修复总控智能体共识后仍被错判为继续派活的死循环
_find_dispatch_message 原实现会一路向前翻历史,直到撞到任意一条带 tool_calls 的 AIMessage,导致本轮 LLM 即使共识(tool_calls=[]),也会 被上一轮的派活 AI 翻出来再用一次,前端因此把同样的 task 又发给子智能体, 形成"嘴上共识、手上派活"的死循环。 改成只看最新一条 AIMessage(跳过末尾 skill_stop / clarification ack ToolMessage 即可),让 tool_calls 是否为空作为本轮的唯一权威信号。 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
1 parent
621fdc9244
commit
c769dd20f7
3 files changed
+30
-15
No files matched your search
@@ -14,7 +14,7 @@ models:
|
||||
display_name: DeepSeek Chat
|
||||
use: langchain_openai:ChatOpenAI
|
||||
model: deepseek-chat
|
||||
api_key: sk-e1c22b7931dc446f8b67e57878edd105
|
||||
api_key: sk-1520028668cb4cc388ed8315ff1e856e
|
||||
base_url: https://api.deepseek.com
|
||||
request_timeout: 600.0
|
||||
max_retries: 2
|
||||
|
||||
Reference in new issue
Block a user