#include "VoxelRenderer.h"
#include "wiPrimitive.h"
#include <algorithm>
#include <cmath>

using namespace wi::graphics;

namespace voxel {

// ── VoxelRenderer Implementation ────────────────────────────────

VoxelRenderer::VoxelRenderer() = default;
VoxelRenderer::~VoxelRenderer() { shutdown(); }

void VoxelRenderer::initialize(GraphicsDevice* dev) {
    device_ = dev;
    if (!device_) return;

    createPipeline();
    if (!pso_.IsValid()) {
        wi::backlog::post("VoxelRenderer: pipeline creation failed", wi::backlog::LogLevel::Error);
        initialized_ = false;
        return;
    }
    generateTextures();

    // Create mega quad buffer (SRV for vertex pulling)
    GPUBufferDesc megaDesc;
    megaDesc.size = MEGA_BUFFER_CAPACITY * sizeof(PackedQuad);
    megaDesc.bind_flags = BindFlag::SHADER_RESOURCE;
    megaDesc.misc_flags = ResourceMiscFlag::BUFFER_STRUCTURED;
    megaDesc.stride = sizeof(PackedQuad);
    megaDesc.usage = Usage::DEFAULT;
    device_->CreateBuffer(&megaDesc, nullptr, &megaQuadBuffer_);

    // Create chunk info buffer (SRV for VS chunk lookup)
    GPUBufferDesc infoDesc;
    infoDesc.size = MAX_CHUNKS * sizeof(GPUChunkInfo);
    infoDesc.bind_flags = BindFlag::SHADER_RESOURCE;
    infoDesc.misc_flags = ResourceMiscFlag::BUFFER_STRUCTURED;
    infoDesc.stride = sizeof(GPUChunkInfo);
    infoDesc.usage = Usage::DEFAULT;
    device_->CreateBuffer(&infoDesc, nullptr, &chunkInfoBuffer_);

    // Create indirect args buffer (for DrawInstancedIndirectCount, up to 6 draws per chunk)
    // UAV bind flag needed for GPU cull compute shader to write args
    GPUBufferDesc argsDesc;
    argsDesc.size = MAX_DRAWS * sizeof(IndirectDrawArgs);
    argsDesc.bind_flags = BindFlag::UNORDERED_ACCESS;
    argsDesc.misc_flags = ResourceMiscFlag::BUFFER_STRUCTURED | ResourceMiscFlag::INDIRECT_ARGS;
    argsDesc.stride = sizeof(IndirectDrawArgs);
    argsDesc.usage = Usage::DEFAULT;
    device_->CreateBuffer(&argsDesc, nullptr, &indirectArgsBuffer_);

    // Create draw count buffer (single uint32, raw for RWByteAddressBuffer)
    // UAV bind flag needed for GPU cull compute shader atomic counter
    GPUBufferDesc countDesc;
    countDesc.size = sizeof(uint32_t);
    countDesc.bind_flags = BindFlag::UNORDERED_ACCESS;
    countDesc.misc_flags = ResourceMiscFlag::BUFFER_RAW | ResourceMiscFlag::INDIRECT_ARGS;
    countDesc.usage = Usage::DEFAULT;
    device_->CreateBuffer(&countDesc, nullptr, &drawCountBuffer_);

    // ── GPU Timestamp Queries ──────────────────────────────────────
    GPUQueryHeapDesc queryDesc;
    queryDesc.type = GpuQueryType::TIMESTAMP;
    queryDesc.query_count = TS_COUNT;
    device_->CreateQueryHeap(&queryDesc, &timestampHeap_);

    GPUBufferDesc readbackDesc;
    readbackDesc.size = TS_COUNT * sizeof(uint64_t);
    readbackDesc.usage = Usage::READBACK;
    device_->CreateBuffer(&readbackDesc, nullptr, &timestampReadback_);

    // ── GPU Compute Mesher resources ─────────────────────────────
    wi::renderer::LoadShader(ShaderStage::CS, meshShader_, "voxel/voxelMeshCS.cso");
    gpuMesherAvailable_ = meshShader_.IsValid();
    if (gpuMesherAvailable_) {
        // Voxel data buffer: 1 chunk's worth (32^3 voxels / 2 per uint = 16384 uint)
        GPUBufferDesc voxDesc;
        voxDesc.size = (CHUNK_VOLUME / 2) * sizeof(uint32_t);
        voxDesc.bind_flags = BindFlag::SHADER_RESOURCE;
        voxDesc.misc_flags = ResourceMiscFlag::BUFFER_STRUCTURED;
        voxDesc.stride = sizeof(uint32_t);
        voxDesc.usage = Usage::DEFAULT;
        device_->CreateBuffer(&voxDesc, nullptr, &voxelDataBuffer_);

        // GPU quad output: same capacity as mega-buffer
        GPUBufferDesc gpuQDesc;
        gpuQDesc.size = MEGA_BUFFER_CAPACITY * sizeof(uint64_t); // PackedQuad = 8 bytes
        gpuQDesc.bind_flags = BindFlag::UNORDERED_ACCESS;
        gpuQDesc.misc_flags = ResourceMiscFlag::BUFFER_STRUCTURED;
        gpuQDesc.stride = sizeof(uint64_t); // uint2 = 8 bytes
        gpuQDesc.usage = Usage::DEFAULT;
        device_->CreateBuffer(&gpuQDesc, nullptr, &gpuQuadBuffer_);

        // Quad counter
        GPUBufferDesc cntDesc;
        cntDesc.size = sizeof(uint32_t);
        cntDesc.bind_flags = BindFlag::UNORDERED_ACCESS;
        cntDesc.misc_flags = ResourceMiscFlag::BUFFER_RAW;
        cntDesc.usage = Usage::DEFAULT;
        device_->CreateBuffer(&cntDesc, nullptr, &gpuQuadCounter_);

        wi::backlog::post("VoxelRenderer: GPU compute mesher available");
    } else {
        wi::backlog::post("VoxelRenderer: GPU compute mesher not available", wi::backlog::LogLevel::Warning);
    }

    cpuMegaQuads_.reserve(MEGA_BUFFER_CAPACITY);
    cpuChunkInfo_.reserve(MAX_CHUNKS);
    chunkSlots_.reserve(MAX_CHUNKS);
    cpuIndirectArgs_.reserve(MAX_CHUNKS);

    initialized_ = true;
    wi::backlog::post("VoxelRenderer: initialized (mega-buffer: "
        + std::to_string(MEGA_BUFFER_CAPACITY) + " quads capacity)");
}

void VoxelRenderer::shutdown() {
    chunkSlots_.clear();
    cpuChunkInfo_.clear();
    cpuMegaQuads_.clear();
    initialized_ = false;
}

void VoxelRenderer::createPipeline() {
    // Constant buffer for per-frame data
    GPUBufferDesc cbDesc;
    cbDesc.size = sizeof(VoxelConstants);
    cbDesc.bind_flags = BindFlag::CONSTANT_BUFFER;
    cbDesc.usage = Usage::DEFAULT;
    device_->CreateBuffer(&cbDesc, nullptr, &constantBuffer_);

    // Anisotropic wrap sampler
    SamplerDesc samplerDesc;
    samplerDesc.filter = Filter::ANISOTROPIC;
    samplerDesc.address_u = TextureAddressMode::WRAP;
    samplerDesc.address_v = TextureAddressMode::WRAP;
    samplerDesc.address_w = TextureAddressMode::WRAP;
    samplerDesc.max_anisotropy = 16;
    device_->CreateSampler(&samplerDesc, &sampler_);

    // Load shaders
    wi::renderer::LoadShader(ShaderStage::VS, vertexShader_, "voxel/voxelVS.cso");
    wi::renderer::LoadShader(ShaderStage::PS, pixelShader_, "voxel/voxelPS.cso");
    wi::renderer::LoadShader(ShaderStage::CS, cullShader_, "voxel/voxelCullCS.cso");

    if (!vertexShader_.IsValid() || !pixelShader_.IsValid()) {
        wi::backlog::post("VoxelRenderer: shader loading failed", wi::backlog::LogLevel::Error);
        return;
    }
    // GPU cull shader loads but MDI path is disabled pending barrier debugging.
    // CPU fallback with per-face-group DrawInstanced + backface culling is used instead.
    gpuCullingEnabled_ = false;
    if (cullShader_.IsValid()) {
        wi::backlog::post("VoxelRenderer: cull compute shader compiled (GPU cull path disabled, using CPU fallback)");
    } else {
        wi::backlog::post("VoxelRenderer: cull compute shader not available", wi::backlog::LogLevel::Warning);
    }

    // Pipeline: backface cull, depth test, opaque blend, triangle list
    PipelineStateDesc psoDesc;
    psoDesc.vs = &vertexShader_;
    psoDesc.ps = &pixelShader_;
    psoDesc.rs = wi::renderer::GetRasterizerState(wi::enums::RSTYPE_FRONT);
    psoDesc.dss = wi::renderer::GetDepthStencilState(wi::enums::DSSTYPE_DEFAULT);
    psoDesc.bs = wi::renderer::GetBlendState(wi::enums::BSTYPE_OPAQUE);
    psoDesc.pt = PrimitiveTopology::TRIANGLELIST;

    device_->CreatePipelineState(&psoDesc, &pso_);
}

// ── Procedural texture generation ───────────────────────────────

static void generateNoiseTexture(uint8_t* pixels, int w, int h,
    uint8_t r0, uint8_t g0, uint8_t b0,
    uint8_t r1, uint8_t g1, uint8_t b1,
    uint32_t seed)
{
    uint32_t s = seed;
    for (int y = 0; y < h; y++) {
        for (int x = 0; x < w; x++) {
            s = s * 1664525u + 1013904223u;
            float noise = (float)(s & 0xFFFF) / 65535.0f;
            float fx = (float)x / w;
            float fy = (float)y / h;
            float pattern = 0.5f + 0.5f * std::sin(fx * 20.0f + noise * 3.0f) *
                            std::cos(fy * 20.0f + noise * 3.0f);
            float t = noise * 0.6f + pattern * 0.4f;

            int idx = (y * w + x) * 4;
            pixels[idx + 0] = (uint8_t)(r0 + (r1 - r0) * t);
            pixels[idx + 1] = (uint8_t)(g0 + (g1 - g0) * t);
            pixels[idx + 2] = (uint8_t)(b0 + (b1 - b0) * t);
            pixels[idx + 3] = 255;
        }
    }
}

void VoxelRenderer::generateTextures() {
    const int TEX_SIZE = 256;
    const int NUM_MATERIALS = 5;

    std::vector<uint8_t> allPixels(TEX_SIZE * TEX_SIZE * 4 * NUM_MATERIALS);

    struct MatColor { uint8_t r0,g0,b0, r1,g1,b1; uint32_t seed; };
    MatColor colors[NUM_MATERIALS] = {
        { 60, 140, 40,   80, 180, 60,  101 },  // Grass
        { 100, 70, 40,  140, 100, 60,  202 },  // Dirt
        { 110, 110, 105, 140, 140, 130, 303 },  // Stone
        { 200, 190, 140, 230, 220, 170, 404 },  // Sand
        { 220, 225, 230, 245, 248, 252, 505 },  // Snow
    };

    for (int i = 0; i < NUM_MATERIALS; i++) {
        auto& c = colors[i];
        generateNoiseTexture(
            allPixels.data() + i * TEX_SIZE * TEX_SIZE * 4,
            TEX_SIZE, TEX_SIZE,
            c.r0, c.g0, c.b0, c.r1, c.g1, c.b1, c.seed
        );
    }

    TextureDesc texDesc;
    texDesc.type = TextureDesc::Type::TEXTURE_2D;
    texDesc.width = TEX_SIZE;
    texDesc.height = TEX_SIZE;
    texDesc.array_size = NUM_MATERIALS;
    texDesc.mip_levels = 1;
    texDesc.format = Format::R8G8B8A8_UNORM;
    texDesc.bind_flags = BindFlag::SHADER_RESOURCE;
    texDesc.usage = Usage::DEFAULT;

    std::vector<SubresourceData> subData(NUM_MATERIALS);
    for (int i = 0; i < NUM_MATERIALS; i++) {
        subData[i].data_ptr = allPixels.data() + i * TEX_SIZE * TEX_SIZE * 4;
        subData[i].row_pitch = TEX_SIZE * 4;
        subData[i].slice_pitch = TEX_SIZE * TEX_SIZE * 4;
    }

    device_->CreateTexture(&texDesc, subData.data(), &textureArray_);
}

// ── Mega-buffer rebuild ─────────────────────────────────────────
// Packs all chunk quads contiguously into a single buffer.
// Simple strategy: full rebuild whenever any chunk is dirty.

void VoxelRenderer::rebuildMegaBuffer(VoxelWorld& world) {
    cpuMegaQuads_.clear();
    chunkSlots_.clear();
    cpuChunkInfo_.clear();

    uint32_t offset = 0;
    float debugFlag = debugFaceColors_ ? 1.0f : 0.0f;

    world.forEachChunk([&](const ChunkPos& pos, Chunk& chunk) {
        if (chunk.quadCount == 0) return;
        if (offset + chunk.quadCount > MEGA_BUFFER_CAPACITY) return; // overflow guard

        ChunkSlot slot;
        slot.pos = pos;
        slot.quadOffset = offset;
        slot.quadCount = chunk.quadCount;
        chunkSlots_.push_back(slot);

        GPUChunkInfo info = {};
        info.worldPos = XMFLOAT4(
            (float)(pos.x * CHUNK_SIZE),
            (float)(pos.y * CHUNK_SIZE),
            (float)(pos.z * CHUNK_SIZE),
            debugFlag
        );
        info.quadOffset = offset;
        info.quadCount = chunk.quadCount;
        for (int f = 0; f < 6; f++) {
            info.faceOffsets[f] = chunk.faceOffsets[f];
            info.faceCounts[f] = chunk.faceCounts[f];
        }
        cpuChunkInfo_.push_back(info);

        cpuMegaQuads_.insert(cpuMegaQuads_.end(), chunk.quads.begin(), chunk.quads.end());
        offset += chunk.quadCount;
    });

    chunkCount_ = (uint32_t)chunkSlots_.size();
    totalQuads_ = offset;
}

void VoxelRenderer::updateMeshes(VoxelWorld& world) {
    if (!device_) return;

    // Re-mesh dirty chunks
    bool anyDirty = false;
    world.forEachChunk([&](const ChunkPos& pos, Chunk& chunk) {
        if (chunk.dirty) {
            VoxelMesher::meshChunk(chunk, world);
            anyDirty = true;
        }
    });

    if (anyDirty || megaBufferDirty_) {
        rebuildMegaBuffer(world);
        megaBufferDirty_ = false;
    }
}

// ── Frustum plane extraction (Gribb-Hartmann method) ────────────
static void extractFrustumPlanes(const XMMATRIX& vp, XMFLOAT4 planes[6]) {
    XMFLOAT4X4 m;
    XMStoreFloat4x4(&m, vp);

    // Left
    planes[0] = XMFLOAT4(m._14 + m._11, m._24 + m._21, m._34 + m._31, m._44 + m._41);
    // Right
    planes[1] = XMFLOAT4(m._14 - m._11, m._24 - m._21, m._34 - m._31, m._44 - m._41);
    // Bottom
    planes[2] = XMFLOAT4(m._14 + m._12, m._24 + m._22, m._34 + m._32, m._44 + m._42);
    // Top
    planes[3] = XMFLOAT4(m._14 - m._12, m._24 - m._22, m._34 - m._32, m._44 - m._42);
    // Near
    planes[4] = XMFLOAT4(m._13, m._23, m._33, m._43);
    // Far
    planes[5] = XMFLOAT4(m._14 - m._13, m._24 - m._23, m._34 - m._33, m._44 - m._43);

    // Normalize each plane
    for (int i = 0; i < 6; i++) {
        float len = std::sqrt(planes[i].x * planes[i].x +
                              planes[i].y * planes[i].y +
                              planes[i].z * planes[i].z);
        if (len > 0.0001f) {
            planes[i].x /= len;
            planes[i].y /= len;
            planes[i].z /= len;
            planes[i].w /= len;
        }
    }
}

// ── Render pass ─────────────────────────────────────────────────

void VoxelRenderer::render(
    CommandList cmd,
    const wi::scene::CameraComponent& camera,
    const Texture& depthBuffer,
    const Texture& renderTarget
) const {
    if (!initialized_ || chunkCount_ == 0 || !pso_.IsValid()) return;

    auto* dev = device_;

    // Upload mega-buffer and chunk info to GPU
    if (!cpuMegaQuads_.empty()) {
        dev->UpdateBuffer(&megaQuadBuffer_, cpuMegaQuads_.data(), cmd,
            cpuMegaQuads_.size() * sizeof(PackedQuad));
    }
    if (!cpuChunkInfo_.empty()) {
        dev->UpdateBuffer(&chunkInfoBuffer_, cpuChunkInfo_.data(), cmd,
            cpuChunkInfo_.size() * sizeof(GPUChunkInfo));
    }

    // Per-frame constants (with frustum planes for GPU cull shader)
    VoxelConstants cb = {};
    XMMATRIX vpMatrix = camera.GetViewProjection();
    XMStoreFloat4x4(&cb.viewProjection, vpMatrix);
    cb.cameraPosition = XMFLOAT4(camera.Eye.x, camera.Eye.y, camera.Eye.z, 1.0f);
    cb.sunDirection = XMFLOAT4(-0.5f, -0.8f, -0.3f, 0.0f);
    cb.sunColor = XMFLOAT4(1.2f, 1.1f, 0.9f, 1.0f);
    cb.chunkSize = (float)CHUNK_SIZE;
    cb.textureTiling = 0.25f;
    cb.chunkCount = chunkCount_;
    extractFrustumPlanes(vpMatrix, cb.frustumPlanes);
    dev->UpdateBuffer(&constantBuffer_, &cb, cmd, sizeof(cb));

    // Push constant structure (must be 48 bytes = 12 x uint32, matches b999)
    struct VoxelPush {
        uint32_t chunkIndex;
        uint32_t quadOffset;
        uint32_t flags;       // bit 0: 1=MDI mode, 0=CPU mode
        uint32_t pad[9];
    };

    visibleChunks_ = 0;
    drawCalls_ = 0;

    // ── GPU Cull + MDI path ────────────────────────────────────────
    if (gpuCullingEnabled_) {
        // Zero the draw count buffer (sets state to COPY_DST)
        uint32_t zero = 0;
        dev->UpdateBuffer(&drawCountBuffer_, &zero, cmd, sizeof(uint32_t));
        // Touch indirect args buffer to establish COPY_DST state
        dev->UpdateBuffer(&indirectArgsBuffer_, &zero, cmd, sizeof(uint32_t));

        // Barriers: COPY_DST → UAV for compute shader writes
        GPUBarrier preBarriers[] = {
            GPUBarrier::Buffer(&drawCountBuffer_, ResourceState::COPY_DST, ResourceState::UNORDERED_ACCESS),
            GPUBarrier::Buffer(&indirectArgsBuffer_, ResourceState::COPY_DST, ResourceState::UNORDERED_ACCESS),
        };
        dev->Barrier(preBarriers, 2, cmd);

        // Timestamp: cull begin
        dev->QueryEnd(&timestampHeap_, TS_CULL_BEGIN, cmd);

        // Dispatch GPU frustum + backface cull compute shader
        dev->BindComputeShader(&cullShader_, cmd);
        dev->BindConstantBuffer(&constantBuffer_, 0, cmd);
        dev->BindResource(&chunkInfoBuffer_, 2, cmd);
        dev->BindUAV(&indirectArgsBuffer_, 0, cmd);
        dev->BindUAV(&drawCountBuffer_, 1, cmd);
        dev->Dispatch((chunkCount_ + 63) / 64, 1, 1, cmd);

        // Timestamp: cull end
        dev->QueryEnd(&timestampHeap_, TS_CULL_END, cmd);

        // Barriers: UAV → INDIRECT_ARGUMENT for DrawInstancedIndirectCount
        GPUBarrier postBarriers[] = {
            GPUBarrier::Buffer(&indirectArgsBuffer_, ResourceState::UNORDERED_ACCESS, ResourceState::INDIRECT_ARGUMENT),
            GPUBarrier::Buffer(&drawCountBuffer_, ResourceState::UNORDERED_ACCESS, ResourceState::INDIRECT_ARGUMENT),
        };
        dev->Barrier(postBarriers, 2, cmd);

        // Set MDI flag in push constants (VS uses binary search for chunk index)
        VoxelPush pushData = {};
        pushData.flags = 1; // MDI mode
        dev->PushConstants(&pushData, sizeof(pushData), cmd);

        // ── Render pass ────────────────────────────────────────────
        RenderPassImage rp[] = {
            RenderPassImage::RenderTarget(
                &renderTarget,
                RenderPassImage::LoadOp::CLEAR,
                RenderPassImage::StoreOp::STORE,
                ResourceState::SHADER_RESOURCE,
                ResourceState::SHADER_RESOURCE
            ),
            RenderPassImage::DepthStencil(
                &depthBuffer,
                RenderPassImage::LoadOp::CLEAR,
                RenderPassImage::StoreOp::STORE,
                ResourceState::DEPTHSTENCIL,
                ResourceState::DEPTHSTENCIL,
                ResourceState::DEPTHSTENCIL
            ),
        };
        dev->RenderPassBegin(rp, 2, cmd);

        Viewport vp;
        vp.width = (float)renderTarget.GetDesc().width;
        vp.height = (float)renderTarget.GetDesc().height;
        vp.min_depth = 0.0f;
        vp.max_depth = 1.0f;
        dev->BindViewports(1, &vp, cmd);

        Rect scissor = { 0, 0, (int)vp.width, (int)vp.height };
        dev->BindScissorRects(1, &scissor, cmd);

        dev->BindPipelineState(&pso_, cmd);
        dev->BindConstantBuffer(&constantBuffer_, 0, cmd);
        dev->BindResource(&megaQuadBuffer_, 0, cmd);
        dev->BindResource(&textureArray_, 1, cmd);
        dev->BindResource(&chunkInfoBuffer_, 2, cmd);
        dev->BindSampler(&sampler_, 0, cmd);

        // Timestamp: draw begin
        dev->QueryEnd(&timestampHeap_, TS_DRAW_BEGIN, cmd);

        // Single MDI call: GPU cull shader filled the indirect args
        dev->DrawInstancedIndirectCount(
            &indirectArgsBuffer_, 0,
            &drawCountBuffer_, 0,
            MAX_DRAWS, cmd
        );
        drawCalls_ = 1;

        // Timestamp: draw end
        dev->QueryEnd(&timestampHeap_, TS_DRAW_END, cmd);

        dev->RenderPassEnd(cmd);

        // Resolve timestamps for readback (results available next frame)
        dev->QueryResolve(&timestampHeap_, 0, TS_COUNT, &timestampReadback_, 0, cmd);

        // Read back previous frame's timestamps (persistently mapped READBACK buffer)
        uint64_t* tsData = (uint64_t*)timestampReadback_.mapped_data;
        if (tsData) {
            double freq = (double)dev->GetTimestampFrequency();
            if (freq > 0.0 && tsData[TS_CULL_END] > tsData[TS_CULL_BEGIN]) {
                gpuCullTimeMs_ = (float)((double)(tsData[TS_CULL_END] - tsData[TS_CULL_BEGIN]) / freq * 1000.0);
            }
            if (freq > 0.0 && tsData[TS_DRAW_END] > tsData[TS_DRAW_BEGIN]) {
                gpuDrawTimeMs_ = (float)((double)(tsData[TS_DRAW_END] - tsData[TS_DRAW_BEGIN]) / freq * 1000.0);
            }
        }

        // GPU cull handles visibility counting — approximate from chunkCount
        visibleChunks_ = chunkCount_; // exact count would require readback of drawCount

        return;
    }

    // ── CPU frustum + backface cull (shared by MDI and per-face paths) ──
    wi::primitive::Frustum frustum;
    frustum.Create(camera.GetViewProjection());

    // ── Phase 2.2: CPU-filled indirect args + MDI draw ──────────────
    if (mdiEnabled_) {
        // CPU cull: fill indirect args with visible face groups
        cpuIndirectArgs_.clear();
        uint32_t cpuDrawCount = 0;

        for (uint32_t i = 0; i < chunkCount_; i++) {
            const auto& slot = chunkSlots_[i];
            if (slot.quadCount == 0) continue;

            XMFLOAT3 aabbMin(
                (float)(slot.pos.x * CHUNK_SIZE),
                (float)(slot.pos.y * CHUNK_SIZE),
                (float)(slot.pos.z * CHUNK_SIZE)
            );
            XMFLOAT3 aabbMax(
                aabbMin.x + CHUNK_SIZE,
                aabbMin.y + CHUNK_SIZE,
                aabbMin.z + CHUNK_SIZE
            );
            wi::primitive::AABB aabb(aabbMin, aabbMax);
            if (!frustum.CheckBoxFast(aabb)) continue;

            visibleChunks_++;
            const auto& info = cpuChunkInfo_[i];

            for (uint32_t f = 0; f < 6; f++) {
                if (info.faceCounts[f] == 0) continue;

                bool backFacing = false;
                switch (f) {
                case 0: backFacing = (camera.Eye.x < aabbMin.x); break;
                case 1: backFacing = (camera.Eye.x > aabbMax.x); break;
                case 2: backFacing = (camera.Eye.y < aabbMin.y); break;
                case 3: backFacing = (camera.Eye.y > aabbMax.y); break;
                case 4: backFacing = (camera.Eye.z < aabbMin.z); break;
                case 5: backFacing = (camera.Eye.z > aabbMax.z); break;
                }
                if (backFacing) continue;

                IndirectDrawArgs args = {};
                // Pack chunkIndex (low 16 bits) + faceIndex (high 16 bits) into push constant.
                // The shader unpacks this to look up quadOffset from GPUChunkInfo.
                // We do NOT use startVertexLocation because SV_VertexID may not include it
                // reliably in ExecuteIndirect context.
                args.pushConstant = i | (f << 16);
                args.vertexCountPerInstance = info.faceCounts[f] * 6;
                args.instanceCount = 1;
                args.startVertexLocation = 0;
                args.startInstanceLocation = 0;
                cpuIndirectArgs_.push_back(args);
                cpuDrawCount++;
            }
        }

        // Upload indirect args and draw count to GPU
        // Note: no explicit barriers needed here. Buffers start in COMMON each frame
        // (DX12 buffer decay after command list execution). COMMON is implicitly
        // promoted to COPY_DST by UpdateBuffer, then to INDIRECT_ARGUMENT by
        // DrawInstancedIndirectCount. This matches Phase 2.1 pattern (no barriers
        // between UpdateBuffer and SRV usage for megaQuadBuffer_/chunkInfoBuffer_).
        if (!cpuIndirectArgs_.empty()) {
            dev->UpdateBuffer(&indirectArgsBuffer_, cpuIndirectArgs_.data(), cmd,
                cpuIndirectArgs_.size() * sizeof(IndirectDrawArgs));
        }
        dev->UpdateBuffer(&drawCountBuffer_, &cpuDrawCount, cmd, sizeof(uint32_t));

        // ── Render pass ────────────────────────────────────────────
        RenderPassImage rp[] = {
            RenderPassImage::RenderTarget(
                &renderTarget,
                RenderPassImage::LoadOp::CLEAR,
                RenderPassImage::StoreOp::STORE,
                ResourceState::SHADER_RESOURCE,
                ResourceState::SHADER_RESOURCE
            ),
            RenderPassImage::DepthStencil(
                &depthBuffer,
                RenderPassImage::LoadOp::CLEAR,
                RenderPassImage::StoreOp::STORE,
                ResourceState::DEPTHSTENCIL,
                ResourceState::DEPTHSTENCIL,
                ResourceState::DEPTHSTENCIL
            ),
        };
        dev->RenderPassBegin(rp, 2, cmd);

        Viewport vp;
        vp.width = (float)renderTarget.GetDesc().width;
        vp.height = (float)renderTarget.GetDesc().height;
        vp.min_depth = 0.0f;
        vp.max_depth = 1.0f;
        dev->BindViewports(1, &vp, cmd);

        Rect scissor = { 0, 0, (int)vp.width, (int)vp.height };
        dev->BindScissorRects(1, &scissor, cmd);

        dev->BindPipelineState(&pso_, cmd);
        dev->BindConstantBuffer(&constantBuffer_, 0, cmd);
        dev->BindResource(&megaQuadBuffer_, 0, cmd);
        dev->BindResource(&textureArray_, 1, cmd);
        dev->BindResource(&chunkInfoBuffer_, 2, cmd);
        dev->BindSampler(&sampler_, 0, cmd);

        // MDI mode: VS uses binary search to find chunk from SV_VertexID
        VoxelPush pushData = {};
        pushData.flags = 1; // MDI mode
        dev->PushConstants(&pushData, sizeof(pushData), cmd);

        dev->DrawInstancedIndirectCount(
            &indirectArgsBuffer_, 0,
            &drawCountBuffer_, 0,
            MAX_DRAWS, cmd
        );
        drawCalls_ = 1;

        dev->RenderPassEnd(cmd);
        return;
    }

    // ── Phase 2.1 Fallback: per-face-group DrawInstanced ────────────
    RenderPassImage rp[] = {
        RenderPassImage::RenderTarget(
            &renderTarget,
            RenderPassImage::LoadOp::CLEAR,
            RenderPassImage::StoreOp::STORE,
            ResourceState::SHADER_RESOURCE,
            ResourceState::SHADER_RESOURCE
        ),
        RenderPassImage::DepthStencil(
            &depthBuffer,
            RenderPassImage::LoadOp::CLEAR,
            RenderPassImage::StoreOp::STORE,
            ResourceState::DEPTHSTENCIL,
            ResourceState::DEPTHSTENCIL,
            ResourceState::DEPTHSTENCIL
        ),
    };
    dev->RenderPassBegin(rp, 2, cmd);

    Viewport vp;
    vp.width = (float)renderTarget.GetDesc().width;
    vp.height = (float)renderTarget.GetDesc().height;
    vp.min_depth = 0.0f;
    vp.max_depth = 1.0f;
    dev->BindViewports(1, &vp, cmd);

    Rect scissor = { 0, 0, (int)vp.width, (int)vp.height };
    dev->BindScissorRects(1, &scissor, cmd);

    dev->BindPipelineState(&pso_, cmd);
    dev->BindConstantBuffer(&constantBuffer_, 0, cmd);
    dev->BindResource(&megaQuadBuffer_, 0, cmd);
    dev->BindResource(&textureArray_, 1, cmd);
    dev->BindResource(&chunkInfoBuffer_, 2, cmd);
    dev->BindSampler(&sampler_, 0, cmd);

    for (uint32_t i = 0; i < chunkCount_; i++) {
        const auto& slot = chunkSlots_[i];
        if (slot.quadCount == 0) continue;

        XMFLOAT3 aabbMin(
            (float)(slot.pos.x * CHUNK_SIZE),
            (float)(slot.pos.y * CHUNK_SIZE),
            (float)(slot.pos.z * CHUNK_SIZE)
        );
        XMFLOAT3 aabbMax(
            aabbMin.x + CHUNK_SIZE,
            aabbMin.y + CHUNK_SIZE,
            aabbMin.z + CHUNK_SIZE
        );
        wi::primitive::AABB aabb(aabbMin, aabbMax);
        if (!frustum.CheckBoxFast(aabb)) continue;

        visibleChunks_++;
        const auto& info = cpuChunkInfo_[i];

        for (uint32_t f = 0; f < 6; f++) {
            if (info.faceCounts[f] == 0) continue;

            bool backFacing = false;
            switch (f) {
            case 0: backFacing = (camera.Eye.x < aabbMin.x); break;
            case 1: backFacing = (camera.Eye.x > aabbMax.x); break;
            case 2: backFacing = (camera.Eye.y < aabbMin.y); break;
            case 3: backFacing = (camera.Eye.y > aabbMax.y); break;
            case 4: backFacing = (camera.Eye.z < aabbMin.z); break;
            case 5: backFacing = (camera.Eye.z > aabbMax.z); break;
            }
            if (backFacing) continue;

            VoxelPush pushData = {};
            pushData.chunkIndex = i;
            pushData.quadOffset = slot.quadOffset + info.faceOffsets[f];
            pushData.flags = 0; // CPU mode
            dev->PushConstants(&pushData, sizeof(pushData), cmd);

            dev->DrawInstanced(info.faceCounts[f] * 6, 1, 0, 0, cmd);
            drawCalls_++;
        }
    }

    dev->RenderPassEnd(cmd);
}

// ── VoxelRenderPath (custom RenderPath3D) ───────────────────────

void VoxelRenderPath::Start() {
    RenderPath3D::Start();

    auto* device = wi::graphics::GetDevice();
    renderer.initialize(device);
    renderer.debugFaceColors_ = debugMode;

    // Generate world
    if (debugMode) {
        world.generateDebug();
        cameraPos = { 10.0f, 10.0f, 0.0f };
        cameraPitch = -0.4f;
        cameraYaw = 0.5f;
    } else {
        world.generateAround(cameraPos.x, cameraPos.y, cameraPos.z, 4);
    }
    if (renderer.isInitialized()) {
        renderer.updateMeshes(world);
    }
    worldGenerated_ = true;

    setAO(AO_DISABLED);
    setFXAAEnabled(true);
    setBloomEnabled(false);

    createRenderTargets();
}

void VoxelRenderPath::createRenderTargets() {
    auto* device = wi::graphics::GetDevice();
    if (!device) return;

    uint32_t w = GetPhysicalWidth();
    uint32_t h = GetPhysicalHeight();
    if (w == 0 || h == 0) { w = 1920; h = 1080; }

    wi::graphics::TextureDesc rtDesc;
    rtDesc.type = wi::graphics::TextureDesc::Type::TEXTURE_2D;
    rtDesc.width = w;
    rtDesc.height = h;
    rtDesc.format = wi::graphics::Format::R8G8B8A8_UNORM;
    rtDesc.bind_flags = wi::graphics::BindFlag::RENDER_TARGET | wi::graphics::BindFlag::SHADER_RESOURCE;
    rtDesc.mip_levels = 1;
    rtDesc.sample_count = 1;
    rtDesc.layout = wi::graphics::ResourceState::SHADER_RESOURCE;
    device->CreateTexture(&rtDesc, nullptr, &voxelRT_);

    wi::graphics::TextureDesc depthDesc;
    depthDesc.type = wi::graphics::TextureDesc::Type::TEXTURE_2D;
    depthDesc.width = w;
    depthDesc.height = h;
    depthDesc.format = wi::graphics::Format::D32_FLOAT;
    depthDesc.bind_flags = wi::graphics::BindFlag::DEPTH_STENCIL | wi::graphics::BindFlag::SHADER_RESOURCE;
    depthDesc.mip_levels = 1;
    depthDesc.sample_count = 1;
    depthDesc.layout = wi::graphics::ResourceState::DEPTHSTENCIL;
    device->CreateTexture(&depthDesc, nullptr, &voxelDepth_);

    rtCreated_ = voxelRT_.IsValid() && voxelDepth_.IsValid();
    wi::backlog::post("VoxelRenderPath: render targets " + std::string(rtCreated_ ? "OK" : "FAILED")
        + " (" + std::to_string(w) + "x" + std::to_string(h) + ")");
}

// ── WASD camera input ───────────────────────────────────────────

static constexpr wi::input::BUTTON KEY_W = (wi::input::BUTTON)(wi::input::CHARACTER_RANGE_START + ('W' - 'A'));
static constexpr wi::input::BUTTON KEY_A = (wi::input::BUTTON)(wi::input::CHARACTER_RANGE_START + ('A' - 'A'));
static constexpr wi::input::BUTTON KEY_S = (wi::input::BUTTON)(wi::input::CHARACTER_RANGE_START + ('S' - 'A'));
static constexpr wi::input::BUTTON KEY_D = (wi::input::BUTTON)(wi::input::CHARACTER_RANGE_START + ('D' - 'A'));

void VoxelRenderPath::handleInput(float dt) {
    if (wi::input::Press(wi::input::MOUSE_BUTTON_RIGHT)) {
        mouseCaptured = !mouseCaptured;
        wi::input::HidePointer(mouseCaptured);
    }

    if (mouseCaptured) {
        auto mouseState = wi::input::GetMouseState();
        cameraYaw += mouseState.delta_position.x * cameraSensitivity;
        cameraPitch += mouseState.delta_position.y * cameraSensitivity;
        cameraPitch = std::clamp(cameraPitch, -1.5f, 1.5f);
    }

    float cosPitch = std::cos(cameraPitch);
    XMFLOAT3 forward(
        std::sin(cameraYaw) * cosPitch,
        -std::sin(cameraPitch),
        std::cos(cameraYaw) * cosPitch
    );
    XMFLOAT3 right(std::cos(cameraYaw), 0.0f, -std::sin(cameraYaw));

    float speed = cameraSpeed * dt;
    if (wi::input::Down(wi::input::KEYBOARD_BUTTON_LSHIFT)) speed *= 3.0f;

    if (wi::input::Down(KEY_W)) { cameraPos.x += forward.x * speed; cameraPos.y += forward.y * speed; cameraPos.z += forward.z * speed; }
    if (wi::input::Down(KEY_S)) { cameraPos.x -= forward.x * speed; cameraPos.y -= forward.y * speed; cameraPos.z -= forward.z * speed; }
    if (wi::input::Down(KEY_A)) { cameraPos.x -= right.x * speed; cameraPos.z -= right.z * speed; }
    if (wi::input::Down(KEY_D)) { cameraPos.x += right.x * speed; cameraPos.z += right.z * speed; }
    if (wi::input::Down(wi::input::KEYBOARD_BUTTON_SPACE))    cameraPos.y += speed;
    if (wi::input::Down(wi::input::KEYBOARD_BUTTON_LCONTROL)) cameraPos.y -= speed;

    camera->Eye = cameraPos;
    camera->At = forward;
    camera->Up = XMFLOAT3(0, 1, 0);
    camera->UpdateCamera();
}

void VoxelRenderPath::Update(float dt) {
    lastDt_ = dt;
    float instantFps = (dt > 0.0f) ? (1.0f / dt) : 0.0f;
    smoothFps_ = smoothFps_ * 0.95f + instantFps * 0.05f;
    if (camera) handleInput(dt);
    if (renderer.isInitialized()) renderer.updateMeshes(world);
    RenderPath3D::Update(dt);
}

void VoxelRenderPath::Render() const {
    RenderPath3D::Render();

    if (renderer.isInitialized() && camera && rtCreated_) {
        auto* device = wi::graphics::GetDevice();
        CommandList cmd = device->BeginCommandList();
        renderer.render(cmd, *camera, voxelDepth_, voxelRT_);
    }
}

void VoxelRenderPath::Compose(CommandList cmd) const {
    frameCount_++;

    RenderPath3D::Compose(cmd);

    if (rtCreated_ && voxelRT_.IsValid()) {
        wi::image::Params fx;
        fx.enableFullScreen();
        fx.blendFlag = wi::enums::BLENDMODE_OPAQUE;
        wi::image::Draw(&voxelRT_, fx, cmd);
    }

    // HUD overlay
    wi::font::Params fp;
    fp.posX = 10; fp.posY = 10; fp.size = 20;
    fp.color = wi::Color(255, 255, 255, 230);
    fp.shadowColor = wi::Color(0, 0, 0, 180);

    char fpsStr[16];
    snprintf(fpsStr, sizeof(fpsStr), "%.1f", smoothFps_);
    char dtStr[16];
    snprintf(dtStr, sizeof(dtStr), "%.2f", lastDt_ * 1000.0f);

    std::string stats = "BVLE Voxel Engine (Phase 2 — GPU-driven)\n";
    stats += "FPS: " + std::string(fpsStr) + " (" + std::string(dtStr) + " ms)\n";
    if (debugMode) {
        stats += "=== DEBUG FACE MODE ===\n";
        stats += "+X=Red  -X=DkRed  +Y=Green  -Y=DkGreen  +Z=Blue  -Z=DkBlue\n";
    }
    stats += "Chunks: " + std::to_string(renderer.getVisibleChunks())
           + "/" + std::to_string(renderer.getChunkCount()) + "\n";
    stats += "Quads: " + std::to_string(renderer.getTotalQuads()) + "\n";
    std::string renderMode;
    if (renderer.isGpuCulling())
        renderMode = "MDI + GPU cull";
    else if (renderer.isMdiEnabled())
        renderMode = "MDI + CPU cull";
    else
        renderMode = "DrawInstanced + CPU cull + backface";
    stats += "Draw Calls: " + std::to_string(renderer.getDrawCalls())
           + " (" + renderMode + ")\n";

    char cullStr[16], drawStr[16];
    snprintf(cullStr, sizeof(cullStr), "%.3f", renderer.getGpuCullTimeMs());
    snprintf(drawStr, sizeof(drawStr), "%.3f", renderer.getGpuDrawTimeMs());
    stats += "GPU Cull: " + std::string(cullStr) + " ms | Draw: " + std::string(drawStr) + " ms\n";
    stats += "WASD+Space/Ctrl: move | Shift: fast | Right-click: capture mouse";

    wi::font::Draw(stats, fp, cmd);
}

} // namespace voxel