code reveiw fix

Author: KSemenenko

AGENTS.md

@@ -7,6 +7,7 @@
 - Keep default prompts in static C# classes; do not rely on prompt files under `prompts/` for built-in templates.
 - Register language models through Microsoft.Extensions.AI keyed services; avoid bespoke `LanguageModelConfig` providers.
 - Always run `dotnet format GraphRag.slnx` before finishing work.
+- Always run `dotnet test GraphRag.slnx` before finishing work, after building.
 
 # Conversations
 any resulting updates to agents.md should go under the section "## Rules to follow"

Directory.Build.props

@@ -25,8 +25,8 @@
         <RepositoryUrl>https://github.com/managedcode/graphrag</RepositoryUrl>
         <PackageProjectUrl>https://github.com/managedcode/graphrag</PackageProjectUrl>
         <Product>Managed Code GraphRag</Product>
-        <Version>0.0.3</Version>
-        <PackageVersion>0.0.3</PackageVersion>
+        <Version>0.0.4</Version>
+        <PackageVersion>0.0.4</PackageVersion>
 
     </PropertyGroup>
     <PropertyGroup Condition="'$(GITHUB_ACTIONS)' == 'true'">

src/ManagedCode.GraphRag/Community/CommunityBuilder.cs

@@ -181,12 +181,9 @@ private static List<List<string>> BuildUsingConnectedComponents(
                     .OrderBy(_ => random.Next())
                     .ToList();
 
-                foreach (var neighbor in orderedNeighbors)
+                foreach (var neighbor in orderedNeighbors.Where(visited.Add))
                 {
-                    if (visited.Add(neighbor))
-                    {
-                        queue.Enqueue(neighbor);
-                    }
+                    queue.Enqueue(neighbor);
                 }
             }
 

src/ManagedCode.GraphRag/Config/HeuristicMaintenanceConfig.cs

@@ -1,7 +1,7 @@
 namespace GraphRag.Config;
 
 /// <summary>
-/// Represents heuristic controls that fine-tune ingestion and graph maintenance behaviour.
+/// Represents heuristic controls that fine-tune ingestion and graph maintenance behavior.
 /// The defaults mirror the semantics implemented in the GraphRag.Net demo service where
 /// ingestion aggressively deduplicates, trims by token budgets, and repairs sparse graphs.
 /// </summary>

src/ManagedCode.GraphRag/Indexing/Heuristics/GraphExtractionHeuristics.cs

@@ -229,12 +229,9 @@ public void Add(RelationshipSeed seed)
             _count++;
             _description = SelectDescription(_description, seed.Description);
 
-            foreach (var textUnit in seed.TextUnitIds)
+            foreach (var textUnit in seed.TextUnitIds.Where(static id => !string.IsNullOrWhiteSpace(id)))
             {
-                if (!string.IsNullOrWhiteSpace(textUnit))
-                {
-                    _textUnits.Add(textUnit);
-                }
+                _textUnits.Add(textUnit);
             }
         }
 
@@ -279,6 +276,7 @@ public RelationshipSeed ToSeed(HeuristicMaintenanceConfig heuristics)
                 return incoming;
             }
 
+            // Prefer shorter descriptions to keep summaries concise and token efficient.
             return incoming.Length < existing.Length ? incoming : existing;
         }
     }

src/ManagedCode.GraphRag/Indexing/Heuristics/TextUnitHeuristicProcessor.cs

@@ -44,6 +44,10 @@ public static async Task<IReadOnlyList<TextUnitRecord>> ApplyAsync(
         {
             return await DeduplicateAsync(filtered, generator, heuristics, cancellationToken).ConfigureAwait(false);
         }
+        catch (OperationCanceledException)
+        {
+            throw;
+        }
         catch (Exception ex)
         {
             logger?.LogWarning(ex, "Failed to execute semantic deduplication heuristics. Retaining filtered text units only.");
@@ -198,17 +202,9 @@ private static double CosineSimilarity(IReadOnlyList<float> left, IReadOnlyList<
     private static List<string> DeduplicatePreservingOrder(IEnumerable<string> source)
     {
         var seen = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
-        var result = new List<string>();
-
-        foreach (var item in source)
-        {
-            if (seen.Add(item))
-            {
-                result.Add(item);
-            }
-        }
-
-        return result;
+        return source
+            .Where(seen.Add)
+            .ToList();
     }
 
     private static IEmbeddingGenerator<string, Embedding<float>>? ResolveEmbeddingGenerator(
@@ -248,7 +244,8 @@ private sealed class DeduplicationCluster(TextUnitRecord record, float[] vector)
         public void Update(TextUnitRecord incoming)
         {
             var mergedDocuments = MergeLists(Record.DocumentIds, incoming.DocumentIds);
-            var tokenCount = Math.Min(Record.TokenCount, incoming.TokenCount);
+            // Sum token counts so merged records reflect their combined budget.
+            var tokenCount = (int)Math.Min((long)Record.TokenCount + incoming.TokenCount, int.MaxValue);
 
             Record = Record with
             {
@@ -259,26 +256,11 @@ public void Update(TextUnitRecord incoming)
 
         private static string[] MergeLists(IReadOnlyList<string> first, IReadOnlyList<string> second)
         {
-            var merged = new List<string>(first.Count + second.Count);
             var seen = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
-
-            foreach (var item in first)
-            {
-                if (seen.Add(item))
-                {
-                    merged.Add(item);
-                }
-            }
-
-            foreach (var item in second)
-            {
-                if (seen.Add(item))
-                {
-                    merged.Add(item);
-                }
-            }
-
-            return merged.ToArray();
+            return first
+                .Concat(second)
+                .Where(seen.Add)
+                .ToArray();
         }
     }
 }

src/ManagedCode.GraphRag/Indexing/Workflows/CreateBaseTextUnitsWorkflow.cs

@@ -24,8 +24,8 @@ public static WorkflowDelegate Create()
 
             var textUnits = new List<TextUnitRecord>();
             var callbacks = context.Callbacks;
-            var chunkingConfig = config.Chunks;
             var heuristicConfig = config.Heuristics ?? new HeuristicMaintenanceConfig();
+            var chunkingConfig = CloneChunkingConfig(config.Chunks);
             if (heuristicConfig.MinimumChunkOverlap > 0 && chunkingConfig.Overlap < heuristicConfig.MinimumChunkOverlap)
             {
                 chunkingConfig.Overlap = heuristicConfig.MinimumChunkOverlap;
@@ -102,6 +102,22 @@ public static WorkflowDelegate Create()
         return builder.ToString();
     }
 
+    private static ChunkingConfig CloneChunkingConfig(ChunkingConfig source)
+    {
+        return new ChunkingConfig
+        {
+            Size = source.Size,
+            Overlap = source.Overlap,
+            EncodingModel = source.EncodingModel,
+            Strategy = source.Strategy,
+            PrependMetadata = source.PrependMetadata,
+            ChunkSizeIncludesMetadata = source.ChunkSizeIncludesMetadata,
+            GroupByColumns = source.GroupByColumns is { Count: > 0 }
+                ? new List<string>(source.GroupByColumns)
+                : new List<string>()
+        };
+    }
+
     private static ChunkingConfig CreateEffectiveConfig(ChunkingConfig original, int metadataTokens)
     {
         if (!original.ChunkSizeIncludesMetadata || metadataTokens == 0)

tests/ManagedCode.GraphRag.Tests/Integration/HeuristicMaintenanceIntegrationTests.cs

@@ -126,7 +126,7 @@ public async Task HeuristicMaintenanceWorkflow_AppliesBudgetsAndSemanticDeduplic
         Assert.Equal(2, merged.DocumentIds.Count);
         Assert.Contains("doc-1", merged.DocumentIds, StringComparer.OrdinalIgnoreCase);
         Assert.Contains("doc-2", merged.DocumentIds, StringComparer.OrdinalIgnoreCase);
-        Assert.Equal(35, merged.TokenCount);
+        Assert.Equal(75, merged.TokenCount);
 
         var survivor = Assert.Single(processed, unit => unit.Id == "b");
         Assert.Single(survivor.DocumentIds);