refactor: add common shaders helpers + fix shadow export

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

CLAUDE.md

@@ -66,6 +66,18 @@ pixel is a handful of `f32` complex multiplies.
   `compute_reference`/`compute_set_reference`: iterate the chosen formula at
   high precision on the CPU, emitting `Z_n` as `f32` pairs — that's the
   reference orbit the GPU perturbs from.
+- `src/shaders/*.wgsl` — none of these are standalone WGSL modules; WGSL has
+  no `#include`, so each is compiled by concatenating plain-text fragments
+  with `concat!`/`include_str!` at the `create_shader_module` call site (see
+  `renderer.rs`, `buddhabrot.rs`, and `tests/shader_valid.rs`, which must
+  concatenate the same pieces to validate what actually gets built).
+  `common.wgsl` (fullscreen-triangle vertex helper, `cmul`/`cpow`, `KIND_*`
+  constants) is prepended to every shader. `iterate_uniforms.wgsl` (the
+  perturbation-pipeline `Uniforms` struct + `palette()`) is additionally
+  prepended to `mandelbrot.wgsl` and `colorize.wgsl`, which share that layout.
+  Because there's no namespacing, a definition must live in exactly one file
+  among those concatenated together for a given shader — don't redefine a
+  `common.wgsl`/`iterate_uniforms.wgsl` symbol locally.
 - `src/shaders/mandelbrot.wgsl` — the perturbation fragment shader.
   `advance_delta(z, e)` is the per-kind delta step (`z` = reference point,
   `e` = current delta); the caller adds `step_add` (= `dc`) afterward — this
@@ -75,8 +87,8 @@ pixel is a handful of `f32` complex multiplies.
   reference data since the orbit point alone wouldn't be enough to recover an
   exact delta). `fprime(z)` is the derivative used for distance-estimation
   (DE) shading; exact for holomorphic kinds, an approximation (`~2Z`) for the
-  abs-based ones. A `KIND_*` constant here must match the matching
-  `FractalKind` variant's discriminant exactly.
+  abs-based ones. A `KIND_*` constant (from `common.wgsl`) must match the
+  matching `FractalKind` variant's discriminant exactly.
 - `src/fractal/renderer.rs` — `FractalRenderer` (wgpu pipelines, uniform +
   storage buffers, bind groups), `Uniforms` (repr(C) layout that must match
   the WGSL `Uniforms` struct field-for-field, including padding), and
@@ -105,9 +117,10 @@ pixel is a handful of `f32` complex multiplies.
 ### Adding a new `FractalKind`
 
 Touches, in order: `reference.rs` (enum variant + CPU iteration formula, and a
-test comparing against a naive `f64` iteration), `mandelbrot.wgsl` (matching
-`KIND_*` const + `advance_delta`/`fprime` arms), `buddhabrot.wgsl` (matching
-arm in `advance()`, if the kind makes sense as a Buddhabrot), `renderer.rs`
+test comparing against a naive `f64` iteration), `common.wgsl` (matching
+`KIND_*` const), `mandelbrot.wgsl` (matching `advance_delta`/`fprime` arms),
+`buddhabrot.wgsl` (matching arm in `advance()`, if the kind makes sense as a
+Buddhabrot), `renderer.rs`
 `Uniforms` (only if the kind needs a new per-kind constant, e.g. Phoenix's
 `phoenix_p`), `share.rs` (encode/decode string tag), `app.rs` (`KINDS` label,
 `JULIA_PRESETS`/`SET_PRESETS` slot, `default_view_for` entry, and optionally a

src/app.rs

@@ -791,6 +791,13 @@ impl FractalApp {
         &self.reference
     }
 
+    /// The configured shadow-style lights, for headless export's `ExportRender`
+    /// (which has no `FractalCallback` to source them from).
+    #[cfg(not(target_arch = "wasm32"))]
+    pub(crate) fn lights(&self) -> &[Light] {
+        &self.lights
+    }
+
     /// Recompute the reference orbit when needed. Native: dispatch to a worker
     /// thread and pick up completed results. Web: compute inline.
     fn ensure_reference(&mut self) {
@@ -1024,6 +1031,7 @@ impl FractalApp {
             renderer.export_handles()
         };
         let reference = Arc::clone(&self.reference);
+        let lights = self.lights.clone();
 
         let shared = Arc::new(Mutex::new(ExportShared {
             fraction: 0.0,
@@ -1050,6 +1058,7 @@ impl FractalApp {
                     h,
                     uniforms,
                     reference.as_slice(),
+                    &lights,
                 );
                 let sh = Arc::clone(&shared);
                 let png =
@@ -1079,6 +1088,7 @@ impl FractalApp {
                     h,
                     uniforms,
                     reference.as_slice(),
+                    &lights,
                 );
 
                 // Render tile by tile, awaiting each submission so the browser
@@ -2055,10 +2065,10 @@ impl FractalApp {
                 dx -= PAN_SPEED_PX * dt;
             }
             if down {
-                dy += PAN_SPEED_PX * dt;
+                dy -= PAN_SPEED_PX * dt;
             }
             if up {
-                dy -= PAN_SPEED_PX * dt;
+                dy += PAN_SPEED_PX * dt;
             }
             if dx != 0.0 || dy != 0.0 {
                 self.view.pan_pixels(dx, dy, height_px);

src/fractal/buddhabrot.rs

@@ -120,7 +120,13 @@ impl BuddhabrotRenderer {
     pub fn new(device: &wgpu::Device, target_format: wgpu::TextureFormat) -> Self {
         let shader = device.create_shader_module(wgpu::ShaderModuleDescriptor {
             label: Some("buddhabrot"),
-            source: wgpu::ShaderSource::Wgsl(include_str!("../shaders/buddhabrot.wgsl").into()),
+            source: wgpu::ShaderSource::Wgsl(
+                concat!(
+                    include_str!("../shaders/common.wgsl"),
+                    include_str!("../shaders/buddhabrot.wgsl"),
+                )
+                .into(),
+            ),
         });
 
         let uniform_buffer = device.create_buffer(&wgpu::BufferDescriptor {

src/fractal/renderer.rs

@@ -164,7 +164,14 @@ impl FractalRenderer {
     pub fn new(device: &wgpu::Device, target_format: wgpu::TextureFormat) -> Self {
         let shader = device.create_shader_module(wgpu::ShaderModuleDescriptor {
             label: Some("mandelbrot"),
-            source: wgpu::ShaderSource::Wgsl(include_str!("../shaders/mandelbrot.wgsl").into()),
+            source: wgpu::ShaderSource::Wgsl(
+                concat!(
+                    include_str!("../shaders/common.wgsl"),
+                    include_str!("../shaders/iterate_uniforms.wgsl"),
+                    include_str!("../shaders/mandelbrot.wgsl"),
+                )
+                .into(),
+            ),
         });
 
         let uniform_buffer = device.create_buffer(&wgpu::BufferDescriptor {
@@ -211,6 +218,19 @@ impl FractalRenderer {
                     },
                     count: None,
                 },
+                // Only read by the export pipeline's shadow branch (`fs_color`
+                // with the custom-lights palette); the iterate pipeline
+                // (`fs_data`) ignores it, but both pipelines share this layout.
+                wgpu::BindGroupLayoutEntry {
+                    binding: 2,
+                    visibility: wgpu::ShaderStages::FRAGMENT,
+                    ty: wgpu::BindingType::Buffer {
+                        ty: wgpu::BufferBindingType::Uniform,
+                        has_dynamic_offset: false,
+                        min_binding_size: None,
+                    },
+                    count: None,
+                },
             ],
         });
 
@@ -226,6 +246,10 @@ impl FractalRenderer {
                     binding: 1,
                     resource: ref_buffer.as_entire_binding(),
                 },
+                wgpu::BindGroupEntry {
+                    binding: 2,
+                    resource: lights_buffer.as_entire_binding(),
+                },
             ],
         });
 
@@ -292,7 +316,14 @@ impl FractalRenderer {
         // Colourise pass: data texture + colour uniforms → colour texture.
         let colorize_shader = device.create_shader_module(wgpu::ShaderModuleDescriptor {
             label: Some("colorize"),
-            source: wgpu::ShaderSource::Wgsl(include_str!("../shaders/colorize.wgsl").into()),
+            source: wgpu::ShaderSource::Wgsl(
+                concat!(
+                    include_str!("../shaders/common.wgsl"),
+                    include_str!("../shaders/iterate_uniforms.wgsl"),
+                    include_str!("../shaders/colorize.wgsl"),
+                )
+                .into(),
+            ),
         });
         let colorize_bind_group_layout =
             device.create_bind_group_layout(&wgpu::BindGroupLayoutDescriptor {
@@ -366,7 +397,13 @@ impl FractalRenderer {
         // Blit pipeline: samples the cache texture onto egui's surface.
         let blit_shader = device.create_shader_module(wgpu::ShaderModuleDescriptor {
             label: Some("blit"),
-            source: wgpu::ShaderSource::Wgsl(include_str!("../shaders/blit.wgsl").into()),
+            source: wgpu::ShaderSource::Wgsl(
+                concat!(
+                    include_str!("../shaders/common.wgsl"),
+                    include_str!("../shaders/blit.wgsl"),
+                )
+                .into(),
+            ),
         });
 
         let blit_bind_group_layout =
@@ -592,6 +629,7 @@ impl ExportRender {
         height: u32,
         uniforms: Uniforms,
         reference: &[[f32; 2]],
+        lights: &[Light],
     ) -> Self {
         let uniform_buffer = device.create_buffer(&wgpu::BufferDescriptor {
             label: Some("export uniforms"),
@@ -612,6 +650,19 @@ impl ExportRender {
             queue.write_buffer(&ref_buffer, 0, bytemuck::cast_slice(&reference[..count]));
         }
 
+        // Only read by the shadow branch's custom-lights palette; harmless
+        // (zeroed) for every other coloring mode.
+        let lights_buffer = device.create_buffer(&wgpu::BufferDescriptor {
+            label: Some("export lights"),
+            size: (MAX_LIGHT_COUNT * std::mem::size_of::<Light>()) as u64,
+            usage: wgpu::BufferUsages::UNIFORM | wgpu::BufferUsages::COPY_DST,
+            mapped_at_creation: false,
+        });
+        let mut light_bytes = [0u8; size_of::<Light>() * MAX_LIGHT_COUNT];
+        let n = lights.len().min(MAX_LIGHT_COUNT);
+        light_bytes[..n * size_of::<Light>()].copy_from_slice(bytemuck::cast_slice(&lights[..n]));
+        queue.write_buffer(&lights_buffer, 0, &light_bytes);
+
         let bind_group = device.create_bind_group(&wgpu::BindGroupDescriptor {
             label: Some("export bind group"),
             layout: bind_group_layout,
@@ -624,6 +675,10 @@ impl ExportRender {
                     binding: 1,
                     resource: ref_buffer.as_entire_binding(),
                 },
+                wgpu::BindGroupEntry {
+                    binding: 2,
+                    resource: lights_buffer.as_entire_binding(),
+                },
             ],
         });
 

src/headless.rs

@@ -48,6 +48,7 @@ pub fn run(cli: Cli) -> Result<(), String> {
         height,
         uniforms,
         app.reference_points(),
+        app.lights(),
     );
 
     eprintln!("rendering {width}×{height}…");

src/shaders/blit.wgsl

@@ -13,12 +13,7 @@ struct VsOut {
 
 @vertex
 fn vs_main(@builtin(vertex_index) idx: u32) -> VsOut {
-    var verts = array<vec2<f32>, 3>(
-        vec2<f32>(-1.0, -1.0),
-        vec2<f32>(3.0, -1.0),
-        vec2<f32>(-1.0, 3.0),
-    );
-    let p = verts[idx];
+    let p = fullscreen_triangle_pos(idx);
     var out: VsOut;
     out.pos = vec4<f32>(p, 0.0, 1.0);
     // Map NDC to texture UV. v is flipped so the cache's top row (rendered at

src/shaders/buddhabrot.wgsl

@@ -62,17 +62,6 @@ const PALETTE_NEBULA: u32 = 0u;
 const PALETTE_YELLOW: u32 = 1u;
 const PALETTE_GRAYSCALE: u32 = 2u;
 
-const KIND_MANDELBROT: u32 = 0u;
-const KIND_BURNING_SHIP: u32 = 1u;
-const KIND_TRICORN: u32 = 2u;
-const KIND_MULTIBROT: u32 = 3u;
-const KIND_CELTIC: u32 = 4u;
-const KIND_PERPENDICULAR: u32 = 5u;
-const KIND_BUFFALO: u32 = 6u;
-const KIND_PHOENIX: u32 = 7u;
-const KIND_LAMBDA: u32 = 8u;
-const KIND_COMPLEX_MULTIBROT: u32 = 9u;
-
 @group(0) @binding(0) var<uniform> u: Uniforms;
 // Compute pass: read-write atomic histogram (3 planes of width*height, R/G/B).
 @group(0) @binding(1) var<storage, read_write> histogram: array<atomic<u32>>;
@@ -93,10 +82,6 @@ fn rand01(seed: u32) -> f32 {
     return f32(hash_u32(seed)) * (1.0 / 4294967295.0);
 }
 
-fn cmul(a: vec2<f32>, b: vec2<f32>) -> vec2<f32> {
-    return vec2<f32>(a.x * b.x - a.y * b.y, a.x * b.y + a.y * b.x);
-}
-
 fn complex_pow(z: vec2<f32>, p: u32) -> vec2<f32> {
     var r = vec2<f32>(1.0, 0.0);
     for (var i: u32 = 0u; i < p; i = i + 1u) {
@@ -105,21 +90,6 @@ fn complex_pow(z: vec2<f32>, p: u32) -> vec2<f32> {
     return r;
 }
 
-// z^p for a complex exponent p, via the principal branch z^p = exp(p * ln z),
-// ln z = ln|z| + i*arg(z). z = 0 maps to 0 (the correct limit for the
-// Re(p) > 0 region the UI exposes; ln(0) would otherwise be -inf).
-fn cpow(z: vec2<f32>, p: vec2<f32>) -> vec2<f32> {
-    let r2 = dot(z, z);
-    if r2 < 1e-30 {
-        return vec2<f32>(0.0, 0.0);
-    }
-    let ln_r = 0.5 * log(r2);
-    let theta = atan2(z.y, z.x);
-    let mag = exp(p.x * ln_r - p.y * theta);
-    let ang = p.x * theta + p.y * ln_r;
-    return mag * vec2<f32>(cos(ang), sin(ang));
-}
-
 // One iteration step z_n -> z_{n+1} for the current kind. `zp` is the
 // previous iterate (z_{n-1}), used only by the Phoenix two-term recurrence.
 // Must match `FractalKind` in reference.rs (the direct, non-perturbative form
@@ -251,12 +221,7 @@ fn cs_main(@builtin(global_invocation_id) gid: vec3<u32>) {
 
 @vertex
 fn vs_main(@builtin(vertex_index) idx: u32) -> @builtin(position) vec4<f32> {
-    var verts = array<vec2<f32>, 3>(
-        vec2<f32>(-1.0, -1.0),
-        vec2<f32>(3.0, -1.0),
-        vec2<f32>(-1.0, 3.0),
-    );
-    return vec4<f32>(verts[idx], 0.0, 1.0);
+    return vec4<f32>(fullscreen_triangle_pos(idx), 0.0, 1.0);
 }
 
 @fragment

src/shaders/colorize.wgsl

@@ -10,148 +10,28 @@
 // at the fragment's integer pixel coordinate (nearest — iteration data must not
 // be linearly filtered across escape boundaries).
 
-// Must match `Uniforms` in mandelbrot.wgsl / the Rust `Uniforms` struct.
-struct Uniforms {
-    span: vec2<f32>,
-    max_iter: u32,
-    ref_len: u32,
-    color_offset: f32,
-    color_scale: f32,
-    bailout_sq: f32,
-    is_julia: u32,
-    palette_id: u32,
-    shadow_palette_id: u32,
-    aa_level: u32,
-    kind: u32,
-    power: u32,
-    dc_offset: vec2<f32>,
-    phoenix_p: vec2<f32>,
-    lambda_l: vec2<f32>,
-    complex_power: vec2<f32>,
-    de_coloring: u32,
-    shadow: u32,
-};
-
-struct Light {
-    azimuth: f32,
-    altitude: f32,
-    color: u32,
-    _pad: u32
-};
-
 @group(0) @binding(0) var<uniform> u: Uniforms;
 @group(0) @binding(1) var data_tex: texture_2d<f32>;
 @group(0) @binding(2) var<uniform> lights: array<Light, 16>;
 
-// Smooth cyclic palettes (Inigo Quilez cosine palettes). Must match the palette
-// in mandelbrot.wgsl.
-fn palette(id: u32, t: f32) -> vec3<f32> {
-    if id == 4u {
-        return vec3<f32>(t, t, t); // grayscale
-    }
-    let a = vec3<f32>(0.5, 0.5, 0.5);
-    let b = vec3<f32>(0.5, 0.5, 0.5);
-    var c = vec3<f32>(1.0, 1.0, 1.0);
-    var d = vec3<f32>(0.00, 0.10, 0.20); // 0: amber / blue
-    if id == 1u {
-        d = vec3<f32>(0.00, 0.33, 0.67); // rainbow
-    } else if id == 2u {
-        d = vec3<f32>(0.30, 0.20, 0.20); // warm ember
-    } else if id == 3u {
-        c = vec3<f32>(1.0, 1.0, 0.5);
-        d = vec3<f32>(0.80, 0.90, 0.30); // lime / magenta
-    }
-    return a + b * cos(6.28318530718 * (c * t + d));
-}
-
 @vertex
 fn vs_main(@builtin(vertex_index) idx: u32) -> @builtin(position) vec4<f32> {
-    var verts = array<vec2<f32>, 3>(
-        vec2<f32>(-1.0, -1.0),
-        vec2<f32>(3.0, -1.0),
-        vec2<f32>(-1.0, 3.0),
-    );
-    return vec4<f32>(verts[idx], 0.0, 1.0);
-}
-
-fn load(x: i32, y: i32) -> vec3<f32> {
-    let dist = textureLoad(data_tex, vec2<i32>(x, y), 0).g;
-    return vec3<f32>(f32(x), f32(y), dist);
-}
-
-fn compute_light(normal: vec3<f32>, light: vec3<f32>) -> vec3<f32> {
-    return vec3<f32>(max(0., dot(normal, normalize(light))));
-}
-
-fn uncharted2tonemap(x: vec3<f32>) -> vec3<f32> {
-    let A = 0.15; // Shoulder strength
-    let B = 0.50; // Linear strength
-    let C = 0.10; // Linear angle
-    let D = 0.20; // Toe strength
-    let E = 0.02; // Toe numerator / shoarder angle/etc.
-    let F = 0.30; // Toe denominator
-
-    return ((x * (A * x + C * B) + D * E) / (x * (A * x + B) + D * F)) - E / F;
-}
-
-fn filmic(color: vec3<f32>, white_point: f32) -> vec3<f32> {
-    let exposure_bias = 2.0;
-    let curr = uncharted2tonemap(color * exposure_bias);
-    
-    // Valeur blanche maximale de référence
-    let white_scale = vec3(1.0) / uncharted2tonemap(vec3(white_point));
-    return curr * white_scale;
-}
-
-fn s(color: vec3<f32>, k: f32, c: f32) -> vec3<f32> {
-    return 1. / (1. + exp(-k * (color - c)));
-}
-
-fn contrast(color: vec3<f32>, k: f32, c: f32) -> vec3<f32> {
-    let color_c = s(color, k, c);
-
-    return (color_c - s(vec3<f32>(0), k, c)) / (s(vec3<f32>(1), k, c) - s(vec3<f32>(0), k, c));
+    return vec4<f32>(fullscreen_triangle_pos(idx), 0.0, 1.0);
 }
 
 @fragment
 fn fs_main(@builtin(position) pos: vec4<f32>) -> @location(0) vec4<f32> {
     if u.shadow != 0u {
-        if textureLoad(data_tex, vec2<i32>(i32(pos.x), i32(pos.y)), 0).b != 0. {
+        let x = i32(pos.x);
+        let y = i32(pos.y);
+        if textureLoad(data_tex, vec2<i32>(x, y), 0).b != 0. {
             return vec4<f32>(0.1, 0.1, 0.1, 1.0);
         } else {
-            let d = array<vec3<f32>, 3>(load(i32(pos.x), i32(pos.y)), load(i32(pos.x + 1), i32(pos.y)), load(i32(pos.x), i32(pos.y + 1)));
-
-            let normal = normalize(cross(d[1] - d[0], d[2] - d[0]));
-
-            var color: vec3<f32>;
-            if u.shadow_palette_id == 0u {
-                color = compute_light(normal,vec3<f32>(.5, .5, .5)) + vec3<f32>(0.58, 0.85, 1.) * 0.2;
-
-                color = filmic(color, 2.5);
-                color = contrast(color, 4., 0.67);
-            } else if u.shadow_palette_id == 1u {
-                color = compute_light(normal, vec3<f32>(0., .5, .5)) * vec3<f32>(1., 0.5, 0.5) + compute_light(normal, vec3<f32>(0.5, 0., .5)) * vec3<f32>(0.5, 1., 1.);
-
-                color = filmic(color, 4.2);
-            } else {
-                color = vec3<f32>(0);
-                var light_count = 0;
-                for (var i = 0u ; i < 16; i++) {
-                    let light_color = unpack4x8unorm(lights[i].color);
-                    if any(light_color != vec4<f32>(0)) {
-                        light_count       += 1;
-                    }
-
-                    color       += compute_light(normal, vec3<f32>(
-                        cos(lights[i].azimuth) * cos(lights[i].altitude),
-                        sin(lights[i].azimuth) * cos(lights[i].altitude),
-                        sin(lights[i].altitude))) * light_color.xyz * light_color.a;
-                }
-
-                color = filmic(color, 1. + f32(light_count));
-            }
-
-            return vec4<f32>(color, 1.0);
+            let h0 = textureLoad(data_tex, vec2<i32>(x, y), 0).g;
+            let h1 = textureLoad(data_tex, vec2<i32>(x + 1, y), 0).g;
+            let h2 = textureLoad(data_tex, vec2<i32>(x, y + 1), 0).g;
+            let normal = normal_from_heights(h0, h1, h2);
+            return vec4<f32>(shadow_color(normal), 1.0);
         }
     } else {
         let d = textureLoad(data_tex, vec2<i32>(i32(pos.x), i32(pos.y)), 0);
@@ -159,8 +39,7 @@ fn fs_main(@builtin(position) pos: vec4<f32>) -> @location(0) vec4<f32> {
         let de = d.g;
         let interior_frac = d.b;
 
-        let t = fract(ci * u.color_scale + u.color_offset);
-        var col = palette(u.palette_id, t) * sqrt(de);
+        var col = classic_color(ci, de);
         // Anti-alias the set boundary: fade toward black by the fraction of the
         // pixel's sub-samples that landed in the interior.
         col = col * (1.0 - interior_frac);

src/shaders/common.wgsl

@@ -0,0 +1,51 @@
+// Shared helpers, concatenated into every shader at build time via
+// `concat!`/`include_str!` (see renderer.rs / buddhabrot.rs). Keep this file
+// free of anything that differs between pipelines (e.g. a `Uniforms` struct —
+// mandelbrot/colorize and buddhabrot each have their own shape) since every
+// shader gets the whole thing spliced in.
+
+// Fullscreen triangle vertex position: one triangle that covers the whole
+// viewport (cheaper than a quad's two), shared by every full-screen vertex
+// shader in this project.
+fn fullscreen_triangle_pos(idx: u32) -> vec2<f32> {
+    var verts = array<vec2<f32>, 3>(
+        vec2<f32>(-1.0, -1.0),
+        vec2<f32>(3.0, -1.0),
+        vec2<f32>(-1.0, 3.0),
+    );
+    return verts[idx];
+}
+
+// Complex multiply.
+fn cmul(a: vec2<f32>, b: vec2<f32>) -> vec2<f32> {
+    return vec2<f32>(a.x * b.x - a.y * b.y, a.x * b.y + a.y * b.x);
+}
+
+// z^p for a complex exponent p, via the principal branch z^p = exp(p * ln z),
+// ln z = ln|z| + i*arg(z). z = 0 maps to 0 (the correct limit for the
+// Re(p) > 0 region the UI exposes; ln(0) would otherwise be -inf).
+fn cpow(z: vec2<f32>, p: vec2<f32>) -> vec2<f32> {
+    let r2 = dot(z, z);
+    if r2 < 1e-30 {
+        return vec2<f32>(0.0, 0.0);
+    }
+    let ln_r = 0.5 * log(r2);
+    let theta = atan2(z.y, z.x);
+    let mag = exp(p.x * ln_r - p.y * theta);
+    let ang = p.x * theta + p.y * ln_r;
+    return mag * vec2<f32>(cos(ang), sin(ang));
+}
+
+// Iteration formula selector, shared by the perturbation (mandelbrot.wgsl)
+// and direct (buddhabrot.wgsl) iteration paths. Must match `FractalKind` in
+// reference.rs.
+const KIND_MANDELBROT: u32 = 0u;
+const KIND_BURNING_SHIP: u32 = 1u;
+const KIND_TRICORN: u32 = 2u;
+const KIND_MULTIBROT: u32 = 3u;
+const KIND_CELTIC: u32 = 4u;
+const KIND_PERPENDICULAR: u32 = 5u;
+const KIND_BUFFALO: u32 = 6u;
+const KIND_PHOENIX: u32 = 7u;
+const KIND_LAMBDA: u32 = 8u;
+const KIND_COMPLEX_MULTIBROT: u32 = 9u;

src/shaders/iterate_uniforms.wgsl

@@ -0,0 +1,161 @@
+// Shared by mandelbrot.wgsl (writes the per-pixel data texture) and
+// colorize.wgsl (reads it): the iteration pass and the colour remap pass
+// must agree on both the uniform layout and the palette function.
+
+// Must match the Rust `Uniforms` struct in renderer.rs field-for-field,
+// including padding.
+struct Uniforms {
+    span: vec2<f32>,
+    max_iter: u32,
+    ref_len: u32,
+    color_offset: f32,
+    color_scale: f32,
+    bailout_sq: f32,
+    is_julia: u32,
+    palette_id: u32,
+    shadow_palette_id: u32,
+    aa_level: u32,
+    // Iteration formula (see the KIND_* constants in common.wgsl).
+    kind: u32,
+    // Exponent for the Multibrot kind.
+    power: u32,
+    dc_offset: vec2<f32>,
+    // Distortion constant p for the Phoenix map (z^2 + c + p*z_{n-1}); unused
+    // by other kinds. Placed by dc_offset so both vec2s stay 8-byte aligned.
+    phoenix_p: vec2<f32>,
+    // Distortion constant l for the Lambda map (l*z(1 - z_{n-1})); unused
+    // by other kinds.
+    lambda_l: vec2<f32>,
+    // Complex exponent for the Complex Multibrot kind (z^power + c); unused
+    // by other kinds.
+    complex_power: vec2<f32>,
+    // 0 = escape-time coloring, 1 = distance-estimation shading.
+    de_coloring: u32,
+    // 0 = classic colors, 1 = shadows
+    shadow: u32,
+};
+
+// Smooth cyclic palettes (Inigo Quilez cosine palettes), selected by id.
+fn palette(id: u32, t: f32) -> vec3<f32> {
+    if id == 4u {
+        return vec3<f32>(t, t, t); // grayscale
+    }
+    let a = vec3<f32>(0.5, 0.5, 0.5);
+    let b = vec3<f32>(0.5, 0.5, 0.5);
+    var c = vec3<f32>(1.0, 1.0, 1.0);
+    var d = vec3<f32>(0.00, 0.10, 0.20); // 0: amber / blue
+    if id == 1u {
+        d = vec3<f32>(0.00, 0.33, 0.67); // rainbow
+    } else if id == 2u {
+        d = vec3<f32>(0.30, 0.20, 0.20); // warm ember
+    } else if id == 3u {
+        c = vec3<f32>(1.0, 1.0, 0.5);
+        d = vec3<f32>(0.80, 0.90, 0.30); // lime / magenta
+    }
+    return a + b * cos(6.28318530718 * (c * t + d));
+}
+
+// Classic (non-shadow) escape colouring: palette lookup at the smoothed
+// iteration count `ci`, darkened by the distance-estimate factor `de`
+// (sqrt-compressed so the darkening falls off more gently near the
+// boundary). Shared by the colourise pass's classic branch (colorize.wgsl,
+// applied to an already-averaged data texel) and the PNG-export pass
+// (mandelbrot.wgsl's `fs_color`, applied per sub-sample pre-AA) — the two
+// places a fully escaped point is turned into a final pixel colour.
+fn classic_color(ci: f32, de: f32) -> vec3<f32> {
+    let t = fract(ci * u.color_scale + u.color_offset);
+    return palette(u.palette_id, t) * sqrt(de);
+}
+
+// A single directional/point light, set by the UI's light list. `color`'s
+// alpha channel doubles as intensity (see `shadow_color`'s use of
+// `light_color.a`). Each shader that binds a `lights: array<Light, 16>`
+// uniform (colorize.wgsl, mandelbrot.wgsl's export shadow path) uses this
+// same layout.
+struct Light {
+    azimuth: f32,
+    altitude: f32,
+    color: u32,
+    _pad: u32,
+};
+
+fn compute_light(normal: vec3<f32>, light: vec3<f32>) -> vec3<f32> {
+    return vec3<f32>(max(0., dot(normal, normalize(light))));
+}
+
+fn uncharted2tonemap(x: vec3<f32>) -> vec3<f32> {
+    let A = 0.15; // Shoulder strength
+    let B = 0.50; // Linear strength
+    let C = 0.10; // Linear angle
+    let D = 0.20; // Toe strength
+    let E = 0.02; // Toe numerator / shoarder angle/etc.
+    let F = 0.30; // Toe denominator
+
+    return ((x * (A * x + C * B) + D * E) / (x * (A * x + B) + D * F)) - E / F;
+}
+
+fn filmic(color: vec3<f32>, white_point: f32) -> vec3<f32> {
+    let exposure_bias = 2.0;
+    let curr = uncharted2tonemap(color * exposure_bias);
+
+    // Valeur blanche maximale de référence
+    let white_scale = vec3(1.0) / uncharted2tonemap(vec3(white_point));
+    return curr * white_scale;
+}
+
+fn s(color: vec3<f32>, k: f32, c: f32) -> vec3<f32> {
+    return 1. / (1. + exp(-k * (color - c)));
+}
+
+fn contrast(color: vec3<f32>, k: f32, c: f32) -> vec3<f32> {
+    let color_c = s(color, k, c);
+
+    return (color_c - s(vec3<f32>(0), k, c)) / (s(vec3<f32>(1), k, c) - s(vec3<f32>(0), k, c));
+}
+
+// Surface normal from three height samples (`h0` at the pixel, `h1` one pixel
+// to the right, `h2` one pixel down), treating DE as a height field. Only the
+// differences matter, so callers don't need to pass pixel coordinates — a
+// texture-backed caller (colorize.wgsl) and a live-sampled caller
+// (mandelbrot.wgsl's export shadow path) can share this.
+fn normal_from_heights(h0: f32, h1: f32, h2: f32) -> vec3<f32> {
+    let d0 = vec3<f32>(0.0, 0.0, h0);
+    let d1 = vec3<f32>(1.0, 0.0, h1);
+    let d2 = vec3<f32>(0.0, 1.0, h2);
+    return normalize(cross(d1 - d0, d2 - d0));
+}
+
+// Shade a DE-derived surface normal per `u.shadow_palette_id`: 0 = grayscale
+// key light, 1 = red/blue two-tone, 2 = the user's custom `lights` list.
+// Shared by the interactive shadow pass (colorize.wgsl) and the PNG-export
+// shadow path (mandelbrot.wgsl's `fs_color`), which must render identically.
+fn shadow_color(normal: vec3<f32>) -> vec3<f32> {
+    var color: vec3<f32>;
+    if u.shadow_palette_id == 0u {
+        color = compute_light(normal, vec3<f32>(.5, .5, .5)) + vec3<f32>(0.58, 0.85, 1.) * 0.2;
+
+        color = filmic(color, 2.5);
+        color = contrast(color, 4., 0.67);
+    } else if u.shadow_palette_id == 1u {
+        color = compute_light(normal, vec3<f32>(0., .5, .5)) * vec3<f32>(1., 0.5, 0.5) + compute_light(normal, vec3<f32>(0.5, 0., .5)) * vec3<f32>(0.5, 1., 1.);
+
+        color = filmic(color, 4.2);
+    } else {
+        color = vec3<f32>(0);
+        var light_count = 0;
+        for (var i = 0u; i < 16; i++) {
+            let light_color = unpack4x8unorm(lights[i].color);
+            if any(light_color != vec4<f32>(0)) {
+                light_count += 1;
+            }
+
+            color += compute_light(normal, vec3<f32>(
+                cos(lights[i].azimuth) * cos(lights[i].altitude),
+                sin(lights[i].azimuth) * cos(lights[i].altitude),
+                sin(lights[i].altitude))) * light_color.xyz * light_color.a;
+        }
+
+        color = filmic(color, 1. + f32(light_count));
+    }
+    return color;
+}

src/shaders/mandelbrot.wgsl

@@ -12,50 +12,11 @@
 // the reference index to 0 and carry the full value as the new delta (valid
 // because X_0 = 0).
 
-struct Uniforms {
-    span: vec2<f32>,
-    max_iter: u32,
-    ref_len: u32,
-    color_offset: f32,
-    color_scale: f32,
-    bailout_sq: f32,
-    is_julia: u32,
-    palette_id: u32,
-    shadow_palette_id: u32,
-    aa_level: u32,
-    // Iteration formula (see the KIND_* constants below).
-    kind: u32,
-    // Exponent for the Multibrot kind.
-    power: u32,
-    dc_offset: vec2<f32>,
-    // Distortion constant p for the Phoenix map (z^2 + c + p*z_{n-1}); unused
-    // by other kinds. Placed by dc_offset so both vec2s stay 8-byte aligned.
-    phoenix_p: vec2<f32>,
-    // Distortion constant l for the Lambda map (l*z(1 - z_{n-1})); unused
-    // by other kinds.
-    lambda_l: vec2<f32>,
-    // Complex exponent for the Complex Multibrot kind (z^power + c); unused
-    // by other kinds.
-    complex_power: vec2<f32>,
-    // 0 = escape-time coloring, 1 = distance-estimation shading.
-    de_coloring: u32,
-    // 0 = classic colors, 1 = shadows
-    shadow: u32,
-};
-
-const KIND_MANDELBROT: u32 = 0u;
-const KIND_BURNING_SHIP: u32 = 1u;
-const KIND_TRICORN: u32 = 2u;
-const KIND_MULTIBROT: u32 = 3u;
-const KIND_CELTIC: u32 = 4u;
-const KIND_PERPENDICULAR: u32 = 5u;
-const KIND_BUFFALO: u32 = 6u;
-const KIND_PHOENIX: u32 = 7u;
-const KIND_LAMBDA: u32 = 8u;
-const KIND_COMPLEX_MULTIBROT: u32 = 9u;
-
 @group(0) @binding(0) var<uniform> u: Uniforms;
 @group(0) @binding(1) var<storage, read> ref_orbit: array<vec2<f32>>;
+// Only read by `fs_color`'s shadow branch (custom-lights palette); the
+// iteration pass (`fs_data`) never touches it.
+@group(0) @binding(2) var<uniform> lights: array<Light, 16>;
 
 struct VsOut {
     @builtin(position) pos: vec4<f32>,
@@ -65,12 +26,7 @@ struct VsOut {
 
 @vertex
 fn vs_main(@builtin(vertex_index) idx: u32) -> VsOut {
-    var verts = array<vec2<f32>, 3>(
-        vec2<f32>(-1.0, -1.0),
-        vec2<f32>(3.0, -1.0),
-        vec2<f32>(-1.0, 3.0),
-    );
-    let ndc = verts[idx];
+    let ndc = fullscreen_triangle_pos(idx);
     var out: VsOut;
     out.pos = vec4<f32>(ndc, 0.0, 1.0);
     // Flip y so +imaginary points up the screen.
@@ -78,11 +34,6 @@ fn vs_main(@builtin(vertex_index) idx: u32) -> VsOut {
     return out;
 }
 
-// Complex multiply.
-fn cmul(a: vec2<f32>, b: vec2<f32>) -> vec2<f32> {
-    return vec2<f32>(a.x * b.x - a.y * b.y, a.x * b.y + a.y * b.x);
-}
-
 // Complex conjugate.
 fn conj(a: vec2<f32>) -> vec2<f32> {
     return vec2<f32>(a.x, -a.y);
@@ -94,21 +45,6 @@ fn cdiv(a: vec2<f32>, b: vec2<f32>) -> vec2<f32> {
     return vec2<f32>(a.x * b.x + a.y * b.y, a.y * b.x - a.x * b.y) / d;
 }
 
-// z^p for a complex exponent p, via the principal branch z^p = exp(p * ln z),
-// ln z = ln|z| + i*arg(z). z = 0 maps to 0 (the correct limit for the
-// Re(p) > 0 region the UI exposes; ln(0) would otherwise be -inf).
-fn cpow(z: vec2<f32>, p: vec2<f32>) -> vec2<f32> {
-    let r2 = dot(z, z);
-    if r2 < 1e-30 {
-        return vec2<f32>(0.0, 0.0);
-    }
-    let ln_r = 0.5 * log(r2);
-    let theta = atan2(z.y, z.x);
-    let mag = exp(p.x * ln_r - p.y * theta);
-    let ang = p.x * theta + p.y * ln_r;
-    return mag * vec2<f32>(cos(ang), sin(ang));
-}
-
 // |c + d| - |c|, evaluated exactly (no catastrophic cancellation even when the
 // sum crosses zero). This is what makes the Burning Ship delta correct through
 // the sign flips that happen all along the axes, where the ship's detail lives.
@@ -156,18 +92,25 @@ fn multibrot_delta(z: vec2<f32>, e: vec2<f32>, p: u32) -> vec2<f32> {
 const COMPLEX_MULTIBROT_TERMS: u32 = 16u;
 
 // Perturbation delta for z -> z^p with a complex p: (Z+e)^p - Z^p.
-// = Z^p * ((1+w)^p - 1), w = e/Z, expanded as a Taylor series in w (never
-// forming 1+w, which would round tiny w away in f32 — the same reason
-// `multibrot_delta` never forms Z+e directly). Series: (1+w)^p - 1 =
-// sum_{k=1}^N C(p,k) w^k, with the complex binomial coefficient built up
-// incrementally: C(p,k) = C(p,k-1) * (p-(k-1)) / k.
 //
-// Z ~ 0 (the reference start, X_0 = 0 for Mandelbrot) makes w singular; there
-// (0+e)^p - 0^p = e^p exactly, so that case is handled directly via `cpow`.
+// When |e| << |Z| (the common case: it's the whole reason perturbation
+// works), forming Z+e directly would round e away in f32, so instead expand
+// = Z^p * ((1+w)^p - 1), w = e/Z, as a Taylor series in w: (1+w)^p - 1 =
+// sum_{k=1}^N C(p,k) w^k, with the complex binomial coefficient built up
+// incrementally: C(p,k) = C(p,k-1) * (p-(k-1)) / k. Unlike `multibrot_delta`
+// (a finite binomial sum for an integer power), this only *converges* — and
+// only for |w| < 1 — rather than terminating exactly.
+//
+// Right after a rebase (or near a reference point close to zero, where w is
+// singular), e is *not* small relative to Z — that's normal perturbation
+// dynamics, not a deep-zoom edge case — and the series above would diverge.
+// But forming Z+e directly is numerically safe exactly there (e isn't many
+// orders of magnitude smaller than Z), so fall back to a plain subtraction.
 fn complex_multibrot_delta(z: vec2<f32>, e: vec2<f32>, p: vec2<f32>) -> vec2<f32> {
-    if dot(z, z) < 1e-20 {
-        return cpow(e, p);
-    }
+    // |w|^2 = |e|^2 / |Z|^2; inf or nan (Z ~ 0, or both ~ 0) correctly fails
+    // the `< 0.25` test below and falls through to the direct branch.
+    let w2 = dot(e, e) / dot(z, z);
+    if w2 < 0.25 {
         let w = cdiv(e, z);
         var wk = vec2<f32>(1.0, 0.0); // w^0
         var coef = vec2<f32>(1.0, 0.0); // C(p,0)
@@ -178,6 +121,8 @@ fn complex_multibrot_delta(z: vec2<f32>, e: vec2<f32>, p: vec2<f32>) -> vec2<f32
             acc = acc + cmul(coef, wk);
         }
         return cmul(cpow(z, p), acc);
+    }
+    return cpow(z + e, p) - cpow(z, p);
 }
 
 // One perturbation step of the current fractal's delta: e -> f(Z+e) - f(Z),
@@ -249,26 +194,6 @@ fn fprime(z: vec2<f32>) -> vec2<f32> {
     return 2.0 * z;
 }
 
-// Smooth cyclic palettes (Inigo Quilez cosine palettes), selected by id.
-fn palette(id: u32, t: f32) -> vec3<f32> {
-    if id == 4u {
-        return vec3<f32>(t, t, t); // grayscale
-    }
-    let a = vec3<f32>(0.5, 0.5, 0.5);
-    let b = vec3<f32>(0.5, 0.5, 0.5);
-    var c = vec3<f32>(1.0, 1.0, 1.0);
-    var d = vec3<f32>(0.00, 0.10, 0.20); // 0: amber / blue
-    if id == 1u {
-        d = vec3<f32>(0.00, 0.33, 0.67); // rainbow
-    } else if id == 2u {
-        d = vec3<f32>(0.30, 0.20, 0.20); // warm ember
-    } else if id == 3u {
-        c = vec3<f32>(1.0, 1.0, 0.5);
-        d = vec3<f32>(0.80, 0.90, 0.30); // lime / magenta
-    }
-    return a + b * cos(6.28318530718 * (c * t + d));
-}
-
 // Escape data for one sample: `ci` is the (color-independent) palette parameter,
 // `de` the distance-estimate darkening factor in [0,1], `escaped` false for the
 // interior of the set. Splitting iteration from coloring lets a colour change be
@@ -407,22 +332,15 @@ fn color_sample(s: Sample) -> vec3<f32> {
     if !s.escaped {
         return vec3<f32>(0.0, 0.0, 0.0);
     }
-    let t = fract(s.ci * u.color_scale + u.color_offset);
-    return palette(u.palette_id, t) * s.de;
+    return classic_color(s.ci, s.de);
 }
 
-// Iteration pass: write per-pixel escape data (color-independent) so a colour
-// change is remapped by the cheap colourise pass without re-iterating.
-//   R = ci (palette parameter), G = DE factor, B = interior fraction (for AA).
-// AA is grid-supersampled here; the interior fraction lets the colourise pass
-// anti-alias the set boundary (blend toward black) after the fact.
-@fragment
-fn fs_data(in: VsOut) -> @location(0) vec4<f32> {
-    let base = in.centered * u.span + u.dc_offset;
-    let dx = dpdx(base);
-    let dy = dpdy(base);
-    let px = length(abs(dx) + abs(dy));
-
+// Supersampled escape data at one point: average (ci, DE factor) over the
+// AA grid's escaped sub-samples, plus the fraction that landed in the
+// interior. Shared by `fs_data` (writes it straight to the data texture) and
+// `fs_color`'s shadow branch (used both at the pixel and at its two
+// neighbours, to build a DE height field without a texture round-trip).
+fn aggregate_sample(base: vec2<f32>, dx: vec2<f32>, dy: vec2<f32>, px: f32) -> vec3<f32> {
     let aa = max(u.aa_level, 1u);
     let inv = 1.0 / f32(aa);
     var ci_sum = 0.0;
@@ -444,7 +362,22 @@ fn fs_data(in: VsOut) -> @location(0) vec4<f32> {
     let ci_avg = select(0.0, ci_sum / f32(escaped_n), escaped_n > 0u);
     let de_avg = select(1.0, de_sum / f32(escaped_n), escaped_n > 0u);
     let interior_frac = 1.0 - f32(escaped_n) / total;
-    return vec4<f32>(ci_avg, de_avg, interior_frac, 1.0);
+    return vec3<f32>(ci_avg, de_avg, interior_frac);
+}
+
+// Iteration pass: write per-pixel escape data (color-independent) so a colour
+// change is remapped by the cheap colourise pass without re-iterating.
+//   R = ci (palette parameter), G = DE factor, B = interior fraction (for AA).
+// AA is grid-supersampled here; the interior fraction lets the colourise pass
+// anti-alias the set boundary (blend toward black) after the fact.
+@fragment
+fn fs_data(in: VsOut) -> @location(0) vec4<f32> {
+    let base = in.centered * u.span + u.dc_offset;
+    let dx = dpdx(base);
+    let dy = dpdy(base);
+    let px = length(abs(dx) + abs(dy));
+
+    return vec4<f32>(aggregate_sample(base, dx, dy, px), 1.0);
 }
 
 // Combined iterate + colour in a single pass, for PNG export (which never needs
@@ -457,6 +390,21 @@ fn fs_color(in: VsOut) -> @location(0) vec4<f32> {
     let dy = dpdy(base);
     let px = length(abs(dx) + abs(dy));
 
+    if u.shadow != 0u {
+        // No data texture to sample neighbours from (this pass never runs
+        // one), so build the same DE height field colorize.wgsl reads from
+        // the texture by aggregating live, at the pixel and its two
+        // neighbours a `dx`/`dy` step away.
+        let here = aggregate_sample(base, dx, dy, px);
+        if here.z != 0.0 {
+            return vec4<f32>(0.1, 0.1, 0.1, 1.0);
+        }
+        let right = aggregate_sample(base + dx, dx, dy, px);
+        let down = aggregate_sample(base + dy, dx, dy, px);
+        let normal = normal_from_heights(here.y, right.y, down.y);
+        return vec4<f32>(shadow_color(normal), 1.0);
+    }
+
     let aa = max(u.aa_level, 1u);
     let inv = 1.0 / f32(aa);
     var acc = vec3<f32>(0.0, 0.0, 0.0);

tests/shader_valid.rs

@@ -21,24 +21,44 @@ fn validate(name: &str, src: &str) {
 fn mandelbrot_shader_is_valid() {
     validate(
         "mandelbrot.wgsl",
+        concat!(
+            include_str!("../src/shaders/common.wgsl"),
+            include_str!("../src/shaders/iterate_uniforms.wgsl"),
             include_str!("../src/shaders/mandelbrot.wgsl"),
+        ),
     );
 }
 
 #[test]
 fn colorize_shader_is_valid() {
-    validate("colorize.wgsl", include_str!("../src/shaders/colorize.wgsl"));
+    validate(
+        "colorize.wgsl",
+        concat!(
+            include_str!("../src/shaders/common.wgsl"),
+            include_str!("../src/shaders/iterate_uniforms.wgsl"),
+            include_str!("../src/shaders/colorize.wgsl"),
+        ),
+    );
 }
 
 #[test]
 fn blit_shader_is_valid() {
-    validate("blit.wgsl", include_str!("../src/shaders/blit.wgsl"));
+    validate(
+        "blit.wgsl",
+        concat!(
+            include_str!("../src/shaders/common.wgsl"),
+            include_str!("../src/shaders/blit.wgsl"),
+        ),
+    );
 }
 
 #[test]
 fn buddhabrot_shader_is_valid() {
     validate(
         "buddhabrot.wgsl",
+        concat!(
+            include_str!("../src/shaders/common.wgsl"),
             include_str!("../src/shaders/buddhabrot.wgsl"),
+        ),
     );
 }