feat: Semantische Suche über Chat-History (memory_search)

- Lokales Embedding-Model (all-MiniLM-L6-v2, ONNX, CPU)
- EmbeddingService: WordPiece-Tokenizer + Mean Pooling (384 Dim)
- VectorSearchService: SQLite-basierte Vektor-Speicherung + Cosine Similarity
- EmbeddingBackgroundService: Backfill bestehender Messages + Live-Queue
- Neues Tool memory_search: Semantische Suche über alle Sessions (inkl. archivierte)
- ~9000 Messages embedded, Suche über komplette Chat-History

gott.csproj

@@ -36,6 +36,7 @@
     <PackageReference Include="Microsoft.Extensions.Hosting.WindowsServices" Version="10.0.3" />
     <PackageReference Include="Dapper" Version="2.1.66" />
     <PackageReference Include="Microsoft.Data.Sqlite" Version="10.0.3" />
+    <PackageReference Include="Microsoft.ML.OnnxRuntime" Version="1.24.3" />
     <PackageReference Include="SixLabors.ImageSharp" Version="3.1.12" />
   </ItemGroup>