+    float a = 2.51;
+    float b = 0.03;
+    float c = 2.43;
+    float d = 0.59;
+    float e = 0.14;
+    return clamp((color * (a * color + b)) / (color * (c * color + d) + e), 0.0, 1.0);
+}
+
 void main()
 {
     vec3 N = normalize(fragNormal);
-    
-    // Hardcoded light at (0, 10, 0) — test if lighting works at all
-    vec3 lightPos = vec3(0.0, 10.0, 0.0);
+    vec3 V = normalize(-fragWorldPos);
+    vec3 albedo = fragAlbedo;
+    float roughness = 0.5;
+    float metallic = 0.1;
+
+    vec3 color = AMBIENT * albedo;
+
+    vec3 lightPos = pc.lightPos.xyz;
+    float lightIntensity = pc.lightPos.w;
+    vec3 lightColor = pc.lightColor.xyz;
+    float lightRange = pc.lightColor.w;
+
     vec3 toLight = lightPos - fragWorldPos;
     float dist = length(toLight);
-    vec3 L = normalize(toLight);
+    vec3 L = toLight / max(dist, 0.001);
+
+    float attenuation = pow(clamp(1.0 - dist / max(lightRange, 0.001), 0.0, 1.0), 2.0);
+    vec3 radiance = lightColor * lightIntensity * attenuation;
+
+    vec3 H = normalize(V + L);
+    vec3 F0 = mix(vec3(0.04), albedo, metallic);
+
+    float NDF = distributionGGX(N, H, roughness);
+    float G = geometrySmith(N, V, L, roughness);
+    vec3 F = fresnelSchlick(max(dot(H, V), 0.0), F0);
+
+    vec3 numerator = NDF * G * F;
+    float denominator = 4.0 * max(dot(N, V), 0.0) * max(dot(N, L), 0.0) + 0.0001;
+    vec3 specular = numerator / denominator;
+
+    vec3 kS = F;
+    vec3 kD = (vec3(1.0) - kS) * (1.0 - metallic);
 
     float NdotL = max(dot(N, L), 0.0);
-    float atten = 1.0 / (1.0 + dist * dist * 0.05);
-    float intensity = 30.0;
+    color += (kD * albedo / PI + specular) * radiance * NdotL;
 
-    vec3 color = fragAlbedo * vec3(1.0, 0.9, 0.7) * NdotL * intensity * atten;
-    color += fragAlbedo * 0.02;
+    color = acesTonemap(color);
+    color = pow(color, vec3(1.0 / 2.2));
 
     outColor = vec4(color, 1.0);
 }