jonah791/dsh-agent-teams0

@nanmicoder/dsh-agent-teams

AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI

包名
@nanmicoder/dsh-agent-teams
版本
0.1.14
许可证
MIT
最近更新
2026年9月7日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jonah791/dsh-agent-teams

Configuration

Defaults work without extra setup. A trusted profile can override member behavior:

- id: agent-teams
  config:
    stateDir: .agent-teams
    memberProvider: spawn
    memberModel: deepseek-v4
    memberMaxDepth: 1
    maxMembers: 8

memberProvider is the sub-agent runtime backend (spawn / fork), not an LLM provider. Cross-LLM-provider routing uses the optional provider + model fields of agent_teams_add_member; memberModel is only a model default for all members. A member on the captain's current provider/model inherits the captain's reasoning effort, while a changed provider or model automatically uses the target model's default. To request a particular effort, pass the optional reasoning_effort field — one of the target model's supported effort ids, or "default" to force the model's own default.

slashCommand: false disables the deterministic /agent-teams activation surfaces (slash command and gesture boundary), leaving the natural-language trigger as the only entry point.