gott/Endpoints/EmbeddingDebugEndpoint.cs

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."
        });
    }
}