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>

Endpoints/ChatEndpoint.cs

@@ -254,7 +254,7 @@ public static class ChatEndpoint
 
                     if (anthropic.IsCliAvailable)
                     {
-                        await anthropic.StreamChatViaCli(res, ctx.ModelId, ctx.SystemPrompt, messages, ctx.ChainId, workspace: ctx.Workspace, allowUserChoice: ctx.Agent?.AllowUserChoice ?? true, planMode: body.PlanMode, webSearch: !string.IsNullOrEmpty(ctx.WebSearchVersion), sessionId: sessionId, agentId: ctx.AgentId, remoteMgr: remoteMgr, unityMcpUrl: ctx.Session?.UnityMcpUrl, unityMcpToken: ctx.Session?.UnityMcpToken, workCt: workCt, sseCt: sseCt);
+                        await anthropic.StreamChatViaCli(res, ctx.ModelId, ctx.SystemPrompt, messages, ctx.ChainId, workspace: ctx.Workspace, allowUserChoice: ctx.Agent?.AllowUserChoice ?? true, planMode: body.PlanMode, webSearch: !string.IsNullOrEmpty(ctx.WebSearchVersion), sessionId: sessionId, agentId: ctx.AgentId, remoteMgr: remoteMgr, unityMcpUrl: ctx.Session?.UnityMcpUrl, unityMcpToken: ctx.Session?.UnityMcpToken, useAutoContext: ctx.Agent?.UseAutoContext ?? true, workCt: workCt, sseCt: sseCt);
                     }
                     else
                     {

Endpoints/EmbeddingDebugEndpoint.cs

@@ -0,0 +1,198 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Threading.Tasks;
+using Gott.Extensions;
+using Gott.Services;
+using Microsoft.AspNetCore.Builder;
+using Microsoft.AspNetCore.Http;
+
+namespace Gott.Endpoints;
+
+public static class EmbeddingDebugEndpoint
+{
+    public static void MapEmbeddingDebugEndpoints(this WebApplication app)
+    {
+        app.MapGet("/api/admin/embedding-debug", HandleDebugSearch);
+        app.MapGet("/api/admin/embedding-debug/stats", HandleStats);
+        app.MapPost("/api/admin/embedding-debug/re-embed", HandleReEmbed);
+    }
+
+    /// <summary>
+    /// Diagnose-Suche: Zeigt Top-N mit Scores, inkl. Ergebnisse unter Schwellenwert.
+    /// Query-Params: q (query), agentId, topN (default 20), chainId (zum Simulieren des Filters)
+    /// </summary>
+    private static async Task HandleDebugSearch(HttpContext ctx,
+        VectorSearchService vectorSearch, EmbeddingService embeddingService)
+    {
+        if (!ctx.IsAdmin())
+        {
+            ctx.Response.StatusCode = 403;
+            await ctx.Response.WriteAsJsonAsync(new { error = "Admin access required" });
+            return;
+        }
+
+        if (!embeddingService.IsAvailable)
+        {
+            await ctx.Response.WriteAsJsonAsync(new { error = "Embedding model not available" });
+            return;
+        }
+
+        var query = ctx.Request.Query["q"].ToString();
+        var agentId = ctx.Request.Query["agentId"].ToString();
+        var chainId = ctx.Request.Query["chainId"].ToString();
+        var topN = 20;
+        if (int.TryParse(ctx.Request.Query["topN"].ToString(), out var parsedTopN) && parsedTopN > 0)
+            topN = Math.Min(parsedTopN, 100);
+
+        if (string.IsNullOrWhiteSpace(query))
+        {
+            await ctx.Response.WriteAsJsonAsync(new { error = "Query parameter 'q' is required" });
+            return;
+        }
+
+        // Suche mit SEHR niedrigem Schwellenwert, damit wir alles sehen
+        var allResults = await vectorSearch.SearchAsync(query,
+            string.IsNullOrEmpty(agentId) ? null : agentId,
+            topN: topN,
+            minScore: 0.1f);
+
+        // Memory-Dateien auch durchsuchen
+        var memoryResults = new List<VectorSearchService.MemorySearchResult>();
+        if (!string.IsNullOrEmpty(agentId))
+        {
+            memoryResults = await vectorSearch.SearchMemoryFilesAsync(query, agentId, topN: 10, minScore: 0.1f);
+        }
+
+        // Ergebnisse annotieren: Was würde der AutoContext-Filter machen?
+        // Neuer Threshold ist 0.35 durch Hybrid-Suche
+        var annotatedMessages = allResults.Select(r => new
+        {
+            r.MessageId,
+            r.ChainId,
+            r.SessionId,
+            r.AgentId,
+            r.Role,
+            r.TextPreview,
+            FullText = r.FullText ?? r.TextPreview,
+            Score = Math.Round(r.Score, 4),
+            r.CreatedAt,
+            WouldPassThreshold = r.Score >= 0.35f,
+            WouldBeFilteredByChain = !string.IsNullOrEmpty(chainId) && r.ChainId == chainId,
+            WouldBeFilteredByLength = (r.TextPreview?.Length ?? 0) < 20,
+            WouldAppearInAutoContext = r.Score >= 0.35f
+                && (string.IsNullOrEmpty(chainId) || r.ChainId != chainId)
+                && (r.TextPreview?.Length ?? 0) >= 20
+        }).ToList();
+
+        var annotatedMemory = memoryResults.Select(r => new
+        {
+            r.AgentId,
+            r.FilePath,
+            r.ChunkIndex,
+            r.TextPreview,
+            FullText = r.FullText ?? r.TextPreview,
+            Score = Math.Round(r.Score, 4),
+            r.UpdatedAt,
+            WouldPassThreshold = r.Score >= 0.35f
+        }).ToList();
+
+        // Zusammenfassung
+        var summary = new
+        {
+            Query = query,
+            AgentId = agentId,
+            ChainIdFilter = chainId,
+            TotalMessageResults = annotatedMessages.Count,
+            AboveThreshold035 = annotatedMessages.Count(r => r.WouldPassThreshold),
+            BelowThreshold = annotatedMessages.Count(r => !r.WouldPassThreshold),
+            WouldAppearInAutoContext = annotatedMessages.Count(r => r.WouldAppearInAutoContext),
+            FilteredByChain = annotatedMessages.Count(r => r.WouldBeFilteredByChain),
+            FilteredByLength = annotatedMessages.Count(r => r.WouldBeFilteredByLength),
+            TotalMemoryResults = annotatedMemory.Count,
+            MemoryAboveThreshold = annotatedMemory.Count(r => r.WouldPassThreshold)
+        };
+
+        await ctx.Response.WriteAsJsonAsync(new
+        {
+            summary,
+            messages = annotatedMessages,
+            memory = annotatedMemory
+        });
+    }
+
+    /// <summary>
+    /// Statistiken: Anzahl Embeddings pro Agent, Gesamtzahl, etc.
+    /// </summary>
+    private static async Task HandleStats(HttpContext ctx,
+        VectorSearchService vectorSearch, DatabaseService db)
+    {
+        if (!ctx.IsAdmin())
+        {
+            ctx.Response.StatusCode = 403;
+            await ctx.Response.WriteAsJsonAsync(new { error = "Admin access required" });
+            return;
+        }
+
+        using var conn = db.GetConnection();
+
+        var totalMessages = await Dapper.SqlMapper.ExecuteScalarAsync<int>(conn,
+            "SELECT COUNT(*) FROM message_embeddings");
+        var totalMemory = await Dapper.SqlMapper.ExecuteScalarAsync<int>(conn,
+            "SELECT COUNT(*) FROM memory_file_embeddings");
+
+        var perAgentDynamic = await Dapper.SqlMapper.QueryAsync(conn,
+            @"SELECT me.agent_id,
+                     a.name,
+                     COUNT(*) AS message_count,
+                     (SELECT COUNT(*) FROM memory_file_embeddings mfe WHERE mfe.agent_id = me.agent_id) AS memory_chunks
+              FROM message_embeddings me
+              LEFT JOIN agents a ON a.id = me.agent_id
+              GROUP BY me.agent_id
+              ORDER BY COUNT(*) DESC");
+
+        var perAgent = perAgentDynamic.Select(r => new
+        {
+            AgentId = (string)r.agent_id,
+            AgentName = (string)r.name,
+            MessageCount = (long)r.message_count,
+            MemoryChunks = (long)r.memory_chunks
+        }).ToList();
+
+        await ctx.Response.WriteAsJsonAsync(new
+        {
+            totalMessages,
+            totalMemory,
+            perAgent
+        });
+    }
+
+    /// <summary>
+    /// Triggert Re-Embedding aller Messages und Memory-Dateien.
+    /// POST /api/admin/embedding-debug/re-embed
+    /// </summary>
+    private static async Task HandleReEmbed(HttpContext ctx,
+        EmbeddingBackgroundService embeddingBg, EmbeddingService embeddingService)
+    {
+        if (!ctx.IsAdmin())
+        {
+            ctx.Response.StatusCode = 403;
+            await ctx.Response.WriteAsJsonAsync(new { error = "Admin access required" });
+            return;
+        }
+
+        if (!embeddingService.IsAvailable)
+        {
+            await ctx.Response.WriteAsJsonAsync(new { error = "Embedding model not available" });
+            return;
+        }
+
+        embeddingBg.TriggerReEmbed();
+        await ctx.Response.WriteAsJsonAsync(new
+        {
+            status = "Re-embedding triggered",
+            model = embeddingService.ModelName,
+            info = "Background service will re-embed all messages and memory files. Check stats for progress."
+        });
+    }
+}

Plans/SENTENCEPIECE_TOKENIZER.md

@@ -0,0 +1,83 @@
+# Plan: SentencePiece-Tokenizer-Support für multilinguales Embedding-Modell
+
+## Ziel
+`paraphrase-multilingual-MiniLM-L12-v2` als alternatives Embedding-Modell ermöglichen, indem der `EmbeddingService` neben WordPiece (BERT) auch SentencePiece (XLM-RoBERTa) Tokenizer unterstützt.
+
+## Hintergrund
+- Aktuell: `all-MiniLM-L6-v2` (BERT, WordPiece, `vocab.txt`, 384 Dims)
+- Ziel-Modell: `paraphrase-multilingual-MiniLM-L12-v2` (XLM-RoBERTa, SentencePiece, `sentencepiece.bpe.model`, 384 Dims)
+- Problem: Unser Tokenizer ist hardcoded auf WordPiece – Special Tokens (`[CLS]`/`[SEP]`), `token_type_ids`, `vocab.txt`
+
+## Unterschiede zwischen den Tokenizern
+
+| Aspekt | WordPiece (BERT) | SentencePiece (XLM-R) |
+|---|---|---|
+| Vocab-Datei | `vocab.txt` | `sentencepiece.bpe.model` |
+| Special Tokens | `[CLS]`=101, `[SEP]`=102, `[PAD]`=0 | `<s>`=0, `</s>`=2, `<pad>`=1 |
+| token_type_ids | Required (alle 0) | Nicht verwendet |
+| Subword-Prefix | `##` | `▁` (U+2581) |
+| Vocab-Groesse | ~30.522 | ~250.002 |
+
+---
+
+## Schritte
+
+### Schritt 1: NuGet-Paket hinzufuegen
+- `Microsoft.ML.Tokenizers.SentencePieceBpe` oder `SentencePieceSharp` evaluieren
+- Kriterien: .NET 10 Kompatibilitaet, kein native-Dependency-Problem auf Linux, Lizenz
+- Paket zu `gott.csproj` hinzufuegen
+
+### Schritt 2: Tokenizer-Abstraktion in `EmbeddingService.cs`
+- Interface oder Strategie-Pattern: `ITextTokenizer` mit Methode `Tokenize(string text, int maxLen) -> (long[] inputIds, long[] attentionMask, long[]? tokenTypeIds)`
+- `WordPieceTokenizer` – bestehende Logik extrahieren (Zeilen 127-161)
+- `SentencePieceTokenizer` – neue Implementierung
+- Constructor-Logik: Wenn `vocab.txt` existiert -> WordPiece; wenn `sentencepiece.bpe.model` existiert -> SentencePiece
+- Property `TokenizerType` fuer Debug/Logging
+
+### Schritt 3: ONNX-Session Input anpassen
+- WordPiece: 3 Inputs (`input_ids`, `attention_mask`, `token_type_ids`)
+- SentencePiece: 2 Inputs (`input_ids`, `attention_mask`) – kein `token_type_ids`
+- `GenerateEmbedding()` muss dynamisch die richtigen Inputs erstellen basierend auf Tokenizer-Typ
+- ONNX Input-Names aus dem Modell lesen statt hardcoded (robuster)
+
+### Schritt 4: Special Token IDs konfigurierbar machen
+- `[CLS]`/`[SEP]` IDs vs. `<s>`/`</s>` IDs
+- Am besten aus `special_tokens_map.json` oder `tokenizer_config.json` lesen, falls vorhanden
+- Fallback: Hardcoded Mapping pro Tokenizer-Typ
+
+### Schritt 5: Modell-Dateien bereitstellen
+- Von HuggingFace herunterladen:
+  - `model.onnx` (ONNX-Export des Modells)
+  - `sentencepiece.bpe.model`
+- Ablegen in `data/models/paraphrase-multilingual-MiniLM-L12-v2/`
+- Server-Setting `EmbeddingModelDir` auf den neuen Ordner setzen
+
+### Schritt 6: Re-Embed-Kompatibilitaet
+- Dimensionen sind identisch (384) -> Keine DB-Schema-Aenderung noetig
+- Re-Embed-Endpoint muss weiterhin funktionieren
+- Beim Modell-Wechsel: **Alle** Embeddings muessen neu berechnet werden (altes Modell-Vektoren sind inkompatibel mit neuem Modell)
+- Warnung im Admin-UI wenn Modell gewechselt wurde aber Re-Embed noch nicht gelaufen ist
+
+### Schritt 7: Tests & Verifikation
+- Embedding-Debug-Page nutzen: Gleiche Queries mit altem vs. neuem Modell vergleichen
+- Testcases:
+  - Deutsche Query -> deutsche Messages ("weisst du was zum thema autocontext")
+  - Englische Query -> englische Messages ("skills")
+  - Gemischt -> gemischte Messages ("otter karten")
+  - Pruefen ob Scores sich verbessern (besonders fuer deutsche Queries)
+
+---
+
+## Betroffene Dateien
+1. `gott.csproj` – NuGet-Paket
+2. `Services/EmbeddingService.cs` – Tokenizer-Abstraktion, SentencePiece-Support
+3. `wwwroot/js/embedding-debug.js` – ggf. Anzeige des aktiven Modells/Tokenizers
+
+## Risiken
+- **SentencePiece NuGet auf Linux**: Native Dependencies koennten Probleme machen -> vorher testen
+- **Re-Embed Dauer**: 14k Messages mit 256 Tokens -> je nach CPU 5-30 Minuten
+- **Dimensionen-Mismatch**: Falls ein zukuenftiges Modell andere Dims hat -> DB-Migration noetig (aktuell nicht, beide 384)
+
+## Aufwand
+- Geschaetzt: ~2-3 Stunden Implementierung
+- Groesster Block: Tokenizer-Abstraktion sauber bauen

Program.cs

@@ -65,7 +65,14 @@ var chatService = new ChatService(dbService, toolService, memoryService, skillSe
 builder.Services.AddSingleton(chatService);
 
 // Embedding-Services (lokal, ONNX)
-var embeddingService = new Gott.Services.EmbeddingService();
+var embeddingModelDir = serverSettings.Get("EmbeddingModelDir");
+var embeddingMaxSeq = serverSettings.GetInt("EmbeddingMaxSeqLen", 256);
+var embeddingService = new Gott.Services.EmbeddingService(
+    string.IsNullOrEmpty(embeddingModelDir)
+        ? null
+        : Path.Combine(dataDir, "models", embeddingModelDir),
+    embeddingMaxSeq
+);
 builder.Services.AddSingleton(embeddingService);
 var vectorSearchService = new Gott.Services.VectorSearchService(dbPath, embeddingService);
 builder.Services.AddSingleton(vectorSearchService);
@@ -179,6 +186,7 @@ app.MapApiKeysEndpoints();
 app.MapOpenClawEndpoints();
 app.MapRemoteEndpoints();
 app.MapDatabaseExplorerEndpoints();
+app.MapEmbeddingDebugEndpoints();
 app.MapInternalEndpoints();
 
 var port = app.Configuration.GetValue<int>("Port", 19000);

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 autoCtx = await BuildAutoContextAsync(messages, chainId, agentId);
-                    var lastUserText = ExtractLastUserText(messages);
+                    if (autoCtx != null)
-                    if (!string.IsNullOrWhiteSpace(lastUserText))
+                        systemPrompt.Add(new { type = "text", text = autoCtx });
-                    {
-                        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() });
-                        }
-                    }
                 }
                 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
+        // Chunks erstellen mit Overlap
-        var chunks = ChunkText(text, 500);
+        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>();
+        // --- Vector scores ---
-        foreach (var row in rows)
+        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; }
     }

wwwroot/css/form.css

@@ -856,6 +856,139 @@ a.admin-user-meta {
   color: var(--primary);
 }
 
+/* ── Embedding Debug ── */
+
+.emb-summary { margin-bottom: 0.5rem }
+
+.emb-summary-grid {
+  display: flex;
+  flex-wrap: wrap;
+  gap: var(--badge-spacing);
+}
+
+.emb-stat {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  padding: var(--box-padding);
+  background: var(--f1-bg);
+  border: 1px solid var(--f1-border);
+  border-radius: var(--border-radius);
+  min-width: 90px;
+}
+
+.emb-stat-num {
+  font-size: 1.3em;
+  font-weight: bold;
+  font-variant-numeric: tabular-nums;
+}
+
+.emb-stat-label {
+  opacity: var(--semi-transparent);
+}
+
+.emb-stat.good .emb-stat-num {
+  color: var(--secondary);
+}
+
+.emb-stat.warn .emb-stat-num {
+  color: var(--warning);
+}
+
+.emb-results {
+  display: flex;
+  flex-direction: column;
+  gap: var(--badge-spacing);
+}
+
+.emb-result-item {
+  display: flex;
+  flex-direction: column;
+  gap: var(--badge-spacing);
+  padding: var(--box-padding);
+  background: var(--f1-bg);
+  border: 1px solid var(--f1-border);
+  border-radius: var(--border-radius);
+}
+
+.emb-result-header {
+  display: flex;
+  flex-wrap: wrap;
+  align-items: center;
+  gap: var(--badge-spacing);
+}
+
+.emb-rank {
+  font-weight: bold;
+  opacity: var(--semi-transparent);
+  min-width: 2rem;
+}
+
+.emb-score {
+  font-weight: bold;
+  font-variant-numeric: tabular-nums;
+  padding: var(--badge-padding);
+  border-radius: var(--border-radius);
+  font-size: var(--font-size);
+}
+
+.emb-score.score-good {
+  background: rgba(76, 175, 80, 0.2);
+  color: #4caf50;
+}
+
+.emb-score.score-medium {
+  background: rgba(255, 152, 0, 0.2);
+  color: #ff9800;
+}
+
+.emb-score.score-low {
+  background: rgba(244, 67, 54, 0.15);
+  color: #f44336;
+}
+
+.emb-role {
+  opacity: var(--semi-transparent);
+  text-transform: uppercase;
+}
+
+.emb-date {
+  opacity: var(--semi-transparent);
+}
+
+.emb-tag {
+  font-size: var(--font-size);
+  padding: var(--badge-padding);
+  border-radius: var(--border-radius);
+  font-weight: bold;
+  text-transform: uppercase;
+}
+
+.emb-tag.pass {
+  background: rgba(76, 175, 80, 0.2);
+  color: #4caf50;
+}
+
+.emb-tag.threshold {
+  background: rgba(33, 150, 243, 0.2);
+  color: #2196f3;
+}
+
+.emb-tag.filter {
+  background: rgba(244, 67, 54, 0.15);
+  color: #f44336;
+}
+
+.emb-result-text {
+  word-break: break-word;
+  white-space: pre-wrap;
+}
+
+.emb-result-meta {
+  opacity: var(--semi-transparent);
+  font-variant-numeric: tabular-nums;
+}
+
 /* ── Utility Classes (Inline-Style Replacements) ── */
 
 .clickable { cursor: pointer }

wwwroot/index.html

@@ -65,6 +65,7 @@
           <button class="header-menu-item" id="dashboardServerSettingsLink" hidden admin-only><i class="fa fa-server"></i> Servereinstellungen</button>
           <button class="header-menu-item" id="dashboardAdminLink" hidden admin-only><i class="fa fa-users"></i> Benutzerverwaltung</button>
           <button class="header-menu-item" id="dashboardDbExplorerLink" hidden admin-only><i class="fa fa-database"></i> Datenbank</button>
+          <button class="header-menu-item" id="dashboardEmbeddingDebugLink" hidden admin-only><i class="fa fa-search"></i> Embedding-Debug</button>
           <button class="header-menu-item" id="dashboardApiKeysLink" hidden admin-only><i class="fa fa-key"></i> API-Keys</button>
         </div>
       </div>
@@ -569,6 +570,38 @@
   </div>
 </template>
 
+<template id="tpl-embedding-debug">
+  <div class="page form-page">
+    <header>
+      <button class="back-btn icon-btn" data-page="dashboard"><i class="fa fa-arrow-left"></i></button>
+      <h1>Embedding-Debug</h1>
+    </header>
+    <div class="page-content">
+      <div class="form">
+        <div class="form-group">
+          <label>Query</label>
+          <input type="text" id="embDebugQuery" placeholder="Suchbegriff eingeben..." />
+        </div>
+        <div class="form-group">
+          <label>Agent</label>
+          <select id="embDebugAgent"><option value="">Alle Agents</option></select>
+        </div>
+        <div class="form-group">
+          <label>Top N (max 100)</label>
+          <input type="number" id="embDebugTopN" value="20" min="1" max="100" />
+        </div>
+        <div class="form-actions">
+          <button id="embDebugSearchBtn"><i class="fa fa-search"></i> Suchen</button>
+          <button id="embDebugStatsBtn" class="secondary"><i class="fa fa-chart-bar"></i> Statistiken</button>
+          <button id="embDebugReEmbedBtn" class="secondary" style="background:var(--danger-color);color:white"><i class="fa fa-refresh"></i> Re-Embed All</button>
+        </div>
+      </div>
+      <div id="embDebugSummary" style="margin-top:1rem"></div>
+      <div id="embDebugResults" style="margin-top:1rem"></div>
+    </div>
+  </div>
+</template>
+
 <template id="tpl-server-settings">
   <div class="page form-page">
     <header>
@@ -759,6 +792,7 @@
 <script src="js/pages/api-keys-page.js"></script>
 <script src="js/pages/server-settings-page.js"></script>
 <script src="js/pages/db-explorer-page.js"></script>
+<script src="js/pages/embedding-debug-page.js"></script>
 <script src="js/pages/shared-page.js"></script>
 <script src="js/app.js"></script>
 </body>

wwwroot/js/pages/dashboard.js

@@ -17,7 +17,8 @@ registerPage('dashboard', {
       dashboardAdminLink: 'admin',
       dashboardApiKeysLink: 'api-keys',
       dashboardServerSettingsLink: 'server-settings',
-      dashboardDbExplorerLink: 'db-explorer'
+      dashboardDbExplorerLink: 'db-explorer',
+      dashboardEmbeddingDebugLink: 'embedding-debug'
     };
     for (var id in menuItems) {
       document.getElementById(id).addEventListener('click', ((page) => () => {

wwwroot/js/pages/embedding-debug-page.js

@@ -0,0 +1,206 @@
+// ── Embedding Debug Page ──
+
+registerPage('embedding-debug', {
+  async init() {
+    if (!currentUser || !currentUser.isAdmin) {
+      navigateTo('dashboard');
+      return;
+    }
+
+    var queryInput = document.getElementById('embDebugQuery');
+    var agentSelect = document.getElementById('embDebugAgent');
+    var topNInput = document.getElementById('embDebugTopN');
+    var searchBtn = document.getElementById('embDebugSearchBtn');
+    var statsBtn = document.getElementById('embDebugStatsBtn');
+    var reEmbedBtn = document.getElementById('embDebugReEmbedBtn');
+    var summaryEl = document.getElementById('embDebugSummary');
+    var resultsEl = document.getElementById('embDebugResults');
+
+    // Agents laden
+    try {
+      var resp = await fetch('/api/agents/available');
+      var agents = await resp.json();
+      (agents || []).forEach(function(a) {
+        var opt = document.createElement('option');
+        opt.value = a.agentId;
+        opt.textContent = a.name;
+        agentSelect.appendChild(opt);
+      });
+    } catch (e) { /* ignore */ }
+
+    searchBtn.addEventListener('click', doSearch);
+    queryInput.addEventListener('keydown', function(e) {
+      if (e.key === 'Enter') doSearch();
+    });
+    statsBtn.addEventListener('click', doStats);
+
+    if (reEmbedBtn) {
+      reEmbedBtn.addEventListener('click', async function() {
+        if (!confirm('Alle Embeddings löschen und neu generieren?\n\nDas kann bei vielen Messages einige Minuten dauern.')) return;
+        reEmbedBtn.disabled = true;
+        reEmbedBtn.innerHTML = '<i class="fa fa-spinner fa-spin"></i> Läuft...';
+        try {
+          var resp = await fetch('/api/admin/embedding-debug/re-embed', { method: 'POST' });
+          var data = await resp.json();
+          summaryEl.innerHTML = '<div class="success-box">' + esc(data.status || data.error) + (data.model ? ' (Modell: ' + esc(data.model) + ')' : '') + '</div>';
+        } catch (e) {
+          summaryEl.innerHTML = '<div class="error-box">Fehler: ' + esc(e.message) + '</div>';
+        } finally {
+          reEmbedBtn.disabled = false;
+          reEmbedBtn.innerHTML = '<i class="fa fa-refresh"></i> Re-Embed All';
+        }
+      });
+    }
+
+    async function doSearch() {
+      var query = queryInput.value.trim();
+      if (!query) return;
+      searchBtn.disabled = true;
+      searchBtn.innerHTML = '<i class="fa fa-spinner fa-spin"></i> Suche...';
+      summaryEl.innerHTML = '';
+      resultsEl.innerHTML = '';
+
+      try {
+        var params = new URLSearchParams({
+          q: query,
+          agentId: agentSelect.value,
+          topN: topNInput.value || '20'
+        });
+        var resp = await fetch('/api/admin/embedding-debug?' + params);
+        var data = await resp.json();
+
+        if (data.error) {
+          summaryEl.innerHTML = '<div class="error-box">' + esc(data.error) + '</div>';
+          return;
+        }
+
+        renderSummary(data.summary);
+        renderResults(data.messages, data.memory);
+      } catch (e) {
+        summaryEl.innerHTML = '<div class="error-box">Fehler: ' + esc(e.message) + '</div>';
+      } finally {
+        searchBtn.disabled = false;
+        searchBtn.innerHTML = '<i class="fa fa-search"></i> Suchen';
+      }
+    }
+
+    async function doStats() {
+      statsBtn.disabled = true;
+      statsBtn.innerHTML = '<i class="fa fa-spinner fa-spin"></i>';
+      summaryEl.innerHTML = '';
+      resultsEl.innerHTML = '';
+
+      try {
+        var resp = await fetch('/api/admin/embedding-debug/stats');
+        var data = await resp.json();
+        renderStats(data);
+      } catch (e) {
+        summaryEl.innerHTML = '<div class="error-box">Fehler: ' + esc(e.message) + '</div>';
+      } finally {
+        statsBtn.disabled = false;
+        statsBtn.innerHTML = '<i class="fa fa-chart-bar"></i> Statistiken';
+      }
+    }
+
+    function renderSummary(s) {
+      summaryEl.innerHTML =
+        '<div class="emb-summary">' +
+          '<div class="emb-summary-grid">' +
+            '<div class="emb-stat"><span class="emb-stat-num">' + s.totalMessageResults + '</span><span class="emb-stat-label">Treffer gesamt</span></div>' +
+            '<div class="emb-stat good"><span class="emb-stat-num">' + s.aboveThreshold035 + '</span><span class="emb-stat-label">&ge; 0.35 (Threshold)</span></div>' +
+            '<div class="emb-stat warn"><span class="emb-stat-num">' + s.belowThreshold + '</span><span class="emb-stat-label">&lt; 0.35</span></div>' +
+            '<div class="emb-stat"><span class="emb-stat-num">' + s.wouldAppearInAutoContext + '</span><span class="emb-stat-label">→ AutoContext</span></div>' +
+            '<div class="emb-stat"><span class="emb-stat-num">' + s.filteredByChain + '</span><span class="emb-stat-label">Chain-gefiltert</span></div>' +
+            '<div class="emb-stat"><span class="emb-stat-num">' + s.filteredByLength + '</span><span class="emb-stat-label">Zu kurz (&lt;20)</span></div>' +
+          '</div>' +
+          (s.totalMemoryResults > 0 ?
+            '<div class="emb-summary-grid" style="margin-top:0.5rem">' +
+              '<div class="emb-stat"><span class="emb-stat-num">' + s.totalMemoryResults + '</span><span class="emb-stat-label">Memory-Treffer</span></div>' +
+              '<div class="emb-stat good"><span class="emb-stat-num">' + s.memoryAboveThreshold + '</span><span class="emb-stat-label">Memory &ge; 0.35</span></div>' +
+            '</div>' : '') +
+        '</div>';
+    }
+
+    function renderResults(messages, memory) {
+      var html = '';
+
+      if (messages && messages.length > 0) {
+        html += '<h3 style="margin:1rem 0 0.5rem">Message-Ergebnisse</h3>';
+        html += '<div class="emb-results">';
+        messages.forEach(function(r, i) {
+          var scoreClass = r.score >= 0.35 ? 'score-good' : (r.score >= 0.2 ? 'score-medium' : 'score-low');
+          var filterTags = '';
+          if (r.wouldBeFilteredByChain) filterTags += '<span class="emb-tag filter">Chain</span>';
+          if (r.wouldBeFilteredByLength) filterTags += '<span class="emb-tag filter">Kurz</span>';
+          if (r.wouldAppearInAutoContext) filterTags += '<span class="emb-tag pass">AutoContext</span>';
+          else if (r.wouldPassThreshold) filterTags += '<span class="emb-tag threshold">Threshold OK</span>';
+
+          var hasFullText = r.fullText && r.fullText.length > (r.textPreview || '').length;
+          html += '<div class="emb-result-item">' +
+            '<div class="emb-result-header">' +
+              '<span class="emb-rank">#' + (i + 1) + '</span>' +
+              '<span class="emb-score ' + scoreClass + '">' + r.score.toFixed(4) + '</span>' +
+              '<span class="emb-role">' + esc(r.role) + '</span>' +
+              '<span class="emb-date">' + esc(r.createdAt ? r.createdAt.substring(0, 16) : '') + '</span>' +
+              filterTags +
+              (hasFullText ? '<span class="emb-tag" style="cursor:pointer;background:var(--bg-secondary)" onclick="this.closest(\'.emb-result-item\').querySelector(\'.emb-fulltext\').style.display=this.closest(\'.emb-result-item\').querySelector(\'.emb-fulltext\').style.display===\'none\'?\'block\':\'none\'">Full</span>' : '') +
+            '</div>' +
+            '<div class="emb-result-text">' + esc(r.textPreview || '(kein Preview)') + '</div>' +
+            (hasFullText ? '<div class="emb-fulltext" style="display:none;margin-top:0.3rem;padding:0.5rem;background:var(--bg-secondary);border-radius:4px;font-size:0.8rem;white-space:pre-wrap;max-height:300px;overflow-y:auto">' + esc(r.fullText) + '</div>' : '') +
+            '<div class="emb-result-meta">MsgID: ' + r.messageId + ' | Session: ' + esc(r.sessionId || '').substring(0, 8) + ' | Chain: ' + esc(r.chainId || '').substring(0, 8) + '</div>' +
+          '</div>';
+        });
+        html += '</div>';
+      }
+
+      if (memory && memory.length > 0) {
+        html += '<h3 style="margin:1rem 0 0.5rem">Memory-Ergebnisse</h3>';
+        html += '<div class="emb-results">';
+        memory.forEach(function(r, i) {
+          var scoreClass = r.score >= 0.35 ? 'score-good' : (r.score >= 0.2 ? 'score-medium' : 'score-low');
+          var hasFullText = r.fullText && r.fullText.length > (r.textPreview || '').length;
+          html += '<div class="emb-result-item">' +
+            '<div class="emb-result-header">' +
+              '<span class="emb-rank">#' + (i + 1) + '</span>' +
+              '<span class="emb-score ' + scoreClass + '">' + r.score.toFixed(4) + '</span>' +
+              '<span class="emb-role">memory</span>' +
+              '<span class="emb-date">' + esc(r.filePath || '') + '</span>' +
+              (r.score >= 0.35 ? '<span class="emb-tag pass">AutoContext</span>' : '') +
+              (hasFullText ? '<span class="emb-tag" style="cursor:pointer;background:var(--bg-secondary)" onclick="this.closest(\'.emb-result-item\').querySelector(\'.emb-fulltext\').style.display=this.closest(\'.emb-result-item\').querySelector(\'.emb-fulltext\').style.display===\'none\'?\'block\':\'none\'">Full</span>' : '') +
+            '</div>' +
+            '<div class="emb-result-text">' + esc(r.textPreview || '(kein Preview)') + '</div>' +
+            (hasFullText ? '<div class="emb-fulltext" style="display:none;margin-top:0.3rem;padding:0.5rem;background:var(--bg-secondary);border-radius:4px;font-size:0.8rem;white-space:pre-wrap;max-height:300px;overflow-y:auto">' + esc(r.fullText) + '</div>' : '') +
+          '</div>';
+        });
+        html += '</div>';
+      }
+
+      if (!html) {
+        html = '<p style="color:var(--text-muted)">Keine Ergebnisse gefunden (auch nicht unter Threshold).</p>';
+      }
+
+      resultsEl.innerHTML = html;
+    }
+
+    function renderStats(data) {
+      var html = '<h3 style="margin-bottom:0.5rem">Embedding-Statistiken</h3>';
+      html += '<div class="emb-summary-grid">' +
+        '<div class="emb-stat"><span class="emb-stat-num">' + (data.totalMessages || 0).toLocaleString() + '</span><span class="emb-stat-label">Message-Embeddings</span></div>' +
+        '<div class="emb-stat"><span class="emb-stat-num">' + (data.totalMemory || 0).toLocaleString() + '</span><span class="emb-stat-label">Memory-Chunks</span></div>' +
+      '</div>';
+
+      if (data.perAgent && data.perAgent.length > 0) {
+        html += '<h3 style="margin:1rem 0 0.5rem">Pro Agent</h3>';
+        html += '<table class="db-table"><thead><tr><th>Agent</th><th>Messages</th><th>Memory</th></tr></thead><tbody>';
+        data.perAgent.forEach(function(a) {
+          html += '<tr><td>' + esc(a.agentName || a.agentId || '(kein Agent)') + '</td>' +
+            '<td class="db-table-num">' + (a.messageCount || 0).toLocaleString() + '</td>' +
+            '<td class="db-table-num">' + (a.memoryChunks || 0).toLocaleString() + '</td></tr>';
+        });
+        html += '</tbody></table>';
+      }
+
+      resultsEl.innerHTML = html;
+    }
+  }
+});