Auto-Context: Semantische Kontext-Injektion, Memory-File-Embeddings, Agent-Toggle

- Automatische Embedding-basierte Kontext-Injektion vor jeder API-Anfrage
  (Top 5 Chat-Ergebnisse + Top 3 Memory-File-Treffer als recalled_context)
- Memory-Dateien (.md) werden embedded (Backfill + Live nach memory_write)
- Neue Agent-Option 'useAutoContext' (Checkbox, Default: aktiviert)
- VectorSearchService: SearchMemoryFilesAsync, EmbedMemoryFileAsync, Chunking
- EmbeddingBackgroundService: Memory-File-Backfill + EnqueueMemoryFile
- ToolService: memory_write löst Re-Embedding aus
- embeddingBg Parameter an ExecuteTool durchgereicht
This commit is contained in:
Meleki committed 2026-03-11 09:45:50 +01:00
1 parent add111ffe1
commit 148d1459a3
11 files changed
+305 -12

No files matched your search

+1 -1
View File
@@ -208,7 +208,7 @@ public static class ChatEndpoint
try
{
await anthropic.StreamChat(res, ctx.ModelId, ctx.SystemPrompt, messages, ctx.ChainId, ctx.Workspace, sessionId, agentId: ctx.AgentId, useMemory: ctx.UseMemory, webSearchVersion: ctx.WebSearchVersion, maxIterations: ctx.MaxIterations, toolChoice: effectiveToolChoice, review: ctx.Review, finalizer: ctx.Finalizer, allowUserChoice: ctx.Agent?.AllowUserChoice ?? true, planMode: ctx.PlanMode, workCt: workCt, hardCt: hardCt, sseCt: sseCt, remoteMgr: remoteMgr);
await anthropic.StreamChat(res, ctx.ModelId, ctx.SystemPrompt, messages, ctx.ChainId, ctx.Workspace, sessionId, agentId: ctx.AgentId, useMemory: ctx.UseMemory, webSearchVersion: ctx.WebSearchVersion, maxIterations: ctx.MaxIterations, toolChoice: effectiveToolChoice, review: ctx.Review, finalizer: ctx.Finalizer, allowUserChoice: ctx.Agent?.AllowUserChoice ?? true, planMode: ctx.PlanMode, useAutoContext: ctx.Agent?.UseAutoContext ?? true, workCt: workCt, hardCt: hardCt, sseCt: sseCt, remoteMgr: remoteMgr);
}
finally
{