How to use dsh-ha-orchestrator

This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.

Quick start

Orchestrates subagents with model high-availability failover and dynamic orchestration.

— source: plugins.ai_summary

Install & verify

dsh plugin --profile web add dsh-ha-orchestrator

Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.

— source: plugins.install

Key points

• 模型调用中途出错时，自动改用备用模型重试，任务继续跑下去。
• 提供一个 orchestrate 工具，模型遇到适合的任务会自己调用它，把工作拆给多个子智能体并行执行（fanout）、分阶段执行（pipeline），或进行评审/归约（supervisor、map-reduce、router）。
• 模型请求出错时，自动改用下一个备用模型重试，备用模型按顺序轮换。
• 出错的模型被暂时跳过（进入冷却），冷却结束后自动恢复使用。
• 支持突发窗口失败计数、Provider 级熔断、低成本恢复探测，以及可选的上下文超长降级。

— source: plugin_wiki.readme_en (fallback readme_raw)

Pitfalls

Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.

— source: general rule