feat: AutoContext-Suche grundlegend verbessern + Embedding-Debug-Tool

Hybrid-Suche (Vektor + FTS5-Keyword), Recency-Boost, Query-Erweiterung
(letzte 2-3 User-Messages), Chunk-Overlapping, FullText-Speicherung,
konfigurierbares Embedding-Modell/MaxSeqLen, deduplizierter AutoContext-
Code (Streaming + CLI shared), Admin-Diagnose-Seite mit Re-Embed-Funktion.
Threshold von 0.45 auf 0.35 gesenkt (Hybrid-Suche ist präziser).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Services/AnthropicService.Cli.cs

@@ -33,6 +33,7 @@ public partial class AnthropicService
         RemoteConnectionManager remoteMgr = null,
         string unityMcpUrl = null,
         string unityMcpToken = null,
+        bool useAutoContext = true,
         CancellationToken workCt = default,
         CancellationToken sseCt = default)
     {
@@ -77,6 +78,21 @@ public partial class AnthropicService
             }
 
 
+            // ── Automatische Kontext-Injektion via Embedding-Suche (wie in StreamChat) ──
+            if (useAutoContext && messages.Count > 0)
+            {
+                try
+                {
+                    var autoCtx = await BuildAutoContextAsync(messages, chainId, agentId);
+                    if (autoCtx != null)
+                        systemText.AppendLine(autoCtx);
+                }
+                catch (Exception ex)
+                {
+                    Console.WriteLine($"[AutoContext/CLI] Error: {ex.Message}");
+                }
+            }
+
             // Letzte User-Message als Prompt extrahieren
             var prompt = ExtractLastUserText(messages) ?? "";
 
@@ -118,14 +134,16 @@ public partial class AnthropicService
                             // Text-Puffer flushen bevor Tool-Use gespeichert wird (korrekte Reihenfolge in DB)
                             if (fullText.Length > 0)
                             {
-                                await _db.SaveMessage(new MessageRecord
+                                var textForEmbed = fullText.ToString();
+                                var msgId = await _db.SaveMessage(new MessageRecord
                                 {
                                     ChainId = chainId,
                                     Iteration = 1,
                                     Role = "assistant",
                                     Type = "text",
-                                    Content = fullText.ToString()
+                                    Content = textForEmbed
                                 });
+                                _embeddingBg?.Enqueue(msgId, chainId, sessionId, agentId, "assistant", textForEmbed);
                                 fullText.Clear();
                             }
                             var mappedName = MapCliToolName(evt.ToolName);
@@ -235,14 +253,16 @@ public partial class AnthropicService
             // Antwort in DB speichern
             if (fullText.Length > 0)
             {
-                await _db.SaveMessage(new MessageRecord
+                var finalText = fullText.ToString();
+                var msgId = await _db.SaveMessage(new MessageRecord
                 {
                     ChainId = chainId,
                     Iteration = 1,
                     Role = "assistant",
                     Type = "text",
-                    Content = fullText.ToString()
+                    Content = finalText
                 });
+                _embeddingBg?.Enqueue(msgId, chainId, sessionId, agentId, "assistant", finalText);
             }
 
             // Token-Usage vom CLI-Result übernehmen

Services/AnthropicService.Streaming.cs

@@ -58,38 +58,13 @@ public partial class AnthropicService
         try
         {
             // ── Automatische Kontext-Injektion via Embedding-Suche ──
-            if (useAutoContext && _vectorSearch != null && systemPrompt != null && messages.Count > 0)
+            if (useAutoContext)
             {
                 try
                 {
-                    // Letzte User-Message als Query extrahieren
-                    var lastUserText = ExtractLastUserText(messages);
-                    if (!string.IsNullOrWhiteSpace(lastUserText))
-                    {
-                        var contextResults = await _vectorSearch.SearchAsync(lastUserText, agentId, topN: 5, minScore: 0.45f);
-                        // Nur Ergebnisse aus anderen Sessions (nicht aktuelle Chain) und nicht zu kurze
-                        contextResults.RemoveAll(r => r.ChainId == chainId || (r.TextPreview?.Length ?? 0) < 20);
-                        // Memory-Dateien durchsuchen
-                        var memoryResults = await _vectorSearch.SearchMemoryFilesAsync(lastUserText, agentId, topN: 3, minScore: 0.45f);
-
-                        if (contextResults.Count > 0 || memoryResults.Count > 0)
-                        {
-                            var ctxSb = new StringBuilder();
-                            ctxSb.AppendLine("\n<recalled_context>");
-                            ctxSb.AppendLine("Die folgende Information wurde automatisch abgerufen und könnte relevant sein:");
-                            foreach (var r in contextResults)
-                            {
-                                var date = DateTime.TryParse(r.CreatedAt, out var dt) ? dt.ToString("yyyy-MM-dd HH:mm") : r.CreatedAt;
-                                ctxSb.AppendLine($"- [Gespräch, {r.Role}, {date}]: {r.TextPreview}");
-                            }
-                            foreach (var r in memoryResults)
-                            {
-                                ctxSb.AppendLine($"- [Memory, {r.FilePath}]: {r.TextPreview}");
-                            }
-                            ctxSb.AppendLine("</recalled_context>");
-                            systemPrompt.Add(new { type = "text", text = ctxSb.ToString() });
-                        }
-                    }
+                    var autoCtx = await BuildAutoContextAsync(messages, chainId, agentId);
+                    if (autoCtx != null)
+                        systemPrompt.Add(new { type = "text", text = autoCtx });
                 }
                 catch (Exception ex)
                 {

Services/AnthropicService.cs

@@ -136,6 +136,79 @@ public partial class AnthropicService
         return null;
     }
 
+    /// <summary>Extrahiert die letzten N User-Texte für Query-Erweiterung.</summary>
+    private static string ExtractRecentUserTexts(List<object> messages, int count = 3, int maxLength = 500)
+    {
+        var texts = new List<string>();
+        for (int i = messages.Count - 1; i >= 0 && texts.Count < count; i--)
+        {
+            var json = JsonSerializer.Serialize(messages[i]);
+            var el = JsonSerializer.Deserialize<JsonElement>(json);
+            if (!el.TryGetProperty("role", out var role) || role.GetString() != "user") continue;
+            if (!el.TryGetProperty("content", out var content)) continue;
+
+            string text = null;
+            if (content.ValueKind == JsonValueKind.String)
+                text = content.GetString();
+            else if (content.ValueKind == JsonValueKind.Array)
+            {
+                foreach (var block in content.EnumerateArray())
+                {
+                    var type = block.TryGetProperty("type", out var t) ? t.GetString() : "";
+                    if (type == "text" && block.TryGetProperty("text", out var txt))
+                    { text = txt.GetString(); break; }
+                }
+            }
+            if (!string.IsNullOrWhiteSpace(text))
+                texts.Add(text);
+        }
+
+        texts.Reverse(); // chronological order
+        var combined = string.Join(" ", texts);
+        return combined.Length > maxLength ? combined.Substring(0, maxLength) : combined;
+    }
+
+    /// <summary>
+    /// Baut den AutoContext-String aus Embedding-Suche.
+    /// Shared zwischen StreamChat und StreamChatViaCli.
+    /// </summary>
+    private async Task<string> BuildAutoContextAsync(List<object> messages, string chainId, string agentId)
+    {
+        if (_vectorSearch == null || messages.Count == 0) return null;
+
+        // Query-Erweiterung: letzte 2-3 User-Messages statt nur die letzte
+        var queryText = ExtractRecentUserTexts(messages, count: 3, maxLength: 500);
+        if (string.IsNullOrWhiteSpace(queryText)) return null;
+
+        var contextResults = await _vectorSearch.SearchAsync(queryText, agentId, topN: 5, minScore: 0.35f);
+        // Note: threshold lowered from 0.45 to 0.35 because hybrid search is now more precise
+        contextResults.RemoveAll(r => r.ChainId == chainId || (r.TextPreview?.Length ?? 0) < 20);
+
+        var memoryResults = await _vectorSearch.SearchMemoryFilesAsync(queryText, agentId, topN: 3, minScore: 0.35f);
+
+        if (contextResults.Count == 0 && memoryResults.Count == 0) return null;
+
+        var ctxSb = new StringBuilder();
+        ctxSb.AppendLine("\n<recalled_context>");
+        ctxSb.AppendLine("Die folgende Information wurde automatisch abgerufen und könnte relevant sein:");
+        foreach (var r in contextResults)
+        {
+            var date = DateTime.TryParse(r.CreatedAt, out var dt) ? dt.ToString("yyyy-MM-dd HH:mm") : r.CreatedAt;
+            // Use FullText (up to 800 chars) if available, otherwise TextPreview
+            var displayText = r.FullText ?? r.TextPreview ?? "";
+            if (displayText.Length > 800) displayText = displayText.Substring(0, 800);
+            ctxSb.AppendLine($"- [Gespräch, {r.Role}, {date}]: {displayText}");
+        }
+        foreach (var r in memoryResults)
+        {
+            var displayText = r.FullText ?? r.TextPreview ?? "";
+            if (displayText.Length > 800) displayText = displayText.Substring(0, 800);
+            ctxSb.AppendLine($"- [Memory, {r.FilePath}]: {displayText}");
+        }
+        ctxSb.AppendLine("</recalled_context>");
+        return ctxSb.ToString();
+    }
+
     /// <summary>
     /// Extrahiert Bild-Blöcke aus der letzten User-Message, speichert sie als Temp-Dateien
     /// und gibt Datei-Referenz-Hinweise zurück, die der CLI-Prompt vorangestellt werden.

Services/EmbeddingBackgroundService.cs

@@ -23,6 +23,7 @@ public class EmbeddingBackgroundService : BackgroundService
     readonly ConcurrentQueue<EmbeddingJob> _queue = new();
     readonly SemaphoreSlim _signal = new(0);
     readonly string _dataPath;
+    volatile bool _reEmbedRequested;
 
     public EmbeddingBackgroundService(VectorSearchService vectorSearch, EmbeddingService embedding, string dbPath)
     {
@@ -32,6 +33,13 @@ public class EmbeddingBackgroundService : BackgroundService
         _dataPath = Path.GetDirectoryName(dbPath);
     }
 
+    /// <summary>Triggers a full re-embedding of all data.</summary>
+    public void TriggerReEmbed()
+    {
+        _reEmbedRequested = true;
+        _signal.Release();
+    }
+
     /// <summary>Enqueue eine neue Message zum Embedden.</summary>
     public void Enqueue(long messageId, string chainId, string sessionId, string agentId, string role, string text)
     {
@@ -85,6 +93,17 @@ public class EmbeddingBackgroundService : BackgroundService
                         Console.WriteLine($"[EmbeddingBG] Error embedding job: {ex.Message}");
                     }
                 }
+
+                // Check for re-embed request
+                if (_reEmbedRequested)
+                {
+                    _reEmbedRequested = false;
+                    Console.WriteLine("[EmbeddingBG] Re-embedding triggered...");
+                    await _vectorSearch.ReEmbedAllAsync();
+                    await BackfillAsync(ct);
+                    await BackfillMemoryFilesAsync(ct);
+                    Console.WriteLine("[EmbeddingBG] Re-embedding complete.");
+                }
             }
             catch (OperationCanceledException) { break; }
         }

Services/EmbeddingService.cs

@@ -10,8 +10,9 @@ using Microsoft.ML.OnnxRuntime.Tensors;
 namespace Gott.Services;
 
 /// <summary>
-/// Lokaler Embedding-Service basierend auf all-MiniLM-L6-v2 (ONNX).
+/// Lokaler Embedding-Service (ONNX). Standardmäßig all-MiniLM-L6-v2.
 /// Generiert 384-dimensionale Sentence-Embeddings für semantische Suche.
+/// Das Modellverzeichnis und die maximale Sequenzlänge sind konfigurierbar.
 /// </summary>
 public sealed class EmbeddingService : IDisposable
 {
@@ -20,15 +21,20 @@ public sealed class EmbeddingService : IDisposable
     readonly int _clsId;
     readonly int _sepId;
     readonly int _unkId;
-    readonly int _maxSeqLen = 128;
+    readonly int _maxSeqLen;
     bool _disposed;
 
     public bool IsAvailable { get; }
     public int Dimensions => 384;
+    public string ModelName { get; }
+    public bool CrossEncoderAvailable => false;
 
-    public EmbeddingService()
+    public EmbeddingService(string modelDir = null, int maxSeqLen = 256)
     {
-        var modelDir = Path.Combine(AppContext.BaseDirectory, "data", "models", "all-MiniLM-L6-v2");
+        _maxSeqLen = maxSeqLen;
+        if (modelDir == null)
+            modelDir = Path.Combine(AppContext.BaseDirectory, "data", "models", "all-MiniLM-L6-v2");
+        ModelName = Path.GetFileName(modelDir);
         var modelPath = Path.Combine(modelDir, "model.onnx");
         var vocabPath = Path.Combine(modelDir, "vocab.txt");
 

Services/VectorSearchService.cs

@@ -1,5 +1,6 @@
 using System;
 using System.Text;
+using System.Text.RegularExpressions;
 using System.Collections.Generic;
 using System.Linq;
 using System.Threading;
@@ -11,6 +12,7 @@ namespace Gott.Services;
 
 /// <summary>
 /// Verwaltet Message-Embeddings in SQLite und bietet semantische Suche.
+/// Hybrid-Suche: Vektor-Cosine-Similarity + FTS5-Keyword-Matching mit Recency-Boost.
 /// </summary>
 public class VectorSearchService
 {
@@ -32,6 +34,12 @@ public class VectorSearchService
         return conn;
     }
 
+    void TryExecuteSql(SqliteConnection conn, string sql)
+    {
+        try { conn.Execute(sql); }
+        catch { /* Column/table may already exist — idempotent migration */ }
+    }
+
     void InitializeSchema()
     {
         using var conn = CreateConnection();
@@ -62,6 +70,17 @@ public class VectorSearchService
             );
             CREATE INDEX IF NOT EXISTS idx_memfile_agent ON memory_file_embeddings(agent_id);
         ");
+
+        // Schema migration: add new columns (idempotent)
+        TryExecuteSql(conn, "ALTER TABLE message_embeddings ADD COLUMN full_text TEXT");
+        TryExecuteSql(conn, "ALTER TABLE message_embeddings ADD COLUMN embedding_model TEXT");
+        TryExecuteSql(conn, "ALTER TABLE memory_file_embeddings ADD COLUMN full_text TEXT");
+        TryExecuteSql(conn, "ALTER TABLE memory_file_embeddings ADD COLUMN embedding_model TEXT");
+
+        // FTS5 virtual tables for keyword search
+        TryExecuteSql(conn, "CREATE VIRTUAL TABLE IF NOT EXISTS message_embeddings_fts USING fts5(full_text, content='', content_rowid='rowid')");
+        TryExecuteSql(conn, "CREATE VIRTUAL TABLE IF NOT EXISTS memory_embeddings_fts USING fts5(full_text, content='', content_rowid='rowid')");
+
         Console.WriteLine("[VectorSearch] Schema initialized.");
     }
 
@@ -100,9 +119,9 @@ public class VectorSearchService
 
         await conn.ExecuteAsync(@"
             INSERT OR IGNORE INTO message_embeddings
-                (message_id, chain_id, session_id, agent_id, role, text_preview, vector, created_at)
+                (message_id, chain_id, session_id, agent_id, role, text_preview, vector, created_at, full_text, embedding_model)
             VALUES
-                (@messageId, @chainId, @sessionId, @agentId, @role, @preview, @vector, @createdAt)",
+                (@messageId, @chainId, @sessionId, @agentId, @role, @preview, @vector, @createdAt, @fullText, @embeddingModel)",
             new
             {
                 messageId,
@@ -112,13 +131,28 @@ public class VectorSearchService
                 role,
                 preview,
                 vector = EmbeddingService.ToBytes(vector),
-                createdAt = DateTime.UtcNow.ToString("o")
+                createdAt = DateTime.UtcNow.ToString("o"),
+                fullText = text,
+                embeddingModel = _embedding.ModelName
             });
+
+        // Insert into FTS5 index
+        try
+        {
+            var lastId = await conn.ExecuteScalarAsync<long>("SELECT last_insert_rowid()");
+            if (lastId > 0)
+            {
+                await conn.ExecuteAsync(
+                    "INSERT INTO message_embeddings_fts(rowid, full_text) VALUES (@id, @fullText)",
+                    new { id = lastId, fullText = text });
+            }
+        }
+        catch { /* FTS5 insert failure is non-critical */ }
     }
 
     /// <summary>
     /// Semantische Suche: Findet die N ähnlichsten Messages zu einer Query.
-    /// Durchsucht alle Sessions eines Agents (oder alle wenn agentId null).
+    /// Hybrid: Vektor-Cosine-Similarity + FTS5-Keyword + Recency-Boost.
     /// </summary>
     public async Task<List<SearchResult>> SearchAsync(string query, string agentId = null,
         int topN = 10, float minScore = 0.3f)
@@ -146,23 +180,107 @@ public class VectorSearchService
 
         if (!string.IsNullOrEmpty(agentId))
         {
-            sql = "SELECT message_id, chain_id, session_id, agent_id, role, text_preview, vector, created_at FROM message_embeddings WHERE agent_id = @agentId";
+            sql = "SELECT id, message_id, chain_id, session_id, agent_id, role, text_preview, full_text, vector, created_at FROM message_embeddings WHERE agent_id = @agentId";
             param = new { agentId };
         }
         else
         {
-            sql = "SELECT message_id, chain_id, session_id, agent_id, role, text_preview, vector, created_at FROM message_embeddings";
+            sql = "SELECT id, message_id, chain_id, session_id, agent_id, role, text_preview, full_text, vector, created_at FROM message_embeddings";
             param = new { };
         }
 
         var rows = await conn.QueryAsync<EmbeddingRow>(sql, param);
-        var results = new List<SearchResult>();
+        var rowList = rows.ToList();
 
-        foreach (var row in rows)
+        // --- Vector scores ---
+        var vectorScores = new Dictionary<long, float>(); // keyed by id
+        var rowMap = new Dictionary<long, EmbeddingRow>();
+        foreach (var row in rowList)
         {
             var vec = EmbeddingService.FromBytes(row.Vector);
             var score = EmbeddingService.CosineSimilarity(queryVec, vec);
-            if (score >= minScore)
+            vectorScores[row.Id] = score;
+            rowMap[row.Id] = row;
+        }
+
+        // --- FTS5 keyword scores ---
+        var ftsScores = new Dictionary<long, float>();
+        try
+        {
+            var sanitized = SanitizeFtsQuery(query);
+            if (!string.IsNullOrWhiteSpace(sanitized))
+            {
+                string ftsSql;
+                object ftsParam;
+                if (!string.IsNullOrEmpty(agentId))
+                {
+                    ftsSql = @"SELECT me.id, f.rank
+                               FROM message_embeddings_fts f
+                               JOIN message_embeddings me ON me.rowid = f.rowid
+                               WHERE message_embeddings_fts MATCH @query AND me.agent_id = @agentId
+                               ORDER BY f.rank LIMIT @limit";
+                    ftsParam = new { query = sanitized, agentId, limit = topN * 3 };
+                }
+                else
+                {
+                    ftsSql = @"SELECT me.id, f.rank
+                               FROM message_embeddings_fts f
+                               JOIN message_embeddings me ON me.rowid = f.rowid
+                               WHERE message_embeddings_fts MATCH @query
+                               ORDER BY f.rank LIMIT @limit";
+                    ftsParam = new { query = sanitized, limit = topN * 3 };
+                }
+
+                var ftsRows = await conn.QueryAsync<FtsRow>(ftsSql, ftsParam);
+                var ftsList = ftsRows.ToList();
+
+                if (ftsList.Count > 0)
+                {
+                    // FTS5 rank is negative (lower = better). Normalize to 0-1.
+                    var minRank = ftsList.Min(r => r.Rank);
+                    var maxRank = ftsList.Max(r => r.Rank);
+                    var range = maxRank - minRank;
+                    foreach (var r in ftsList)
+                    {
+                        float normalized = range == 0 ? 1.0f : (float)((maxRank - r.Rank) / range);
+                        ftsScores[r.Id] = normalized;
+                        // Ensure row is in rowMap (it should be, but load if needed)
+                        if (!rowMap.ContainsKey(r.Id))
+                        {
+                            var row = await conn.QueryFirstOrDefaultAsync<EmbeddingRow>(
+                                "SELECT id, message_id, chain_id, session_id, agent_id, role, text_preview, full_text, vector, created_at FROM message_embeddings WHERE id = @id",
+                                new { id = r.Id });
+                            if (row != null) rowMap[r.Id] = row;
+                        }
+                    }
+                }
+            }
+        }
+        catch { /* FTS5 query failure — fall back to vector-only */ }
+
+        // --- Score fusion ---
+        var allIds = new HashSet<long>(vectorScores.Keys);
+        foreach (var id in ftsScores.Keys) allIds.Add(id);
+
+        var results = new List<SearchResult>();
+        foreach (var id in allIds)
+        {
+            if (!rowMap.ContainsKey(id)) continue;
+            var row = rowMap[id];
+
+            float vecScore = vectorScores.ContainsKey(id) ? vectorScores[id] : 0f;
+            float ftsScore = ftsScores.ContainsKey(id) ? ftsScores[id] : 0f;
+            float fusedScore = 0.6f * vecScore + 0.4f * ftsScore;
+
+            // Recency boost: up to 15% for messages from last 30 days
+            if (DateTime.TryParse(row.CreatedAt, out var created))
+            {
+                double hoursSince = (DateTime.UtcNow - created).TotalHours;
+                double recencyBoost = Math.Max(0, 1.0 - hoursSince / (30.0 * 24.0)) * 0.15;
+                fusedScore *= (float)(1.0 + recencyBoost);
+            }
+
+            if (fusedScore >= minScore)
             {
                 results.Add(new SearchResult
                 {
@@ -172,7 +290,8 @@ public class VectorSearchService
                     AgentId = row.AgentId,
                     Role = row.Role,
                     TextPreview = row.TextPreview,
-                    Score = score,
+                    FullText = row.FullText ?? row.TextPreview,
+                    Score = fusedScore,
                     CreatedAt = row.CreatedAt
                 });
             }
@@ -208,8 +327,8 @@ public class VectorSearchService
         if (!_embedding.IsAvailable || string.IsNullOrWhiteSpace(text)) return;
         if (text.Length < 10) return;
 
-        // Chunks erstellen: Memory-Dateien können lang sein → in 500-Zeichen-Chunks aufteilen
-        var chunks = ChunkText(text, 500);
+        // Chunks erstellen mit Overlap
+        var chunks = ChunkText(text, 500, 100);
 
         using var conn = CreateConnection();
 
@@ -218,6 +337,19 @@ public class VectorSearchService
             "DELETE FROM memory_file_embeddings WHERE agent_id = @agentId AND file_path = @filePath",
             new { agentId, filePath });
 
+        // Also clean up old FTS entries for this file's chunks
+        try
+        {
+            var oldIds = await conn.QueryAsync<long>(
+                "SELECT rowid FROM memory_file_embeddings WHERE agent_id = @agentId AND file_path = @filePath",
+                new { agentId, filePath });
+            foreach (var oldId in oldIds)
+            {
+                try { await conn.ExecuteAsync("INSERT INTO memory_embeddings_fts(memory_embeddings_fts, rowid, full_text) VALUES('delete', @id, '')", new { id = oldId }); } catch { }
+            }
+        }
+        catch { }
+
         for (int i = 0; i < chunks.Count; i++)
         {
             float[] vector;
@@ -229,9 +361,9 @@ public class VectorSearchService
             var preview = chunks[i].Length > 200 ? chunks[i].Substring(0, 200) : chunks[i];
             await conn.ExecuteAsync(@"
                 INSERT INTO memory_file_embeddings
-                    (agent_id, file_path, chunk_index, text_preview, vector, updated_at)
+                    (agent_id, file_path, chunk_index, text_preview, vector, updated_at, full_text, embedding_model)
                 VALUES
-                    (@agentId, @filePath, @chunkIndex, @preview, @vector, @updatedAt)",
+                    (@agentId, @filePath, @chunkIndex, @preview, @vector, @updatedAt, @fullText, @embeddingModel)",
                 new
                 {
                     agentId,
@@ -239,13 +371,29 @@ public class VectorSearchService
                     chunkIndex = i,
                     preview,
                     vector = EmbeddingService.ToBytes(vector),
-                    updatedAt = DateTime.UtcNow.ToString("o")
+                    updatedAt = DateTime.UtcNow.ToString("o"),
+                    fullText = chunks[i],
+                    embeddingModel = _embedding.ModelName
                 });
+
+            // Insert into FTS5 index
+            try
+            {
+                var lastId = await conn.ExecuteScalarAsync<long>("SELECT last_insert_rowid()");
+                if (lastId > 0)
+                {
+                    await conn.ExecuteAsync(
+                        "INSERT INTO memory_embeddings_fts(rowid, full_text) VALUES (@id, @fullText)",
+                        new { id = lastId, fullText = chunks[i] });
+                }
+            }
+            catch { /* FTS5 insert failure is non-critical */ }
         }
     }
 
     /// <summary>
     /// Sucht über Memory-Dateien eines Agents.
+    /// Hybrid: Vektor-Cosine-Similarity + FTS5-Keyword + Recency-Boost.
     /// </summary>
     public async Task<List<MemorySearchResult>> SearchMemoryFilesAsync(string query, string agentId, int topN = 5, float minScore = 0.4f)
     {
@@ -259,15 +407,83 @@ public class VectorSearchService
 
         using var conn = CreateConnection();
         var rows = await conn.QueryAsync<MemoryFileRow>(
-            "SELECT agent_id, file_path, chunk_index, text_preview, vector, updated_at FROM memory_file_embeddings WHERE agent_id = @agentId",
+            "SELECT id, agent_id, file_path, chunk_index, text_preview, full_text, vector, updated_at FROM memory_file_embeddings WHERE agent_id = @agentId",
             new { agentId });
+        var rowList = rows.ToList();
 
-        var results = new List<MemorySearchResult>();
-        foreach (var row in rows)
+        // --- Vector scores ---
+        var vectorScores = new Dictionary<long, float>();
+        var rowMap = new Dictionary<long, MemoryFileRow>();
+        foreach (var row in rowList)
         {
             var vec = EmbeddingService.FromBytes(row.Vector);
             var score = EmbeddingService.CosineSimilarity(queryVec, vec);
-            if (score >= minScore)
+            vectorScores[row.Id] = score;
+            rowMap[row.Id] = row;
+        }
+
+        // --- FTS5 keyword scores ---
+        var ftsScores = new Dictionary<long, float>();
+        try
+        {
+            var sanitized = SanitizeFtsQuery(query);
+            if (!string.IsNullOrWhiteSpace(sanitized))
+            {
+                var ftsSql = @"SELECT me.id, f.rank
+                               FROM memory_embeddings_fts f
+                               JOIN memory_file_embeddings me ON me.rowid = f.rowid
+                               WHERE memory_embeddings_fts MATCH @query AND me.agent_id = @agentId
+                               ORDER BY f.rank LIMIT @limit";
+                var ftsParam = new { query = sanitized, agentId, limit = topN * 3 };
+
+                var ftsRows = await conn.QueryAsync<FtsRow>(ftsSql, ftsParam);
+                var ftsList = ftsRows.ToList();
+
+                if (ftsList.Count > 0)
+                {
+                    var minRank = ftsList.Min(r => r.Rank);
+                    var maxRank = ftsList.Max(r => r.Rank);
+                    var range = maxRank - minRank;
+                    foreach (var r in ftsList)
+                    {
+                        float normalized = range == 0 ? 1.0f : (float)((maxRank - r.Rank) / range);
+                        ftsScores[r.Id] = normalized;
+                        if (!rowMap.ContainsKey(r.Id))
+                        {
+                            var row = await conn.QueryFirstOrDefaultAsync<MemoryFileRow>(
+                                "SELECT id, agent_id, file_path, chunk_index, text_preview, full_text, vector, updated_at FROM memory_file_embeddings WHERE id = @id",
+                                new { id = r.Id });
+                            if (row != null) rowMap[r.Id] = row;
+                        }
+                    }
+                }
+            }
+        }
+        catch { /* FTS5 query failure — fall back to vector-only */ }
+
+        // --- Score fusion ---
+        var allIds = new HashSet<long>(vectorScores.Keys);
+        foreach (var id in ftsScores.Keys) allIds.Add(id);
+
+        var results = new List<MemorySearchResult>();
+        foreach (var id in allIds)
+        {
+            if (!rowMap.ContainsKey(id)) continue;
+            var row = rowMap[id];
+
+            float vecScore = vectorScores.ContainsKey(id) ? vectorScores[id] : 0f;
+            float ftsScore = ftsScores.ContainsKey(id) ? ftsScores[id] : 0f;
+            float fusedScore = 0.6f * vecScore + 0.4f * ftsScore;
+
+            // Recency boost
+            if (DateTime.TryParse(row.UpdatedAt, out var updated))
+            {
+                double hoursSince = (DateTime.UtcNow - updated).TotalHours;
+                double recencyBoost = Math.Max(0, 1.0 - hoursSince / (30.0 * 24.0)) * 0.15;
+                fusedScore *= (float)(1.0 + recencyBoost);
+            }
+
+            if (fusedScore >= minScore)
             {
                 results.Add(new MemorySearchResult
                 {
@@ -275,7 +491,8 @@ public class VectorSearchService
                     FilePath = row.FilePath,
                     ChunkIndex = row.ChunkIndex,
                     TextPreview = row.TextPreview,
-                    Score = score,
+                    FullText = row.FullText ?? row.TextPreview,
+                    Score = fusedScore,
                     UpdatedAt = row.UpdatedAt
                 });
             }
@@ -284,7 +501,34 @@ public class VectorSearchService
         return results.OrderByDescending(r => r.Score).Take(topN).ToList();
     }
 
-    static List<string> ChunkText(string text, int chunkSize)
+    /// <summary>
+    /// Löscht alle Embeddings zur Neugenerierung.
+    /// </summary>
+    public async Task ReEmbedAllAsync()
+    {
+        using var conn = CreateConnection();
+        await conn.ExecuteAsync("DELETE FROM message_embeddings");
+        await conn.ExecuteAsync("DELETE FROM memory_file_embeddings");
+        // Reset FTS5 tables
+        try { await conn.ExecuteAsync("DELETE FROM message_embeddings_fts"); } catch { }
+        try { await conn.ExecuteAsync("DELETE FROM memory_embeddings_fts"); } catch { }
+        Console.WriteLine("[VectorSearch] All embeddings cleared for re-embedding.");
+    }
+
+    /// <summary>
+    /// Sanitizes a query string for FTS5 MATCH by removing special operators.
+    /// </summary>
+    static string SanitizeFtsQuery(string query)
+    {
+        if (string.IsNullOrWhiteSpace(query)) return "";
+        // Remove FTS5 special characters: * " ( ) : ^ - + AND OR NOT NEAR
+        var sanitized = Regex.Replace(query, @"[""()*:^+\-]", " ");
+        sanitized = Regex.Replace(sanitized, @"\b(AND|OR|NOT|NEAR)\b", " ", RegexOptions.IgnoreCase);
+        sanitized = Regex.Replace(sanitized, @"\s+", " ").Trim();
+        return sanitized;
+    }
+
+    static List<string> ChunkText(string text, int chunkSize, int overlap = 0)
     {
         var chunks = new List<string>();
         if (string.IsNullOrEmpty(text)) return chunks;
@@ -293,12 +537,42 @@ public class VectorSearchService
         var paragraphs = text.Split(new[] { "\n\n", "\r\n\r\n" }, StringSplitOptions.RemoveEmptyEntries);
         var current = new StringBuilder();
 
+        // Track paragraph positions for overlap
+        var paragraphStarts = new List<int>();
+        var paragraphTexts = new List<string>();
+        int pos = 0;
         foreach (var para in paragraphs)
         {
+            paragraphStarts.Add(pos);
+            paragraphTexts.Add(para);
+            pos += para.Length + 2; // approximate separator length
+        }
+
+        for (int pi = 0; pi < paragraphTexts.Count; pi++)
+        {
+            var para = paragraphTexts[pi];
             if (current.Length + para.Length > chunkSize && current.Length > 0)
             {
                 chunks.Add(current.ToString().Trim());
+
+                // Apply overlap: backtrack to include some text from end of current chunk
                 current.Clear();
+                if (overlap > 0 && pi > 0)
+                {
+                    // Collect paragraphs from the end until we have ~overlap chars
+                    int overlapChars = 0;
+                    int startPi = pi;
+                    for (int bi = pi - 1; bi >= 0 && overlapChars < overlap; bi--)
+                    {
+                        overlapChars += paragraphTexts[bi].Length;
+                        startPi = bi;
+                    }
+                    for (int bi = startPi; bi < pi; bi++)
+                    {
+                        if (current.Length > 0) current.AppendLine();
+                        current.Append(paragraphTexts[bi]);
+                    }
+                }
             }
             if (current.Length > 0) current.AppendLine();
             current.Append(para);
@@ -309,12 +583,20 @@ public class VectorSearchService
         return chunks;
     }
 
+    class FtsRow
+    {
+        public long Id { get; set; }
+        public double Rank { get; set; }
+    }
+
     public class MemoryFileRow
     {
+        public long Id { get; set; }
         public string AgentId { get; set; }
         public string FilePath { get; set; }
         public int ChunkIndex { get; set; }
         public string TextPreview { get; set; }
+        public string FullText { get; set; }
         public byte[] Vector { get; set; }
         public string UpdatedAt { get; set; }
     }
@@ -325,18 +607,21 @@ public class VectorSearchService
         public string FilePath { get; set; }
         public int ChunkIndex { get; set; }
         public string TextPreview { get; set; }
+        public string FullText { get; set; }
         public float Score { get; set; }
         public string UpdatedAt { get; set; }
     }
 
     public class EmbeddingRow
     {
+        public long Id { get; set; }
         public long MessageId { get; set; }
         public string ChainId { get; set; }
         public string SessionId { get; set; }
         public string AgentId { get; set; }
         public string Role { get; set; }
         public string TextPreview { get; set; }
+        public string FullText { get; set; }
         public byte[] Vector { get; set; }
         public string CreatedAt { get; set; }
     }
@@ -349,6 +634,7 @@ public class VectorSearchService
         public string AgentId { get; set; }
         public string Role { get; set; }
         public string TextPreview { get; set; }
+        public string FullText { get; set; }
         public float Score { get; set; }
         public string CreatedAt { get; set; }
     }