fix: Resolve WebGPU uniform buffer alignment issues (Task #74)

Fixed multiple WGSL/C++ struct alignment mismatches causing validation errors:

Padding fixes:
- fade_effect.cc: Changed EffectParams padding from vec3<f32> to _pad0/1/2
- theme_modulation_effect.cc: Same padding fix for EffectParams
- Root cause: WGSL vec3<f32> has 16-byte alignment, creating 32-byte structs

ODR violation fix:
- demo_effects.h: Added includes for fade_effect.h, theme_modulation_effect.h
- Removed incomplete forward declarations (88 bytes) conflicting with
  complete definitions (96 bytes), causing heap buffer overflow in make_shared

Member shadowing cleanup:
- Renamed Effect::uniforms_ shadowing members to descriptive names:
  - FadeEffect: uniforms_ -> common_uniforms_
  - FlashEffect: uniforms_ -> flash_uniforms_
  - ThemeModulationEffect: uniforms_ -> common_uniforms_

Results:
- demo64k runs without crashes
- 33/33 tests passing (100%)
- Added Task #75: WGSL uniform validation tool

handoff(Claude): Uniform buffer alignment debugged and fixed

7 files changed, 22 insertions, 30 deletions

diff --git a/src/gpu/demo_effects.h b/src/gpu/demo_effects.h
index 7ad8261..54bf657 100644
--- a/src/gpu/demo_effects.h
+++ b/src/gpu/demo_effects.h
@@ -7,10 +7,12 @@
 #include "3d/scene.h"
 #include "effect.h"
 #include "gpu/effects/circle_mask_effect.h"
+#include "gpu/effects/fade_effect.h" // FadeEffect with full definition
 #include "gpu/effects/flash_effect.h" // FlashEffect with params support
 #include "gpu/effects/post_process_helper.h"
 #include "gpu/effects/rotating_cube_effect.h"
 #include "gpu/effects/shaders.h"
+#include "gpu/effects/theme_modulation_effect.h" // ThemeModulationEffect with full definition
 #include "gpu/gpu.h"
 #include "gpu/texture_manager.h"
 #include "gpu/uniform_helper.h"
@@ -197,22 +199,8 @@ class FlashCubeEffect : public Effect {
   float flash_intensity_;
 };
 
-class ThemeModulationEffect : public PostProcessEffect {
- public:
-  ThemeModulationEffect(const GpuContext& ctx);
-  void render(WGPURenderPassEncoder pass, float time, float beat,
-              float intensity, float aspect_ratio) override;
-  void update_bind_group(WGPUTextureView input_view) override;
-};
-
-class FadeEffect : public PostProcessEffect {
- public:
-  FadeEffect(const GpuContext& ctx);
-  void render(WGPURenderPassEncoder pass, float time, float beat,
-              float intensity, float aspect_ratio) override;
-  void update_bind_group(WGPUTextureView input_view) override;
-};
-
+// ThemeModulationEffect now defined in gpu/effects/theme_modulation_effect.h (included above)
+// FadeEffect now defined in gpu/effects/fade_effect.h (included above)
 // FlashEffect now defined in gpu/effects/flash_effect.h (included above)
 
 // Auto-generated functions
diff --git a/src/gpu/effects/fade_effect.cc b/src/gpu/effects/fade_effect.cc
index c70177e..3efc583 100644
--- a/src/gpu/effects/fade_effect.cc
+++ b/src/gpu/effects/fade_effect.cc
@@ -24,7 +24,9 @@ FadeEffect::FadeEffect(const GpuContext& ctx) : PostProcessEffect(ctx) {
 
     struct EffectParams {
       fade_amount: f32,
-      _pad: vec3<f32>,
+      _pad0: f32,
+      _pad1: f32,
+      _pad2: f32,
     };
 
     @group(0) @binding(0) var inputSampler: sampler;
@@ -55,14 +57,14 @@ FadeEffect::FadeEffect(const GpuContext& ctx) : PostProcessEffect(ctx) {
 
   pipeline_ =
       create_post_process_pipeline(ctx_.device, ctx_.format, shader_code);
-  uniforms_.init(ctx_.device);
+  common_uniforms_.init(ctx_.device);
   params_buffer_ = gpu_create_buffer(
       ctx_.device, 16, WGPUBufferUsage_Uniform | WGPUBufferUsage_CopyDst);
 }
 
 void FadeEffect::update_bind_group(WGPUTextureView input_view) {
   pp_update_bind_group(ctx_.device, pipeline_, &bind_group_, input_view,
-                       uniforms_.get(), params_buffer_);
+                       common_uniforms_.get(), params_buffer_);
 }
 
 void FadeEffect::render(WGPURenderPassEncoder pass, float time, float beat,
@@ -74,7 +76,7 @@ void FadeEffect::render(WGPURenderPassEncoder pass, float time, float beat,
       .beat = beat,
       .audio_intensity = intensity,
   };
-  uniforms_.update(ctx_.queue, u);
+  common_uniforms_.update(ctx_.queue, u);
 
   // Example fade pattern: fade in at start, fade out at end
   // Customize this based on your needs
diff --git a/src/gpu/effects/fade_effect.h b/src/gpu/effects/fade_effect.h
index 485cc01..22b8f76 100644
--- a/src/gpu/effects/fade_effect.h
+++ b/src/gpu/effects/fade_effect.h
@@ -16,6 +16,6 @@ class FadeEffect : public PostProcessEffect {
   void update_bind_group(WGPUTextureView input_view) override;
 
  private:
-  UniformBuffer<CommonPostProcessUniforms> uniforms_;
+  UniformBuffer<CommonPostProcessUniforms> common_uniforms_;
   GpuBuffer params_buffer_;
 };
diff --git a/src/gpu/effects/flash_effect.cc b/src/gpu/effects/flash_effect.cc
index ccf0756..57c1d73 100644
--- a/src/gpu/effects/flash_effect.cc
+++ b/src/gpu/effects/flash_effect.cc
@@ -55,12 +55,12 @@ FlashEffect::FlashEffect(const GpuContext& ctx, const FlashEffectParams& params)
 
   pipeline_ =
       create_post_process_pipeline(ctx_.device, ctx_.format, shader_code);
-  uniforms_.init(ctx_.device);
+  flash_uniforms_.init(ctx_.device);
 }
 
 void FlashEffect::update_bind_group(WGPUTextureView input_view) {
   pp_update_bind_group(ctx_.device, pipeline_, &bind_group_, input_view,
-                       uniforms_.get(), {});
+                       flash_uniforms_.get(), {});
 }
 
 void FlashEffect::render(WGPURenderPassEncoder pass, float time, float beat,
@@ -88,7 +88,7 @@ void FlashEffect::render(WGPURenderPassEncoder pass, float time, float beat,
       ._pad1 = {0.0f, 0.0f}, // Padding for vec3 alignment
       .color = {r, g, b},    // Time-dependent, computed every frame
       ._pad2 = 0.0f};
-  uniforms_.update(ctx_.queue, u);
+  flash_uniforms_.update(ctx_.queue, u);
 
   wgpuRenderPassEncoderSetPipeline(pass, pipeline_);
   wgpuRenderPassEncoderSetBindGroup(pass, 0, bind_group_, 0, nullptr);
diff --git a/src/gpu/effects/flash_effect.h b/src/gpu/effects/flash_effect.h
index d7a438b..55bad7b 100644
--- a/src/gpu/effects/flash_effect.h
+++ b/src/gpu/effects/flash_effect.h
@@ -39,7 +39,7 @@ class FlashEffect : public PostProcessEffect {
 
  private:
   FlashEffectParams params_;
-  UniformBuffer<FlashUniforms> uniforms_;
+  UniformBuffer<FlashUniforms> flash_uniforms_;
   UniformBuffer<FlashEffectParams> params_buffer_;
   float flash_intensity_ = 0.0f;
 };
diff --git a/src/gpu/effects/theme_modulation_effect.cc b/src/gpu/effects/theme_modulation_effect.cc
index fc52b62..f9ae636 100644
--- a/src/gpu/effects/theme_modulation_effect.cc
+++ b/src/gpu/effects/theme_modulation_effect.cc
@@ -26,7 +26,9 @@ ThemeModulationEffect::ThemeModulationEffect(const GpuContext& ctx)
 
     struct EffectParams {
       theme_brightness: f32,
-      _pad: vec3<f32>,
+      _pad0: f32,
+      _pad1: f32,
+      _pad2: f32,
     };
 
     @group(0) @binding(0) var inputSampler: sampler;
@@ -59,14 +61,14 @@ ThemeModulationEffect::ThemeModulationEffect(const GpuContext& ctx)
   pipeline_ =
       create_post_process_pipeline(ctx_.device, ctx_.format, shader_code);
 
-  uniforms_.init(ctx_.device);
+  common_uniforms_.init(ctx_.device);
   params_buffer_ = gpu_create_buffer(
       ctx_.device, 16, WGPUBufferUsage_Uniform | WGPUBufferUsage_CopyDst);
 }
 
 void ThemeModulationEffect::update_bind_group(WGPUTextureView input_view) {
   pp_update_bind_group(ctx_.device, pipeline_, &bind_group_, input_view,
-                       uniforms_.get(), params_buffer_);
+                       common_uniforms_.get(), params_buffer_);
 }
 
 void ThemeModulationEffect::render(WGPURenderPassEncoder pass, float time,
@@ -79,7 +81,7 @@ void ThemeModulationEffect::render(WGPURenderPassEncoder pass, float time,
       .beat = beat,
       .audio_intensity = intensity,
   };
-  uniforms_.update(ctx_.queue, u);
+  common_uniforms_.update(ctx_.queue, u);
 
   // Alternate between bright and dark every 4 seconds (2 pattern changes)
   // Music patterns change every 2 seconds at 120 BPM
diff --git a/src/gpu/effects/theme_modulation_effect.h b/src/gpu/effects/theme_modulation_effect.h
index b972509..107529b 100644
--- a/src/gpu/effects/theme_modulation_effect.h
+++ b/src/gpu/effects/theme_modulation_effect.h
@@ -16,6 +16,6 @@ class ThemeModulationEffect : public PostProcessEffect {
   void update_bind_group(WGPUTextureView input_view) override;
 
  private:
-  UniformBuffer<CommonPostProcessUniforms> uniforms_;
+  UniformBuffer<CommonPostProcessUniforms> common_uniforms_;
   GpuBuffer params_buffer_;
 };