feat(ai): Agent SSE + Anthropic/responses tools + P1 确认写
- Agent 支持 SSE(步骤边推、正文分块),JSON 非流式 fallback - tool calling 覆盖 openai-chat / anthropic / responses(单测解析回灌) - P1:mcp.json mode=read_write 才可写;需 confirm_danger;Agent 剥离模型自带令牌 - GET /api/ai/mcp-status、POST /api/ai/agent/confirm;审计 source=mcp|agent
This commit is contained in:
1 parent
1d6e89449a
commit
2336c9433c
17 files changed
+1324
-197
No files matched your search
@@ -14,6 +14,7 @@ type AuditEntry struct {
|
||||
Tool string `json:"tool"`
|
||||
ConnectionID string `json:"connection_id,omitempty"`
|
||||
Mode string `json:"mode"`
|
||||
Source string `json:"source,omitempty"` // mcp | agent
|
||||
OK bool `json:"ok"`
|
||||
Summary string `json:"summary,omitempty"`
|
||||
Error string `json:"error,omitempty"`
|
||||
|
||||
Reference in new issue
Block a user