zai-org / zai-org/feedback

[建议] 子智能体并行与模型调度优化:主进程并行工作、子智能体独立模型、跨会话互通、模型配置自动拉取

Open
#731 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

priority: P2 status: 待评估 type: 功能建议
Dominant language
No language data
Stars
22
Forks
1
PR merge metrics
No merged PRs in 30d

Description

提交前确认 · Pre-submission checklist
  • 我已搜索过现有 issue,确认这不是重复提议 / I searched existing issues and confirmed this isn't a duplicate.
  • 我已阅读 CONTRIBUTING.md / I've read CONTRIBUTING.md.
问题类别 · Category

对话 / Agent 交互 · Agent chat / interaction

涉及的 Agent 框架 · Agent framework

ZCode Agent(自研)

使用场景 · Use case

在用多子智能体(subagent)并行处理大型任务时遇到以下瓶颈:

  1. 子智能体启动后主进程完全阻塞、不干活,必须等全部子智能体完工才能继续当前任务;
  2. 子智能体不能单独指定其他模型,统一继承主进程模型,多个子智能体并发时容易触发上游限流导致并发中断;
  3. 不同会话 id 之间不能像 Codex 那样相互交流/协作;
  4. 第三方模型的模型列表不能从上游自动拉取,思考等级(reasoning level)不能勾选、要一个个手动填,配置繁琐且容易填错。
建议方案 · Proposal
  1. 主进程与子智能体并行:子智能体运行期间允许主进程继续处理其他工作(后台运行/任务队列),无需等待全部完工;
  2. 子智能体支持独立指定模型(不同提供商或更轻量的模型),分散并发压力,避免限流导致的中断;
  3. 支持跨会话通信:不同会话 id 之间可互相发送消息或共享上下文(类似 Codex 的会话协作);
  4. 模型配置体验优化:第三方模型列表支持从上游 API 自动拉取;思考等级(reasoning level)做成可勾选的选项而非手动填写。
预期价值 · Expected value

大型任务的多智能体并行效率显著提升、不再被限流打断;多会话协作场景(如主会话调度多个专项会话)成为可能;接入第三方模型的上手成本大幅降低。

你认为的优先级 · Your perceived priority

高 · High

你使用的 ZCode 版本 / 环境 · ZCode version / environment

0.16.9 / Windows 11 x64 桌面端(含内置 CLI)

补充材料 · Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No source files, tests, or entry points are identified; the issue is a product-level proposal covering four separate capabilities. Start by locating the agent orchestration and model-configuration components, then split the proposals into independently scoped work with explicit completion criteria.

Written by the indexing model from the issue text.

Assessment

Domain
ai
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.