wip(assembler): round S10 -- LOD8 horizon sampled at MC spacing: LOD8 worker time 18.8 s -> 4.3 s

Planar far horizon samples the LOD8 interior at the MC cell spacing, keeping 128-voxel boundary strips; far recipe v3. LOD8 p95 59.8 -> 13.9 ms, spawn worker-seconds ~41 -> 26.9, full set 7.8 -> 7.1 s, ring 0.49 s, LOD0 1.43 s, 40 m/s ring 75/75. S3/S4 2 cm agreement, 100% cap coverage, W1/W8/W12 and W1/W8/W16 determinism pass. Report: Standalone/Research/WorldAssemblerM3/Round14. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MmSoF64BbRFmk9C3p1VsBJ
2026-10-19 12:23:18 +02:00
1 parent e7586a1256
commit b90d63d0f7
@@ -125,6 +125,11 @@ namespace VoxelForgeCore
        std::uint64_t columnCacheMisses = 0;
        double classificationMilliseconds = 0.0;
        double columnComputeMilliseconds = 0.0;
+        double columnEvaluationExclusiveMilliseconds = 0.0;
+        double marchingCubesExclusiveMilliseconds = 0.0;
+        double groundRefinementExclusiveMilliseconds = 0.0;
+        double capRefinementExclusiveMilliseconds = 0.0;
+        double meshAssemblyMilliseconds = 0.0;
        double meshingMilliseconds = 0.0;
        double featureListMilliseconds = 0.0;
        double farShellMilliseconds = 0.0;
@@ -146,6 +151,9 @@ namespace VoxelForgeCore
        std::uint64_t capRefinedCells = 0;
        std::uint64_t capRefinedTriangles = 0;
        bool capRefined = false;
+        std::uint64_t columnEvaluationWorkerHash = 0;
+        bool columnCoordinateCaptureComplete = true;
+        std::vector<std::array<std::int64_t, 2>> evaluatedColumnCoordinates;
    };

    struct TileMesh
@@ -628,6 +636,9 @@ namespace VoxelForgeCore
        std::uint64_t columnHits = 0;
        std::uint64_t columnMisses = 0;
        double columnComputeMilliseconds = 0.0;
+        bool captureCoordinates = false;
+        bool coordinateCaptureComplete = true;
+        std::vector<std::array<std::int64_t, 2>> evaluatedCoordinates;
    };

    struct FieldInfluenceBounds
@@ -676,8 +687,8 @@ namespace VoxelForgeCore
            std::int64_t minimumYSubvoxels, std::int64_t minimumZSubvoxels,
            std::int64_t maximumXSubvoxels, std::int64_t maximumYSubvoxels,
            std::int64_t maximumZSubvoxels, std::int32_t stepVoxels) const noexcept;
-        static void resetThreadColumnCacheStats() noexcept;
-        static HeightfieldColumnCacheStats threadColumnCacheStats() noexcept;
+        static void resetThreadColumnCacheStats(bool captureCoordinates = false) noexcept;
+        static const HeightfieldColumnCacheStats& threadColumnCacheStats() noexcept;
        FieldInterval interval(std::int64_t minimumXSubvoxels,
                               std::int64_t minimumYSubvoxels,
                               std::int64_t minimumZSubvoxels,
@@ -1002,11 +1013,17 @@ namespace VoxelForgeCore
        // Validation control only; never participates in recipe/world identity.
        // Controle de validation seulement, sans effet sur l'identite du monde.
        bool useAssemblyFeatureQueries = true;
+        // Opt-in diagnostic only; records XY columns evaluated by this LOD8 tile.
+        // Diagnostic seulement; enregistre les colonnes XY evaluees par cette tuile LOD8.
+        bool captureColumnCoordinates = false;
+        // LOD8-only planar horizon interior grid; zero follows the MC step, 128 restores S9.
+        // Grille interieure LOD8 seulement; zero suit la maille MC, 128 restaure S9.
+        std::int32_t lod8HorizonInteriorStepVoxels = 0;
        // Bump when the distant cap representation changes. LOD4-8 mesh hashes are salted;
        // density and LOD0-3 hashes remain unchanged.
        // Incremente quand le plafond lointain change. Les hashes LOD4-8 incluent cette version;
        // densite et hashes LOD0-3 restent inchanges.
-        std::uint32_t farHorizonVersion = 2;
+        std::uint32_t farHorizonVersion = 3;
    };

    class VFCORE_API World
@@ -11,6 +11,8 @@
 #include <unordered_map>
 #include <unordered_set>
 #include <set>
+#include <functional>
+#include <thread>

 namespace vfcore::detail
 {
@@ -247,6 +249,45 @@ namespace VoxelForgeCore
            bool Refined = false;
        };

+        std::vector<int32> BuildNativeHorizonGridCoordinates(int32 TileExtent,int32 InteriorStep)
+        {
+            constexpr int32 BoundaryStep=128;
+            std::vector<int32> Coordinates;
+            if(TileExtent<=0)return Coordinates;
+            if(InteriorStep<=BoundaryStep)
+            {
+                Coordinates.reserve(static_cast<std::size_t>(TileExtent/InteriorStep)+1u);
+                for(int32 Position=0;Position<TileExtent;Position+=InteriorStep)
+                    Coordinates.push_back(Position);
+                if(Coordinates.empty()||Coordinates.back()!=TileExtent)Coordinates.push_back(TileExtent);
+                return Coordinates;
+            }
+            if(TileExtent<2*InteriorStep)
+            {
+                Coordinates.reserve(static_cast<std::size_t>(TileExtent/BoundaryStep)+1u);
+                for(int32 Position=0;Position<TileExtent;Position+=BoundaryStep)
+                    Coordinates.push_back(Position);
+                if(Coordinates.empty()||Coordinates.back()!=TileExtent)Coordinates.push_back(TileExtent);
+                return Coordinates;
+            }
+
+            // Keep the shared 128-voxel boundary lattice for LOD transitions while the LOD8
+            // interior follows the coarse MC cell spacing. Preserve the exact same coordinates
+            // in neighboring tiles, independent of which worker builds either side.
+            // Garder la bordure commune de 128 voxels, avec un interieur a la maille MC de LOD8.
+            for(int32 Position=0;Position<InteriorStep&&Position<TileExtent;Position+=BoundaryStep)
+                Coordinates.push_back(Position);
+            if(Coordinates.empty()||Coordinates.back()!=InteriorStep)
+                Coordinates.push_back(InteriorStep);
+            for(int32 Position=InteriorStep+InteriorStep;Position<TileExtent-InteriorStep;
+                Position+=InteriorStep)
+                Coordinates.push_back(Position);
+            for(int32 Position=TileExtent-InteriorStep;Position<TileExtent;Position+=BoundaryStep)
+                if(Coordinates.empty()||Coordinates.back()!=Position)Coordinates.push_back(Position);
+            if(Coordinates.empty()||Coordinates.back()!=TileExtent)Coordinates.push_back(TileExtent);
+            return Coordinates;
+        }
+
        FVector NormalizeCapNormal(const FVector& Value)
        {
            const double Length=std::sqrt(Value.X*Value.X+Value.Y*Value.Y+Value.Z*Value.Z);
@@ -299,17 +340,28 @@ namespace VoxelForgeCore
        }

        FNativeCapRefinementStats RefineFarNativeGround(const FStandaloneOwnerWorld& Owner,
-            const WorldAssemblyManifest& Manifest,const FVoxelTileKey& Key,FVoxelMeshData& Mesh)
+            const WorldAssemblyManifest& Manifest,const FVoxelTileKey& Key,int32 MeshStepVoxels,
+            int32 InteriorStepOverride,FVoxelMeshData& Mesh)
        {
            FNativeCapRefinementStats Stats;
            if(Key.Level<5||!Owner.Generator)return Stats;
-            const int32 GridStepVoxels=std::min(128,1<<Key.Level);
+            constexpr int32 BoundaryStepVoxels=128;
            constexpr int64 Scale=WorldAssemblySubvoxelsPerVoxel;
-            const int64 GridStepSubvoxels=static_cast<int64>(GridStepVoxels)*Scale;
            const FIntVector TileOrigin=Key.OriginVoxels();
            const int32 TileExtent=Key.ExtentVoxels();
+            const int32 RequestedStep=Key.Level==8
+                ?(InteriorStepOverride>0?InteriorStepOverride:MeshStepVoxels)
+                :std::min(BoundaryStepVoxels,1<<Key.Level);
+            const int32 GridStepVoxels=Key.Level==8
+                ?((RequestedStep<BoundaryStepVoxels||RequestedStep%BoundaryStepVoxels!=0
+                    ||TileExtent<=0||TileExtent%RequestedStep!=0)
+                    ?BoundaryStepVoxels:std::max(BoundaryStepVoxels,RequestedStep))
+                :RequestedStep;
            if(TileExtent<=0||TileExtent%GridStepVoxels!=0)return Stats;
-            const int32 Cells=TileExtent/GridStepVoxels;
+            const std::vector<int32> GridCoordinates=
+                BuildNativeHorizonGridCoordinates(TileExtent,GridStepVoxels);
+            const int32 GridSize=static_cast<int32>(GridCoordinates.size());
+            if(GridSize<2)return Stats;
            const double TileMinZ=static_cast<double>(TileOrigin.Z)*Scale;
            const double TileMaxZ=static_cast<double>(TileOrigin.Z+TileExtent)*Scale;
            const int32 OldSurfaceVertices=std::clamp(Mesh.NumSurfaceVertices,0,Mesh.Vertices.Num());
@@ -324,8 +376,9 @@ namespace VoxelForgeCore

            struct FGroundProfile
            {
-                int32 Cells=0,GridStep=0;
+                int32 GridStep=0;
                double MinimumZ=0.0,MaximumZ=0.0;
+                std::vector<int32> Coordinates;
                std::vector<double> Ground,Cap;
            };
            std::vector<FGroundProfile> GroundProfiles;
@@ -344,14 +397,14 @@ namespace VoxelForgeCore
                    FColor Color=FColor::White;
                    int32 VertexIndex=INDEX_NONE;
                };
-                std::vector<FGridSample> Grid(static_cast<std::size_t>(Cells+1)*(Cells+1));
-                const auto GridIndex=[Cells](int32 X,int32 Y)
-                {return static_cast<std::size_t>(Y)*(Cells+1)+X;};
-                for(int32 Y=0;Y<=Cells;++Y)
-                for(int32 X=0;X<=Cells;++X)
+                std::vector<FGridSample> Grid(static_cast<std::size_t>(GridSize)*GridSize);
+                const auto GridIndex=[GridSize](int32 X,int32 Y)
+                {return static_cast<std::size_t>(Y)*GridSize+X;};
+                for(int32 Y=0;Y<GridSize;++Y)
+                for(int32 X=0;X<GridSize;++X)
                {
-                    const int64 XSub=(static_cast<int64>(TileOrigin.X)+static_cast<int64>(X)*GridStepVoxels)*Scale;
-                    const int64 YSub=(static_cast<int64>(TileOrigin.Y)+static_cast<int64>(Y)*GridStepVoxels)*Scale;
+                    const int64 XSub=(static_cast<int64>(TileOrigin.X)+GridCoordinates[X])*Scale;
+                    const int64 YSub=(static_cast<int64>(TileOrigin.Y)+GridCoordinates[Y])*Scale;
                    const auto Column=Block.point(XSub,YSub,0);
                    auto& Sample=Grid[GridIndex(X,Y)];
                    Sample.Ground=static_cast<double>(Column.groundHeightSubvoxels);
@@ -364,13 +417,13 @@ namespace VoxelForgeCore
                        static_cast<uint8>(std::clamp(std::lround(Blend*255.0f),0l,255l)),
                        static_cast<uint8>(std::clamp(Neighbor,0,255)));
                }
-                for(int32 Y=0;Y<=Cells;++Y)
-                for(int32 X=0;X<=Cells;++X)
+                for(int32 Y=0;Y<GridSize;++Y)
+                for(int32 X=0;X<GridSize;++X)
                {
-                    const int32 Left=std::max(0,X-1),Right=std::min(Cells,X+1);
-                    const int32 Down=std::max(0,Y-1),Up=std::min(Cells,Y+1);
-                    const double DX=static_cast<double>(Right-Left)*GridStepSubvoxels;
-                    const double DY=static_cast<double>(Up-Down)*GridStepSubvoxels;
+                    const int32 Left=std::max(0,X-1),Right=std::min(GridSize-1,X+1);
+                    const int32 Down=std::max(0,Y-1),Up=std::min(GridSize-1,Y+1);
+                    const double DX=static_cast<double>(GridCoordinates[Right]-GridCoordinates[Left])*Scale;
+                    const double DY=static_cast<double>(GridCoordinates[Up]-GridCoordinates[Down])*Scale;
                    const double SlopeX=DX>0.0?(Grid[GridIndex(Right,Y)].Ground
                        -Grid[GridIndex(Left,Y)].Ground)/DX:0.0;
                    const double SlopeY=DY>0.0?(Grid[GridIndex(X,Up)].Ground
@@ -382,7 +435,7 @@ namespace VoxelForgeCore
                }

                FGroundProfile Profile;
-                Profile.Cells=Cells;Profile.GridStep=GridStepVoxels;
+                Profile.GridStep=GridStepVoxels;Profile.Coordinates=GridCoordinates;
                Profile.MinimumZ=static_cast<double>(std::min(Plan.bottomChunkZ,Plan.topChunkZ))*CHUNK_SIZE;
                Profile.MaximumZ=static_cast<double>(std::max(Plan.bottomChunkZ,Plan.topChunkZ)+1)*CHUNK_SIZE;
                Profile.Ground.reserve(Grid.size());Profile.Cap.reserve(Grid.size());
@@ -392,25 +445,25 @@ namespace VoxelForgeCore

                // Partager les sommets du profil entre cellules reduit le payload d'horizon.
                // Share regular profile vertices across adjacent cells to bound horizon payload.
-                for(int32 Y=0;Y<=Cells;++Y)
-                for(int32 X=0;X<=Cells;++X)
+                for(int32 Y=0;Y<GridSize;++Y)
+                for(int32 X=0;X<GridSize;++X)
                {
                    auto& Sample=Grid[GridIndex(X,Y)];
                    if(Sample.Ground>=Sample.Cap||Sample.Ground<TileMinZ||Sample.Ground>TileMaxZ)continue;
-                    const int64 XSub=(static_cast<int64>(TileOrigin.X)+static_cast<int64>(X)*GridStepVoxels)*Scale;
-                    const int64 YSub=(static_cast<int64>(TileOrigin.Y)+static_cast<int64>(Y)*GridStepVoxels)*Scale;
+                    const int64 XSub=(static_cast<int64>(TileOrigin.X)+GridCoordinates[X])*Scale;
+                    const int64 YSub=(static_cast<int64>(TileOrigin.Y)+GridCoordinates[Y])*Scale;
                    const double VoxelSizeCm=static_cast<double>(Owner.CoreVoxelSizeMicrons)/10000.0;
                    Sample.VertexIndex=static_cast<int32>(AddedVertices.size());
-                    AddedVertices.emplace_back(static_cast<double>(TileOrigin.X+X*GridStepVoxels)*VoxelSizeCm,
-                        static_cast<double>(TileOrigin.Y+Y*GridStepVoxels)*VoxelSizeCm,
+                    AddedVertices.emplace_back(static_cast<double>(TileOrigin.X+GridCoordinates[X])*VoxelSizeCm,
+                        static_cast<double>(TileOrigin.Y+GridCoordinates[Y])*VoxelSizeCm,
                        Sample.Ground/Scale*VoxelSizeCm);
                    AddedNormals.push_back(Sample.Normal);
                    if(bHasUVs)AddedUVs.emplace_back(static_cast<float>(XSub/Scale),static_cast<float>(YSub/Scale));
                    if(bHasColors)AddedColors.push_back(Sample.Color);
                }

-                for(int32 Y=0;Y<Cells;++Y)
-                for(int32 X=0;X<Cells;++X)
+                for(int32 Y=0;Y+1<GridSize;++Y)
+                for(int32 X=0;X+1<GridSize;++X)
                {
                    const int32 CellX[4]={X,X+1,X+1,X};
                    const int32 CellY[4]={Y,Y,Y+1,Y+1};
@@ -433,8 +486,8 @@ namespace VoxelForgeCore
                    {
                        const int32 GX=CellX[Corner],GY=CellY[Corner];
                        const auto& Sample=Grid[GridIndex(GX,GY)];
-                        PolygonA[Corner].XSub=static_cast<double>(TileOrigin.X+GX*GridStepVoxels)*Scale;
-                        PolygonA[Corner].YSub=static_cast<double>(TileOrigin.Y+GY*GridStepVoxels)*Scale;
+                        PolygonA[Corner].XSub=static_cast<double>(TileOrigin.X+GridCoordinates[GX])*Scale;
+                        PolygonA[Corner].YSub=static_cast<double>(TileOrigin.Y+GridCoordinates[GY])*Scale;
                        PolygonA[Corner].GroundSub=Sample.Ground;
                        PolygonA[Corner].CapSub=Sample.Cap;
                        PolygonA[Corner].ZSub=Sample.Ground;
@@ -487,16 +540,29 @@ namespace VoxelForgeCore
            const auto InterpolateProfile=[](const std::vector<double>& Values,const FGroundProfile& Profile,
                double LocalX,double LocalY)
            {
-                const double GridX=std::clamp(LocalX/Profile.GridStep,0.0,static_cast<double>(Profile.Cells));
-                const double GridY=std::clamp(LocalY/Profile.GridStep,0.0,static_cast<double>(Profile.Cells));
-                const int32 X=std::min(Profile.Cells-1,static_cast<int32>(std::floor(GridX)));
-                const int32 Y=std::min(Profile.Cells-1,static_cast<int32>(std::floor(GridY)));
-                const double TX=GridX-X,TY=GridY-Y;
-                const std::size_t Width=static_cast<std::size_t>(Profile.Cells+1);
+                const std::size_t Width=Profile.Coordinates.size();
+                const auto FindCell=[&](double Local)
+                {
+                    const double Clamped=std::clamp(Local,static_cast<double>(Profile.Coordinates.front()),
+                        static_cast<double>(Profile.Coordinates.back()));
+                    const auto Upper=std::upper_bound(Profile.Coordinates.begin(),Profile.Coordinates.end(),Clamped);
+                    if(Upper==Profile.Coordinates.begin())return std::pair<std::size_t,double>{0u,0.0};
+                    const std::size_t Index=std::min<std::size_t>(Width-2u,
+                        static_cast<std::size_t>(Upper-Profile.Coordinates.begin()-1));
+                    const double Start=Profile.Coordinates[Index];
+                    const double Span=Profile.Coordinates[Index+1]-Profile.Coordinates[Index];
+                    return std::pair<std::size_t,double>{Index,Span>0.0?(Clamped-Start)/Span:0.0};
+                };
+                const auto [X,TX]=FindCell(LocalX);
+                const auto [Y,TY]=FindCell(LocalY);
                const auto At=[&](int32 PX,int32 PY){return Values[static_cast<std::size_t>(PY)*Width+PX];};
                if(TX>=TY)
-                    return At(X,Y)*(1.0-TX)+At(X+1,Y)*(TX-TY)+At(X+1,Y+1)*TY;
-                return At(X,Y)*(1.0-TY)+At(X+1,Y+1)*TX+At(X,Y+1)*(TY-TX);
+                    return At(static_cast<int32>(X),static_cast<int32>(Y))*(1.0-TX)
+                        +At(static_cast<int32>(X+1u),static_cast<int32>(Y))*(TX-TY)
+                        +At(static_cast<int32>(X+1u),static_cast<int32>(Y+1u))*TY;
+                return At(static_cast<int32>(X),static_cast<int32>(Y))*(1.0-TY)
+                    +At(static_cast<int32>(X+1u),static_cast<int32>(Y+1u))*TX
+                    +At(static_cast<int32>(X),static_cast<int32>(Y+1u))*(TY-TX);
            };
            for(int32 Triangle=0;Triangle<OldSurfaceTriangleCount;++Triangle)
            {
@@ -517,12 +583,13 @@ namespace VoxelForgeCore
                if(LocalX<0.0||LocalY<0.0||LocalX>TileExtent||LocalY>TileExtent)continue;
                for(const auto& Profile:GroundProfiles)
                {
-                    if(LocalX>Profile.Cells*Profile.GridStep||LocalY>Profile.Cells*Profile.GridStep)continue;
+                    if(LocalX>Profile.Coordinates.back()||LocalY>Profile.Coordinates.back())continue;
                    const double Ground=InterpolateProfile(Profile.Ground,Profile,LocalX,LocalY);
                    const double Cap=InterpolateProfile(Profile.Cap,Profile,LocalX,LocalY);
                    if(Cap-Ground<=1.0||Ground<TileMinZ/Scale||Ground>TileMaxZ/Scale
                        ||Ground<Profile.MinimumZ||Ground>Profile.MaximumZ)continue;
-                    const double ReplacementBand=std::max(32.0,2.0*Profile.GridStep);
+                    const double ReplacementBand=std::max(32.0,
+                        2.0*std::min(Profile.GridStep,BoundaryStepVoxels));
                    if(Z>=Ground-ReplacementBand)
                    {
                        RemoveOldGround[static_cast<std::size_t>(Triangle)]=1;
@@ -574,17 +641,28 @@ namespace VoxelForgeCore
        }

        FNativeCapRefinementStats RefineFarNativeCap(const FStandaloneOwnerWorld& Owner,
-            const WorldAssemblyManifest& Manifest,const FVoxelTileKey& Key,FVoxelMeshData& Mesh)
+            const WorldAssemblyManifest& Manifest,const FVoxelTileKey& Key,int32 MeshStepVoxels,
+            int32 InteriorStepOverride,FVoxelMeshData& Mesh)
        {
            FNativeCapRefinementStats Stats;
            if(Key.Level<4||!Owner.Generator)return Stats;
-            const int32 GridStepVoxels=Key.Level<5?std::min(128,1<<Key.Level):128;
-            constexpr int64 Scale=WorldAssemblySubvoxelsPerVoxel;
-            const int64 GridStepSubvoxels=static_cast<int64>(GridStepVoxels)*Scale;
+            constexpr int32 BoundaryStepVoxels=128;
+            const int32 RequestedStep=Key.Level==8
+                ?(InteriorStepOverride>0?InteriorStepOverride:MeshStepVoxels)
+                :(Key.Level<5?std::min(BoundaryStepVoxels,1<<Key.Level):BoundaryStepVoxels);
            const FIntVector TileOrigin=Key.OriginVoxels();
            const int32 TileExtent=Key.ExtentVoxels();
-            if(TileExtent<=0||TileExtent%GridStepVoxels!=0)return Stats;
-            const int32 Cells=TileExtent/GridStepVoxels;
+            const int32 EffectiveGridStep=Key.Level==8
+                ?((RequestedStep<BoundaryStepVoxels||RequestedStep%BoundaryStepVoxels!=0
+                    ||TileExtent<=0||TileExtent%RequestedStep!=0)
+                    ?BoundaryStepVoxels:std::max(BoundaryStepVoxels,RequestedStep))
+                :RequestedStep;
+            constexpr int64 Scale=WorldAssemblySubvoxelsPerVoxel;
+            if(TileExtent<=0||TileExtent%EffectiveGridStep!=0)return Stats;
+            const std::vector<int32> GridCoordinates=
+                BuildNativeHorizonGridCoordinates(TileExtent,EffectiveGridStep);
+            const int32 GridSize=static_cast<int32>(GridCoordinates.size());
+            if(GridSize<2)return Stats;
            const int64 TileMinZ=static_cast<int64>(TileOrigin.Z)*Scale;
            const int64 TileMaxZ=static_cast<int64>(TileOrigin.Z+TileExtent)*Scale;
            const int32 OldSurfaceVertices=std::clamp(Mesh.NumSurfaceVertices,0,Mesh.Vertices.Num());
@@ -612,14 +690,14 @@ namespace VoxelForgeCore
                    FColor Color=FColor::White;
                    int32 VertexIndex=INDEX_NONE;
                };
-                std::vector<FGridSample> Grid(static_cast<std::size_t>(Cells+1)*(Cells+1));
-                const auto GridIndex=[Cells](int32 X,int32 Y)
-                {return static_cast<std::size_t>(Y)*(Cells+1)+X;};
-                for(int32 Y=0;Y<=Cells;++Y)
-                for(int32 X=0;X<=Cells;++X)
+                std::vector<FGridSample> Grid(static_cast<std::size_t>(GridSize)*GridSize);
+                const auto GridIndex=[GridSize](int32 X,int32 Y)
+                {return static_cast<std::size_t>(Y)*GridSize+X;};
+                for(int32 Y=0;Y<GridSize;++Y)
+                for(int32 X=0;X<GridSize;++X)
                {
-                    const int64 XSub=(static_cast<int64>(TileOrigin.X)+static_cast<int64>(X)*GridStepVoxels)*Scale;
-                    const int64 YSub=(static_cast<int64>(TileOrigin.Y)+static_cast<int64>(Y)*GridStepVoxels)*Scale;
+                    const int64 XSub=(static_cast<int64>(TileOrigin.X)+GridCoordinates[X])*Scale;
+                    const int64 YSub=(static_cast<int64>(TileOrigin.Y)+GridCoordinates[Y])*Scale;
                    const auto Column=Block.point(XSub,YSub,0);
                    auto& Sample=Grid[GridIndex(X,Y)];
                    Sample.Ground=static_cast<double>(Column.groundHeightSubvoxels);
@@ -633,13 +711,13 @@ namespace VoxelForgeCore
                    const uint8 B=static_cast<uint8>(std::clamp(std::lround(Blend*255.0f),0l,255l));
                    Sample.Color=FColor(R,0,B,A);
                }
-                for(int32 Y=0;Y<=Cells;++Y)
-                for(int32 X=0;X<=Cells;++X)
+                for(int32 Y=0;Y<GridSize;++Y)
+                for(int32 X=0;X<GridSize;++X)
                {
-                    const int32 Left=std::max(0,X-1),Right=std::min(Cells,X+1);
-                    const int32 Down=std::max(0,Y-1),Up=std::min(Cells,Y+1);
-                    const double DX=static_cast<double>(Right-Left)*GridStepSubvoxels;
-                    const double DY=static_cast<double>(Up-Down)*GridStepSubvoxels;
+                    const int32 Left=std::max(0,X-1),Right=std::min(GridSize-1,X+1);
+                    const int32 Down=std::max(0,Y-1),Up=std::min(GridSize-1,Y+1);
+                    const double DX=static_cast<double>(GridCoordinates[Right]-GridCoordinates[Left])*Scale;
+                    const double DY=static_cast<double>(GridCoordinates[Up]-GridCoordinates[Down])*Scale;
                    const double SlopeX=DX>0.0?(Grid[GridIndex(Right,Y)].Cap-Grid[GridIndex(Left,Y)].Cap)/DX:0.0;
                    const double SlopeY=DY>0.0?(Grid[GridIndex(X,Up)].Cap-Grid[GridIndex(X,Down)].Cap)/DY:0.0;
                    auto& Sample=Grid[GridIndex(X,Y)];
@@ -655,10 +733,10 @@ namespace VoxelForgeCore
                    if(Sample.Cap<Sample.Ground||Sample.Cap<TileMinZ||Sample.Cap>TileMaxZ)continue;
                    Sample.VertexIndex=static_cast<int32>(AddedVertices.size());
                    const std::size_t Index=static_cast<std::size_t>(&Sample-Grid.data());
-                    const int32 GX=static_cast<int32>(Index%static_cast<std::size_t>(Cells+1));
-                    const int32 GY=static_cast<int32>(Index/static_cast<std::size_t>(Cells+1));
-                    const double XSub=static_cast<double>(TileOrigin.X+GX*GridStepVoxels)*Scale;
-                    const double YSub=static_cast<double>(TileOrigin.Y+GY*GridStepVoxels)*Scale;
+                    const int32 GX=static_cast<int32>(Index%static_cast<std::size_t>(GridSize));
+                    const int32 GY=static_cast<int32>(Index/static_cast<std::size_t>(GridSize));
+                    const double XSub=static_cast<double>(TileOrigin.X+GridCoordinates[GX])*Scale;
+                    const double YSub=static_cast<double>(TileOrigin.Y+GridCoordinates[GY])*Scale;
                    const double VoxelSizeCm=static_cast<double>(Owner.CoreVoxelSizeMicrons)/10000.0;
                    AddedVertices.emplace_back(XSub/Scale*VoxelSizeCm,YSub/Scale*VoxelSizeCm,
                        Sample.Cap/Scale*VoxelSizeCm);
@@ -668,8 +746,8 @@ namespace VoxelForgeCore
                    if(bHasColors)AddedColors.push_back(Sample.Color);
                }

-                for(int32 Y=0;Y<Cells;++Y)
-                for(int32 X=0;X<Cells;++X)
+                for(int32 Y=0;Y+1<GridSize;++Y)
+                for(int32 X=0;X+1<GridSize;++X)
                {
                    const int32 CellX[4]={X,X+1,X+1,X};
                    const int32 CellY[4]={Y,Y,Y+1,Y+1};
@@ -692,8 +770,8 @@ namespace VoxelForgeCore
                    {
                        const int32 GX=CellX[Corner],GY=CellY[Corner];
                        const auto& Sample=Grid[GridIndex(GX,GY)];
-                        PolygonA[Corner].XSub=static_cast<double>(TileOrigin.X+GX*GridStepVoxels)*Scale;
-                        PolygonA[Corner].YSub=static_cast<double>(TileOrigin.Y+GY*GridStepVoxels)*Scale;
+                        PolygonA[Corner].XSub=static_cast<double>(TileOrigin.X+GridCoordinates[GX])*Scale;
+                        PolygonA[Corner].YSub=static_cast<double>(TileOrigin.Y+GridCoordinates[GY])*Scale;
                        PolygonA[Corner].ZSub=Sample.Cap;PolygonA[Corner].GroundSub=Sample.Ground;
                        PolygonA[Corner].Normal=Sample.Normal;PolygonA[Corner].Color=Sample.Color;
                    }
@@ -1400,7 +1478,8 @@ namespace VoxelForgeCore
            &&bHasNativeSurfaceHorizonPlan&&!bHasIslandPlanInTile;
        const bool bSkipFarShellRepair=key.lod>=7&&bUseNativeSurfaceHorizon;
        FStandaloneShapeWorld::ResetThreadClassificationStats();
-        VoxelForgeCore::Heightfield2D::resetThreadColumnCacheStats();
+        VoxelForgeCore::Heightfield2D::resetThreadColumnCacheStats(
+            options.captureColumnCoordinates&&key.lod==8);
        bool bNativeSurfaceTile=false;
        bool bNativeSurfaceBandSafe=false;
        if(bHasWorldAssembly)
@@ -1427,7 +1506,7 @@ namespace VoxelForgeCore
                {
                    out.diagnostics.meshingSkipped=true;
                    const auto Counts=FStandaloneShapeWorld::GetThreadClassificationStats();
-                    const auto Columns=VoxelForgeCore::Heightfield2D::threadColumnCacheStats();
+                    const auto& Columns=VoxelForgeCore::Heightfield2D::threadColumnCacheStats();
                    out.diagnostics.solidBoxes=Counts.SolidBoxes;
                    out.diagnostics.airBoxes=Counts.AirBoxes;
                    out.diagnostics.mixedBoxes=Counts.MixedBoxes;
@@ -1571,9 +1650,18 @@ namespace VoxelForgeCore
        out.diagnostics.featureListMilliseconds=std::chrono::duration<double,std::milli>(
            std::chrono::steady_clock::now()-FeatureListStart).count();
        const ScopedWorldAssemblyFeatureQueriesV1 featureScope(featureQueries);
+        const double ColumnMillisecondsBeforeMeshing=
+            VoxelForgeCore::Heightfield2D::threadColumnCacheStats().columnComputeMilliseconds;
+        const auto MarchingCubesStart=std::chrono::steady_clock::now();
        FVoxelMeshData mesh=mesher.GenerateMesh(origin,step,cells,nullptr,
            MeshBandMinZVoxel,MeshBandMaxZVoxel,&sampleCount,nullptr,nullptr,
            (options.hashDensity||options.captureDensitySamples)?&densityValues:nullptr);
+        const double MarchingCubesWallMilliseconds=std::chrono::duration<double,std::milli>(
+            std::chrono::steady_clock::now()-MarchingCubesStart).count();
+        const double ColumnMillisecondsAfterMeshing=
+            VoxelForgeCore::Heightfield2D::threadColumnCacheStats().columnComputeMilliseconds;
+        out.diagnostics.marchingCubesExclusiveMilliseconds=std::max(0.0,
+            MarchingCubesWallMilliseconds-(ColumnMillisecondsAfterMeshing-ColumnMillisecondsBeforeMeshing));
        const double MeshingMilliseconds=std::chrono::duration<double,std::milli>(
            std::chrono::steady_clock::now()-MeshingStart).count();
        out.diagnostics.farHorizonVersion=key.lod>=4?options.farHorizonVersion:0;
@@ -1612,9 +1700,29 @@ namespace VoxelForgeCore
        {
            const auto HorizonStart=std::chrono::steady_clock::now();
            FNativeCapRefinementStats GroundStats;
+            const double ColumnMillisecondsBeforeGround=
+                VoxelForgeCore::Heightfield2D::threadColumnCacheStats().columnComputeMilliseconds;
+            const auto GroundStart=std::chrono::steady_clock::now();
            if(key.lod>=4)
-                GroundStats=RefineFarNativeGround(world,*impl_->worldAssembly,nativeKey,mesh);
-            const auto CapStats=RefineFarNativeCap(world,*impl_->worldAssembly,nativeKey,mesh);
+                GroundStats=RefineFarNativeGround(world,*impl_->worldAssembly,nativeKey,step,
+                    options.lod8HorizonInteriorStepVoxels,mesh);
+            const double GroundWallMilliseconds=std::chrono::duration<double,std::milli>(
+                std::chrono::steady_clock::now()-GroundStart).count();
+            const double ColumnMillisecondsAfterGround=
+                VoxelForgeCore::Heightfield2D::threadColumnCacheStats().columnComputeMilliseconds;
+            out.diagnostics.groundRefinementExclusiveMilliseconds=std::max(0.0,
+                GroundWallMilliseconds-(ColumnMillisecondsAfterGround-ColumnMillisecondsBeforeGround));
+            const double ColumnMillisecondsBeforeCap=
+                VoxelForgeCore::Heightfield2D::threadColumnCacheStats().columnComputeMilliseconds;
+            const auto CapStart=std::chrono::steady_clock::now();
+            const auto CapStats=RefineFarNativeCap(world,*impl_->worldAssembly,nativeKey,step,
+                options.lod8HorizonInteriorStepVoxels,mesh);
+            const double CapWallMilliseconds=std::chrono::duration<double,std::milli>(
+                std::chrono::steady_clock::now()-CapStart).count();
+            const double ColumnMillisecondsAfterCap=
+                VoxelForgeCore::Heightfield2D::threadColumnCacheStats().columnComputeMilliseconds;
+            out.diagnostics.capRefinementExclusiveMilliseconds=std::max(0.0,
+                CapWallMilliseconds-(ColumnMillisecondsAfterCap-ColumnMillisecondsBeforeCap));
            out.diagnostics.farHorizonMilliseconds=std::chrono::duration<double,std::milli>(
                std::chrono::steady_clock::now()-HorizonStart).count();
            out.diagnostics.capRefined=CapStats.Refined;
@@ -1629,7 +1737,7 @@ namespace VoxelForgeCore
        if(bHasWorldAssembly)
        {
            const auto Counts=FStandaloneShapeWorld::GetThreadClassificationStats();
-            const auto Columns=VoxelForgeCore::Heightfield2D::threadColumnCacheStats();
+            const auto& Columns=VoxelForgeCore::Heightfield2D::threadColumnCacheStats();
            out.diagnostics.fieldCalls=Columns.pointCalls;
            out.diagnostics.floatFieldCalls=Counts.NativeFloatFieldCalls;
            out.diagnostics.latticeFieldCalls=Counts.NativeLatticeFieldCalls;
@@ -1637,7 +1745,15 @@ namespace VoxelForgeCore
            out.diagnostics.columnCacheHits=Columns.columnHits;
            out.diagnostics.columnCacheMisses=Columns.columnMisses;
            out.diagnostics.columnComputeMilliseconds=Columns.columnComputeMilliseconds;
+            out.diagnostics.columnEvaluationExclusiveMilliseconds=Columns.columnComputeMilliseconds;
            out.diagnostics.classificationMilliseconds=Counts.Milliseconds;
+            if(options.captureColumnCoordinates&&key.lod==8)
+            {
+                out.diagnostics.columnEvaluationWorkerHash=static_cast<std::uint64_t>(
+                    std::hash<std::thread::id>{}(std::this_thread::get_id()))+1u;
+                out.diagnostics.columnCoordinateCaptureComplete=Columns.coordinateCaptureComplete;
+                out.diagnostics.evaluatedColumnCoordinates=Columns.evaluatedCoordinates;
+            }
            if(bNativeSurfaceTile)
            {
                out.diagnostics.solidBoxes=Counts.SolidBoxes;
@@ -1653,6 +1769,7 @@ namespace VoxelForgeCore
        }
        out.diagnostics.heightfieldBandLimited=bNativeHeightfieldBandLimited;
        out.diagnostics.meshingMilliseconds=MeshingMilliseconds;
+        const auto MeshAssemblyStart=std::chrono::steady_clock::now();
        out.meshPayloadAllocatedBytes=static_cast<std::uint64_t>(mesh.Vertices.GetAllocatedSize())
            +static_cast<std::uint64_t>(mesh.Normals.GetAllocatedSize())
            +static_cast<std::uint64_t>(mesh.UVs.GetAllocatedSize())
@@ -1696,6 +1813,8 @@ namespace VoxelForgeCore
            }
            out.hasDensityHash=out.hasMeshHash=out.hasPayloadHash=out.hasTopologyHash=true;
        }
+        out.diagnostics.meshAssemblyMilliseconds=std::chrono::duration<double,std::milli>(
+            std::chrono::steady_clock::now()-MeshAssemblyStart).count();
        return out;
    }

@@ -1487,6 +1487,17 @@ namespace world_assembly_detail
        HeightfieldColumnStats.columnComputeMilliseconds+=std::chrono::duration<double,std::milli>(
            std::chrono::steady_clock::now()-start).count();
        ++HeightfieldColumnStats.columnMisses;
+        if(HeightfieldColumnStats.captureCoordinates&&HeightfieldColumnStats.coordinateCaptureComplete)
+        {
+            try
+            {
+                HeightfieldColumnStats.evaluatedCoordinates.push_back({x,y});
+            }
+            catch(...)
+            {
+                HeightfieldColumnStats.coordinateCaptureComplete=false;
+            }
+        }
        entry={&recipe,&plan,recipe.contentHash,plan.contentHash,x,y,column};
        return column;
    }
@@ -1954,10 +1965,19 @@ HeightfieldPointSample Heightfield2D::point(std::int64_t x, std::int64_t y,
    return out;
 }

-void Heightfield2D::resetThreadColumnCacheStats() noexcept
-{ world_assembly_detail::HeightfieldColumnStats={}; }
+void Heightfield2D::resetThreadColumnCacheStats(bool captureCoordinates) noexcept
+{
+    auto& Stats=world_assembly_detail::HeightfieldColumnStats;
+    Stats.pointCalls=0;
+    Stats.columnHits=0;
+    Stats.columnMisses=0;
+    Stats.columnComputeMilliseconds=0.0;
+    Stats.captureCoordinates=captureCoordinates;
+    Stats.coordinateCaptureComplete=true;
+    Stats.evaluatedCoordinates.clear();
+}

-HeightfieldColumnCacheStats Heightfield2D::threadColumnCacheStats() noexcept
+const HeightfieldColumnCacheStats& Heightfield2D::threadColumnCacheStats() noexcept
 { return world_assembly_detail::HeightfieldColumnStats; }

 HeightfieldBoxClass Heightfield2D::classifyLatticeBox(std::int64_t minimumX,
@@ -0,0 +1,213 @@
+# World assembler S10 / M3 Round 14 — cheaper far ring
+
+Date: 2026-10-19. Base: S9 / `e7586a1`. No commit, push or stash.
+
+## Result
+
+The planar far path now samples the LOD8 interior at the spacing that LOD8 marching cubes can
+represent. At 25 cm, that is 512 voxels / 128 m per MC cell. Globally aligned 128-voxel (32 m)
+strips remain along tile boundaries. LOD4–LOD7 coordinates and the 2 cm agreement tolerances are
+unchanged. Far recipe version is 3; far mesh hashes change, while density and LOD0–LOD3 remain
+unchanged.
+
+On the owner SurfaceWorld plan, the warmed eight-tile BuildHost LOD8 full-tile p95 fell 76.7%,
+from 59.848 ms to 13.933 ms. In the fresh 6 m/s actor spawn trace, the 2,578 initial tile jobs
+used 26.870 worker-seconds; the LOD8 share was 4.288 seconds. Round13’s S8 spawn reference was
+about 41 worker-seconds, with 18.798 seconds in its 306 LOD8 jobs. Initial readiness was 7.117 s,
+below the 7.7 s target. The active 3×3 walkable ring was ready in 0.490 s, and all 512 LOD0 tiles
+were ready at 1.428 s.
+
+## Count first — exclusive cost and duplicate columns
+
+The counters are measured per tile. Column evaluation is timed only around uncached column work.
+MC, ground and cap counters subtract column time from their respective wall intervals. The mesh
+assembly window covers final payload flattening and optional diagnostic hashing. Each p95 is
+computed independently, so these p95 values are not additive.
+
+| LOD8 warmed p95, BuildHost 25 cm | S9 | S10 | Change |
+|---|---:|---:|---:|
+| Full tile | 59.848 ms | 13.933 ms | −76.7% |
+| Column evaluation | 31.319 ms | 7.478 ms | −76.1% |
+| Marching cubes | 2.667 ms | 2.359 ms | −11.6% |
+| Ground refinement | 11.666 ms | 1.690 ms | −85.5% |
+| Cap refinement | 10.029 ms | 1.330 ms | −86.7% |
+| Mesh assembly and diagnostic hash | 5.445 ms | 1.095 ms | −79.9% |
+| Column-cache misses | 9,679 | 2,287 | −76.4% |
+
+The high-cost S9 sample generated 8,192 ground triangles, removed 531 coarse ground triangles,
+and generated 6,732 cap triangles. S10 generated 968 ground triangles, removed 534, and generated
+840 cap triangles. The geometric checks below pass at the same tolerance.
+
+The fresh W12 Standalone overlap capture counted 153 LOD8 tiles. S10 evaluated 106,219 unique XY
+columns and repeated 32,738 neighboring tile evaluations, including 30,446 cross-worker repeats.
+The same-binary step-128 control counted 660,283 unique columns, 44,319 neighboring repeats and
+41,665 cross-worker repeats. This confirms that cross-worker duplicates remain, while the coarser
+interior removes most column work without sharing cache state between workers.
+
+| Fresh W12 Standalone pipeline | Default step 0 | Negative control step 128 |
+|---|---:|---:|
+| LOD8 worker sum | 3.206 s | 13.534 s |
+| LOD8 unique XY columns | 106,219 | 660,283 |
+| Repeated neighboring evaluations | 32,738 | 44,319 |
+| Cross-worker neighboring repeats | 30,446 | 41,665 |
+
+Both runs used the current v3 binary. Step 128 restores S9 sampling density, but retains the v3
+hash salt; its far mesh hash is therefore expected to differ from S9’s v2 hash.
+
+## BuildHost actor spawn and ring
+
+The fresh 6 m/s trace used the S9 movement, collision and backlog settings: Legacy order, Dynamic
+near reserve, collision lookahead on, 256 result cap, and a 12-CPU affinity mask. Per-LOD worker
+generation sums for the 2,578 initial generation ordinals were:
+
+| LOD | Initial tiles | Worker seconds |
+|---:|---:|---:|
+| 0 | 512 | 3.840 |
+| 1 | 448 | 3.781 |
+| 2 | 320 | 0.811 |
+| 3 | 272 | 2.093 |
+| 4 | 272 | 6.688 |
+| 5 | 208 | 1.535 |
+| 6 | 144 | 1.988 |
+| 7 | 96 | 1.846 |
+| 8 | 306 | 4.288 |
+| **Total** | **2,578** | **26.870** |
+
+At 6 m/s, initial readiness was 7.116525 s (2,578 desired, 2,617 loaded); spawn-tick p95/max was
+1.824/4.993 ms. The support ring became ready at 0.490 s (9/9). The complete LOD0 set was ready at
+1.427630 s, with a 0.990836 s measured build interval. Round13’s S9 6 m/s initial-ready value was
+7.813133 s.
+
+At 40 m/s (4,000 cm/s), all 75 moving support-center arrivals from 30.205 s through 45.011 s had
+the full 9/9 walkable ring ready: 75/75, 100%. A stationary startup gate event before movement is
+excluded from that moving-center denominator. Initial readiness was 7.087272 s. Spawn-tick
+p95/max was 1.833/5.365 ms; the trace passed.
+
+## Quality and determinism
+
+- S3 ground agreement: 72 shared route points; far LOD7 and LOD8 maximum error 0.0427 cm, cross-LOD
+  error 0 cm, within 2 cm. The 100 cm datum-offset control measured 100.0427 cm and was detected.
+- S4 cap agreement: 128 shared points; maximum error 0.0504 cm, within 2 cm. The 100 cm datum-offset
+  control measured 100.0015 cm and was detected. Cap census emitted all 385/385 requested bands.
+- Cap coverage: 2,520/2,520 upward rays hit the cap (100%); no profile-roof, mesh or clip-edge misses.
+- Core-off legacy passed at 12.5 cm. The M2 Hybrid V1 and V2 fixture sets each passed five analytic
+  fixtures and border checks. SurfaceWorld and FloatingIslands passed BuildHost actor validation at
+  25 cm. Water stayed fixed; carve and fill remained unrestricted.
+- Standalone W1/W8/W12 produced identical hashes for the full 2,553-tile view: density
+  `c10697a8f48380c7`, mesh `e75c9119a1498cd5`, payload `49a9a8d1835a6c8c`, topology
+  `edcb23288b5e8724`.
+- BuildHost SurfaceWorld W1/W8/W16 matrix was stable: density `0cd2a1a4152ee4aa`, mesh
+  `a06243aee16b65d5`, payload `c700162935c262d7`, topology `0af901aa42b452bc`. FloatingIslands
+  W1/W8/W16 was stable: density `4dcfb37585d7d986`, mesh `f14f76fbf065c6ed`, payload
+  `53035c45fd1a082e`, topology `23550100654a4ec3`. W16 was a logical partition with the process
+  still capped to 12 executing CPUs.
+
+Far mesh hashes differ from S9 as expected under recipe version 3; current-build determinism passes.
+
+## Matched captures
+
+All captures are 640×400 and under 22 KB. Each was produced at 60 fps with VSync on, then the
+Standalone viewer was closed after its back-buffer capture. Raw 1280×800 PNGs and run logs are under
+`Saved/BuildHost/Round14/CaptureRaw/`.
+
+| View | S9 sampling control, 128 voxels | S10 default, MC spacing |
+|---|---|---|
+| Far horizon, camera 0,-35,-487.94,0,-22 | [s9_far_horizon.jpg](captures/s9_far_horizon.jpg) (21.9 KB) | [s10_far_horizon.jpg](captures/s10_far_horizon.jpg) (18.0 KB) |
+| Cap, camera 0,-35,-487.94,0,22.42 | [s9_cap.jpg](captures/s9_cap.jpg) (10.8 KB) | [s10_cap.jpg](captures/s10_cap.jpg) (10.8 KB) |
+
+The cap is low contrast in this view, as in Round8; the 2 cm agreement, triangle census and ray
+coverage provide the cap acceptance evidence.
+
+## Builds, commands and hashes
+
+Builds on the final source:
+
+~~~powershell
+.\Tools\BuildVoxelForgeCoreHost.ps1 -MaxParallelActions 12 -TimeoutSeconds 900
+.\Standalone\Build.ps1 -Target All -CompileWorkers 12 -BuildPriority Normal
+~~~
+
+The fresh Standalone determinism processes used the same command with workers 1, 8 and 12:
+
+~~~powershell
+foreach ($workers in @(1, 8, 12)) {
+    .\Standalone\bin\VoxelForgeCoreStandalone.exe --workers=$workers --world-assembler-prototype --stream-benchmark --stream-hash --force-generate --clip-radius=3 --max-clip-level=8 --camera=0,-35,-487.94,0,-22 --far-horizon-lod8-step=0 --process-priority=Normal --process-affinity=4095 --frame-limit=60
+}
+~~~
+
+The current-build duplicate count and same-binary step-128 control used:
+
+~~~powershell
+.\Standalone\bin\VoxelForgeCoreStandalone.exe --workers=12 --world-assembler-prototype --stream-pipeline --stream-hash --profile-far-column-overlap --force-generate --clip-radius=3 --max-clip-level=8 --camera=0,-35,-487.94,0,-22 --far-horizon-lod8-step=0 --process-priority=Normal --process-affinity=4095 --frame-limit=60
+.\Standalone\bin\VoxelForgeCoreStandalone.exe --workers=12 --world-assembler-prototype --stream-pipeline --stream-hash --profile-far-column-overlap --force-generate --clip-radius=3 --max-clip-level=8 --camera=0,-35,-487.94,0,-22 --far-horizon-lod8-step=128 --process-priority=Normal --process-affinity=4095 --frame-limit=60
+~~~
+
+Quality and BuildHost actor commands:
+
+~~~powershell
+.\Standalone\bin\VoxelForgeCoreStandalone.exe --world-assembler-audit --workers=12 --clip-radius=3 --max-clip-level=8 --camera=0,-35,-487.94,0,-22 --process-priority=Normal --process-affinity=4095 --frame-limit=60
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -CoreVoxelSizeCm 25 -TimeoutSeconds 900
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -FloatingIslandsOnly -CoreVoxelSizeCm 25 -TimeoutSeconds 900
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -CoreOffTest -CoreVoxelSizeCm 12.5 -TimeoutSeconds 900
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -HybridFixturesOnly -CoreMesherRecipe WorldAssemblerHybridV1 -CoreVoxelSizeCm 25 -TimeoutSeconds 900
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -HybridFixturesOnly -CoreMesherRecipe WorldAssemblerHybridV2 -CoreVoxelSizeCm 25 -TimeoutSeconds 900
+~~~
+
+The two fresh actor traces differed only in speed, 600 or 4,000 cm/s:
+
+~~~powershell
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -StreamingTraceOnly -StartupApplyBoost 0 -StreamingOrder Legacy -NearReserveMode Dynamic -CoreVoxelSizeCm 25 -StreamingCollisionLookahead 1 -TestMoveDirection '0,1,0' -CoreRegionConcurrentAdmission 1 -StreamingResultBacklogCap 256 -TestMoveSpeedCmPerSecond 600 -TimeoutSeconds 900
+.\Tools\TestVoxelForgeCoreWorldHost.ps1 -StreamingTraceOnly -StartupApplyBoost 0 -StreamingOrder Legacy -NearReserveMode Dynamic -CoreVoxelSizeCm 25 -StreamingCollisionLookahead 1 -TestMoveDirection '0,1,0' -CoreRegionConcurrentAdmission 1 -StreamingResultBacklogCap 256 -TestMoveSpeedCmPerSecond 4000 -TimeoutSeconds 900
+~~~
+
+Final binary SHA-256:
+
+| Binary | SHA-256 |
+|---|---|
+| BuildHost UnrealEditor-VoxelForgeCore.dll | `D87CC56BACCDE6559705EEAEA7DB73D1A6ABF79484D37A3887B94A9FD62BABD3` |
+| BuildHost UnrealEditor-VoxelForge.dll | `9D0522ECC9A6AC52D9F3ACC2FD44399FE70F557C5F11D0203AB4C4B8EE75C198` |
+| BuildHost UnrealEditor-VoxelForgeEditor.dll | `AA196DA5A6DB3C84B5EC4F002AEBC787386DBB8F2798F5D1EEC03010BF642BBA` |
+| Standalone VoxelForgeCoreStandalone.exe | `E316D7E3E0B3D3639DAE61D6E2D1091F38C59A210B3B7DD8124928D21A8119A5` |
+
+## Run notes, files and safety review
+
+- BuildHost and Standalone ran at Normal priority with no more than 12 executing CPUs; free memory
+  was above 17 GB before the final launches. BuildHost peak private memory was 3.76 GiB for
+  SurfaceWorld, 3.27 GiB for FloatingIslands, 3.39 GiB for the 6 m/s trace and 3.67 GiB for the
+  40 m/s trace. The Standalone overlap/control processes peaked below 0.72 GiB. No process exceeded
+  8 GiB, and no launch overlapped another Unreal/Standalone process.
+- Standalone’s first compile attempt failed in `StandaloneViewer.cpp` because one helper referred to
+  `App` outside its scope; that reference was corrected and the final build passed. The existing
+  `vswhere.exe` lookup warning and `VoxelStrateManager.cpp` C4838 warnings remained.
+- Three BuildHost CVar attempts (direct argument and two `ExecCmds` forms) read back zero and did not
+  change the worker grid; that no-op CVar/harness path was removed. An early Standalone step-128
+  attempt also did not reach the pipeline; CLI pass-through was corrected and the final same-binary
+  step-128 control above is effective. No CVar remains in the final source.
+- One high-pitch cap capture was black and was discarded. A separate early capture shell lacked its
+  memory-probe type because the PowerShell session was fresh; that capture completed without a
+  pre-launch memory gate. The matched final captures were rerun with the gate active. No
+  `0xC0000142` occurred and no run needed retrying.
+- The only UECC directory was the pre-existing
+  `UECC-Windows-F1A3EFD5469F5DD62E68EBBACAC84376_0000`, timestamped 2026-09-17; no new UECC folder
+  was created.
+- No new source files. Changed source files and compile spots:
+
+| File | Compile spot |
+|---|---|
+| `Standalone/Core/include/VoxelForgeCore/VoxelForgeCore.h`, `Standalone/Core/src/VoxelForgeCore.cpp`, `Standalone/Core/src/WorldAssemblerInternal.h` | VoxelForgeCore in Standalone and BuildHost |
+| `Standalone/Source/StreamingWorld.h`, `Standalone/Source/StandaloneViewer.cpp` | StandaloneViewer / VoxelForgeCoreStandalone.exe |
+| `Source/VoxelForgeEditor/Private/VoxelForgeExploreCommandlet.cpp` | BuildHost VoxelForgeEditor module |
+| `Tools/TestVoxelForgeCoreWorldHost.ps1` | PowerShell harness only; recipe-specific fixture logs |
+
+Async-safety review: no actor async source changed. Epoch checks, MPSC queues, EndPlay draining,
+worker `bShuttingDown` checks and `ModsLock` remain unchanged. Region-page publication, shared_ptr
+lifetime and concurrent eviction remain unchanged. New duplicate capture stays thread-local and is
+copied into the tile result; its worker-id hash is diagnostic only. UObject and RealtimeMeshComponent
+mutation remain on the game thread. No owner `.uproject`, editor, `.uasset`, or RealtimeMeshComponent
+file was modified. `git diff --check` passed. No commit, push or stash.
+
+### Dialogue
+
+**User:** Keep the 12-thread cap; count exclusive LOD8 costs first, optimize the planar far path, and verify quality and determinism.
+
+**Codex:** The LOD8 interior now follows the MC spacing, with 128-voxel boundary strips preserved. The owner-plan LOD8 p95 fell from 59.848 ms to 13.933 ms; cap and ground gates, both BuildHost actor matrices, current-build worker hashes, and the 40 m/s support ring passed.
@@ -1720,6 +1720,7 @@ namespace
        bool Keys[256]{};
        int32 Seed=0;
        int32 WorkerCount=8;
+        int32 FarHorizonLOD8InteriorStepVoxels=0;
        int32 ClipRadius=3;
        int32 MaxClipLevelOverride=-1;
        int32 CaptureTileLimit=0;
@@ -2903,7 +2904,8 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
            Streamer=std::make_unique<FStandaloneStreamingGenerator>(*World,StreamWorkers,false,
                (!bShapeWorld&&MeshCache.IsLoaded())?&MeshCache:nullptr,
                bFarShapeStagePending?World->FullResClipLevels-1:-1,
-                false,false,false,false,ShapeWorld.get());
+                false,false,false,false,ShapeWorld.get(),false,
+                FarHorizonLOD8InteriorStepVoxels);
            if(bGpuFarTimelineEnabled)
                Streamer->EnableColdTimelineTrace(ColdProcessStart,&ColdTimelineFrameOrdinal);
            if(bGpuFarEnabled&&ShapeWorld&&ShapeWorld->hasFarWorld())
@@ -6974,7 +6976,8 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
        const FVector& CameraPositionVoxels,int32 WorkerCount,int32 MaxLevel,
        VoxelForgeCore::DetailVariant DetailVariant,const VoxelForgeCore::JobScheduler& Scheduler,
        bool bHashDensity,bool bSkipUvAndColors,bool bSkipMaterialGroups,bool bSkipUV,bool bSkipColors,
-        std::chrono::steady_clock::time_point ColdStart)
+        std::chrono::steady_clock::time_point ColdStart,bool bProfileFarColumnOverlap,
+        int32 FarHorizonLOD8InteriorStepVoxels)
    {
        using Clock=std::chrono::steady_clock;
        FStandaloneOwnerWorld& World=*OwnerWorld;
@@ -7042,7 +7045,8 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
        const auto ShapeReady=Clock::now();
        const double ShapeSeconds=std::chrono::duration<double>(ShapeReady-ShapeBuildStart).count();
        FStandaloneStreamingGenerator Streamer(World,WorkerCount,bHashDensity,nullptr,MaxLevel,
-            bSkipUvAndColors,bSkipMaterialGroups,bSkipUV,bSkipColors,&Shape);
+            bSkipUvAndColors,bSkipMaterialGroups,bSkipUV,bSkipColors,&Shape,bProfileFarColumnOverlap,
+            FarHorizonLOD8InteriorStepVoxels);
        const auto StreamStart=Clock::now();
        const FStandaloneStreamingUpdate Update=Streamer.StartWithDesired(Desired);
        if(Update.DesiredTiles!=static_cast<int32>(Desired.Tiles.size()))
@@ -7055,6 +7059,43 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
        std::vector<FHashedTile> DensityRows,MeshRows,PayloadRows,TopologyRows;
        int32 Finished=0,NeighborhoodFinished=0,FullDetailFinished=0;
        int32 FullDetailExpected=0;
+        struct FColumnXY
+        {
+            std::int64_t X=0,Y=0;
+            bool operator==(const FColumnXY&)const=default;
+        };
+        struct FColumnXYHash
+        {
+            std::size_t operator()(const FColumnXY& Value)const noexcept
+            {
+                const std::size_t X=std::hash<std::int64_t>{}(Value.X);
+                const std::size_t Y=std::hash<std::int64_t>{}(Value.Y);
+                return X^(Y+static_cast<std::size_t>(0x9E3779B9u)+(X<<6)+(X>>2));
+            }
+        };
+        struct FFirstColumnUse
+        {
+            FVoxelTileKey Tile;
+            std::uint64_t WorkerHash=0;
+        };
+        std::unordered_map<FColumnXY,FFirstColumnUse,FColumnXYHash> LOD8ColumnFirstUse;
+        std::uint64_t LOD8ColumnDuplicateEvents=0,LOD8NeighbourDuplicateEvents=0;
+        std::uint64_t LOD8CrossWorkerNeighbourDuplicateEvents=0;
+        std::size_t LOD8ColumnCaptureTiles=0;
+        bool bLOD8ColumnCaptureComplete=true;
+        std::array<double,9> WorkerSecondsByLOD{};
+        std::array<double,9> ColumnEvalMsByLOD{},MarchingExclusiveMsByLOD{};
+        std::array<double,9> GroundRefineExclusiveMsByLOD{},CapRefineExclusiveMsByLOD{};
+        std::array<double,9> MeshAssemblyMsByLOD{};
+        std::array<std::uint64_t,9> TileCountByLOD{};
+        const auto AreLOD8Neighbours=[](const FVoxelTileKey& A,const FVoxelTileKey& B)
+        {
+            if(A.Level!=8||B.Level!=8)return false;
+            const std::int64_t DX=std::abs(static_cast<std::int64_t>(A.Coord.X)-B.Coord.X);
+            const std::int64_t DY=std::abs(static_cast<std::int64_t>(A.Coord.Y)-B.Coord.Y);
+            const std::int64_t DZ=std::abs(static_cast<std::int64_t>(A.Coord.Z)-B.Coord.Z);
+            return std::max({DX,DY,DZ})<=1&&(DX+DY+DZ)>0;
+        };
        uint64 NativeSolidBoxes=0,NativeAirBoxes=0,NativeMixedBoxes=0,NativeUnknownBoxes=0;
        uint64 NativeFieldCalls=0,NativeColumnHits=0,NativeColumnMisses=0,NativeMeshingSkips=0;
        double NativeClassificationMilliseconds=0.0,NativeColumnComputeMilliseconds=0.0;
@@ -7070,6 +7111,41 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
            for(const FStandaloneCpuTile& Tile:Ready)
            {
                ++Finished;
+                if(Tile.Key.Level>=0&&Tile.Key.Level<static_cast<int32>(TileCountByLOD.size()))
+                {
+                    const std::size_t LOD=static_cast<std::size_t>(Tile.Key.Level);
+                    ++TileCountByLOD[LOD];
+                    WorkerSecondsByLOD[LOD]+=Tile.WorkerSeconds;
+                    ColumnEvalMsByLOD[LOD]+=Tile.CoreDiagnostics.columnEvaluationExclusiveMilliseconds;
+                    MarchingExclusiveMsByLOD[LOD]+=Tile.CoreDiagnostics.marchingCubesExclusiveMilliseconds;
+                    GroundRefineExclusiveMsByLOD[LOD]+=Tile.CoreDiagnostics.groundRefinementExclusiveMilliseconds;
+                    CapRefineExclusiveMsByLOD[LOD]+=Tile.CoreDiagnostics.capRefinementExclusiveMilliseconds;
+                    MeshAssemblyMsByLOD[LOD]+=Tile.CoreDiagnostics.meshAssemblyMilliseconds;
+                }
+                if(bProfileFarColumnOverlap&&Tile.Key.Level==8)
+                {
+                    ++LOD8ColumnCaptureTiles;
+                    bLOD8ColumnCaptureComplete=bLOD8ColumnCaptureComplete
+                        &&Tile.CoreDiagnostics.columnCoordinateCaptureComplete;
+                    std::vector<std::array<std::int64_t,2>> Coordinates=
+                        Tile.CoreDiagnostics.evaluatedColumnCoordinates;
+                    std::sort(Coordinates.begin(),Coordinates.end());
+                    Coordinates.erase(std::unique(Coordinates.begin(),Coordinates.end()),Coordinates.end());
+                    for(const auto& Coordinate:Coordinates)
+                    {
+                        const FColumnXY XY{Coordinate[0],Coordinate[1]};
+                        const auto [First,Inserted]=LOD8ColumnFirstUse.try_emplace(XY,
+                            FFirstColumnUse{Tile.Key,Tile.CoreDiagnostics.columnEvaluationWorkerHash});
+                        if(Inserted)continue;
+                        ++LOD8ColumnDuplicateEvents;
+                        if(AreLOD8Neighbours(First->second.Tile,Tile.Key))
+                        {
+                            ++LOD8NeighbourDuplicateEvents;
+                            if(First->second.WorkerHash!=Tile.CoreDiagnostics.columnEvaluationWorkerHash)
+                                ++LOD8CrossWorkerNeighbourDuplicateEvents;
+                        }
+                    }
+                }
                WholeViewReady=std::max(WholeViewReady,Tile.CompletedAt);
                if(Neighborhood.contains(Tile.Key))
                {
@@ -7115,6 +7191,22 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
            }
        }
        Streamer.Stop();
+        if(bProfileFarColumnOverlap)
+        {
+            std::printf("[WorldAssemblerLOD8ColumnOverlap] tiles=%zu unique_xy_columns=%zu repeated_tile_evaluations=%llu neighbouring_duplicate_evaluations=%llu cross_worker_neighbouring_duplicates=%llu capture_complete=%d\n",
+                LOD8ColumnCaptureTiles,LOD8ColumnFirstUse.size(),
+                static_cast<unsigned long long>(LOD8ColumnDuplicateEvents),
+                static_cast<unsigned long long>(LOD8NeighbourDuplicateEvents),
+                static_cast<unsigned long long>(LOD8CrossWorkerNeighbourDuplicateEvents),
+                bLOD8ColumnCaptureComplete?1:0);
+        }
+        for(std::size_t LOD=0;LOD<TileCountByLOD.size();++LOD)
+        {
+            std::printf("[WorldAssemblerLODWorker] lod=%zu tiles=%llu worker_sum_s=%.6f column_eval_exclusive_ms=%.3f mc_exclusive_ms=%.3f ground_refine_exclusive_ms=%.3f cap_refine_exclusive_ms=%.3f mesh_assembly_ms=%.3f\n",
+                LOD,static_cast<unsigned long long>(TileCountByLOD[LOD]),WorkerSecondsByLOD[LOD],
+                ColumnEvalMsByLOD[LOD],MarchingExclusiveMsByLOD[LOD],
+                GroundRefineExclusiveMsByLOD[LOD],CapRefineExclusiveMsByLOD[LOD],MeshAssemblyMsByLOD[LOD]);
+        }
        const double NeighborhoodSeconds=std::chrono::duration<double>(NeighborhoodReady-ColdStart).count();
        const double NeighborhoodMeshSeconds=std::chrono::duration<double>(NeighborhoodReady-ShapeReady).count();
        const double FullDetailSeconds=std::chrono::duration<double>(FullDetailReady-ColdStart).count();
@@ -7160,7 +7252,8 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
                static_cast<unsigned long long>(HashTileRows(TopologyRows)));
        }
        return NeighborhoodFinished==static_cast<int32>(Neighborhood.size())
-            &&FullDetailFinished==FullDetailExpected&&Finished==Update.DesiredTiles&&bHashesPassing?0:6;
+            &&FullDetailFinished==FullDetailExpected&&Finished==Update.DesiredTiles&&bHashesPassing
+            &&(!bProfileFarColumnOverlap||(bLOD8ColumnCaptureComplete&&LOD8ColumnCaptureTiles>0))?0:6;
    }
    int RunStreamingBenchmark(FStandaloneOwnerWorld& World,VoxelForgeCore::World* CoreWorld,
                              const FVector& CameraPositionVoxels,
@@ -9508,6 +9601,7 @@ int main(int Argc,char** Argv)
    std::string WorldAssemblyManifestOutputPath;
    bool bStreamBenchmark=false;
    bool bStreamPipeline=false;
+    bool bProfileFarColumnOverlap=false;
    bool bCoarseFirstStreamOrder=false;
    bool bProfileDetailBand=false;
    bool bPassageDetailAuditOnly=false;
@@ -9530,6 +9624,9 @@ int main(int Argc,char** Argv)
    {
        const std::string_view Arg=Argv[I];
        if(Arg.starts_with("--capture="))App.CapturePath=std::string(Arg.substr(10));
+        else if(Arg.starts_with("--far-horizon-lod8-step="))
+            App.FarHorizonLOD8InteriorStepVoxels=std::max(0,std::atoi(
+                std::string(Arg.substr(std::string_view("--far-horizon-lod8-step=").size())).c_str()));
        else if(Arg.starts_with("--capture-flight-sequence-prefix="))
            App.FlightCaptureSequencePrefix=std::string(
                Arg.substr(std::string_view("--capture-flight-sequence-prefix=").size()));
@@ -9642,6 +9739,8 @@ int main(int Argc,char** Argv)
        else if(Arg=="--coarse-first-stream-order")bCoarseFirstStreamOrder=true;
        else if(Arg=="--stream-pipeline")
        {bStreamPipeline=true;bStreamBenchmark=true;App.bShapeWorld=true;App.bForceGenerate=true;}
+        else if(Arg=="--profile-far-column-overlap")
+        {bProfileFarColumnOverlap=true;bStreamPipeline=true;bStreamBenchmark=true;App.bShapeWorld=true;App.bForceGenerate=true;}
        else if(Arg=="--edit-benchmark")
        {bEditBenchmark=true;bStreamBenchmark=true;App.bShapeWorld=true;}
        else if(Arg=="--stream-hash")bStreamHash=true;
@@ -9858,7 +9957,8 @@ int main(int Argc,char** Argv)
                FVector(App.Position.X*4.0,App.Position.Y*4.0,App.Position.Z*4.0),
                App.WorkerCount,StreamBenchmarkMaxLevel,App.ShapeDetailVariant,App.CoreScheduler,
                bStreamHash||!BakeMeshCachePath.empty(),bSkipUvAndColors,bSkipMaterialGroups,
-                bSkipUV,bSkipColors,ColdProcessStart);
+                bSkipUV,bSkipColors,ColdProcessStart,bProfileFarColumnOverlap,
+                App.FarHorizonLOD8InteriorStepVoxels);
        if(bEditBenchmark)
            return RunEditTransactionBenchmark(*App.World,*App.ShapeWorld,
                FVector(App.Position.X*4.0,App.Position.Y*4.0,App.Position.Z*4.0),App.WorkerCount);
@@ -423,11 +423,15 @@ public:
                                           bool bInSkipMaterialGroups=false,
                                           bool bInSkipUV=false,
                                           bool bInSkipColors=false,
-                                           VoxelForgeCore::World* InCoreWorld=nullptr)
+                                           VoxelForgeCore::World* InCoreWorld=nullptr,
+                                           bool bInCaptureFarColumnCoordinates=false,
+                                           int32 InLod8HorizonInteriorStepVoxels=0)
        :World(&InWorld),WorkerCount(FMath::Clamp(InWorkerCount,1,16)),bHashDensity(bInHashDensity),
         MeshCache(InMeshCache),MaxLevelFilter(InMaxLevelFilter),
         CoreWorld(InCoreWorld),bSkipUvAndColors(bInSkipUvAndColors),bSkipMaterialGroups(bInSkipMaterialGroups),
-         bSkipUV(bInSkipUV),bSkipColors(bInSkipColors)
+         bSkipUV(bInSkipUV),bSkipColors(bInSkipColors),
+         bCaptureFarColumnCoordinates(bInCaptureFarColumnCoordinates),
+         Lod8HorizonInteriorStepVoxels(std::max(0,InLod8HorizonInteriorStepVoxels))
    {
        VoxelGenLOD::InitializeConsoleSwitches();
        UVoxelMarchingCubesMesher::InitializeConsoleSwitches();
@@ -795,6 +799,8 @@ private:
            Options.bandMinZVoxel=Job.BandZMin;Options.bandMaxZVoxel=Job.BandZMax;
            Options.hashDensity=bHashDensity;Options.skipUvAndColors=bSkipUvAndColors;
            Options.skipMaterialGroups=bSkipMaterialGroups;Options.skipUv=bSkipUV;Options.skipColors=bSkipColors;
+            Options.captureColumnCoordinates=bCaptureFarColumnCoordinates&&Level==8;
+            Options.lod8HorizonInteriorStepVoxels=Lod8HorizonInteriorStepVoxels;
            std::string Error;
            auto Result=CoreWorld->generateTile(
                {{Job.Key.Coord.X,Job.Key.Coord.Y,Job.Key.Coord.Z},Job.Key.Level},Options,Error);
@@ -965,6 +971,8 @@ private:
    bool bSkipMaterialGroups=false;
    bool bSkipUV=false;
    bool bSkipColors=false;
+    bool bCaptureFarColumnCoordinates=false;
+    int32 Lod8HorizonInteriorStepVoxels=0;
    std::atomic<uint64> CacheHitCount{0};
    mutable std::mutex Mutex;
    std::condition_variable Wake;