ha-orchestrator
Model high-availability failover + subagent orchestration (fanout/pipeline/supervisor) for DeepSeek Harness
AI 分析
核心用途是自动将复杂任务拆分为并行子任务、管道流或监督模式进行编排。适合需要多模型容灾和复杂任务自动化拆分执行的用户。
インストール
検証済み bundle がないか、互換性チェックに失敗しています。先にリポジトリの説明を読んでください。 README 全文を読む ↗
ドキュメント
README 全文を読む ↗Usage
No special commands. The model decides when to orchestrate:
You: Research these three open-source projects, compare licenses and community activity, and recommend one.
Model: sees 3 independent subtasks → calls orchestrate (fanout) → parallel research → comparison → recommendation
You: Do requirements analysis first, then a design doc, then an implementation plan.
Model: calls orchestrate (pipeline) → each stage's output feeds the next
You: Write a competitive analysis report and have a senior reviewer vet it.
Model: calls orchestrate (supervisor) → parallel analysis → review and merge → report
Settings
Settings → "HA 与编排":
| Card | What you can do |
|---|---|
| Model High Availability | On/off, backup list, cooldown, failure threshold, error-code filter, quarantined models and failover history |
| Subagent Orchestration | On/off, subagent provider, default concurrency, max subagents per run |
| Custom Subagents | Add, edit, reorder, delete; "AI Generate" creates one from a description |
| System | Plugin language (follow system / Chinese / English), the orchestration hint toggle, and the debug card toggle |