meleki/gott
1
0 Fork 0
Code Activity

feat: Review-Agent (Multi-Agent-Kommunikation)

Browse Source 
- Session hat optionalen ReviewAgentId + MaxReviewIterations
- Nach end_turn des Worker-Agents wird der Review-Agent aufgerufen
- Review-Agent bekommt Worker-Konversation als Kontext + kann Tools nutzen
- [APPROVED] in Review-Antwort → fertig, sonst Feedback an Worker
- Worker korrigiert und wird erneut reviewed (max N Runden)
- SSE-Events: review_start, review_text, review_tool_use, review_feedback, review_approved
- Chat-UI: Review-Phase als eigene Bubble mit Header, Text, Status
- Session-Page: Review-Agent-Picker (gleicher Agent-Card-Helper)
- Dashboard: Review-Agent-Badge auf Session-Cards
- DB-Migration: review_agent_id, max_review_iterations auf sessions
This commit is contained in:
Meleki committed 2026-03-06 16:04:00 +01:00
1 parent 2598656f1c
commit 5fe3f8ac87
12 files changed
+619 -18
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

Endpoints/ChatEndpoint.cs
+1 -1
View File
@@ -85,7 +85,7 @@ 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: ctx.ToolChoice, cancellationToken: linkedCts.Token);
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: ctx.ToolChoice, review: ctx.Review, cancellationToken: linkedCts.Token);
}
finally
{