Bazley13/dsh-multi-model-orchestrator1

dsh-multi-model-orchestrator

A DeepSeek Harness (dsh) plugin: orchestrates complex tasks across multiple models — a 'main brain' decomposes the task and dispatches subtasks to GLM / Kimi / Qwen etc. sub-agents by each model's strengths, with per-model token usage.

包名
dsh-multi-model-orchestrator
版本
0.2.2
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:Bazley13/dsh-multi-model-orchestrator

Configuration reference

Everything is configured in $DSH_HOME/settings.yaml:

SectionPurpose
llm-pi-ai.providersOpenAI-compatible third-party model routes (any vendor).
subagent-model-selectionAllow-list of {provider, model} the sub-agent tool may dispatch to.
multi-model-orchestrator.modelNotesPer-route strengths/weaknesses that guide assignment.

To add your own vendor, extend llm-pi-ai.providers with { api, baseURL, apiKeyEnv, models } (any OpenAI-compatible api: openai-completions gateway works), then add matching entries to subagent-model-selection.allowedModels and multi-model-orchestrator.modelNotes.