llm-routing

Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact model routes, declarative teams and strategies, and bounded subagent delegation - a TypeScript plugin that adds no second runtime.

DSH plugin: sub-agent matrix swarm — routes heterogeneous tasks to the most suitable model (OpenRouter-like + cfgpu.com/llm/square), dispatches each via in-process subagents. 32/32 benchmark green.

Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness

EN: Lifecycle-safe subagent routing and role controls for DSH Web. 中文：面向 DSH Web 的生命周期安全子代理路由与角色控制。

Deterministic per-turn adaptive model routing for DeepSeek Harness

A token-efficient model-routing flywheel for the DeepSeek Harness.

Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, subtask model leases, and observable decisions / DSH 多源配额路由插件

Tiered model routing plugin for DeepSeek Harness (DSH): route delegated work to fast/medium/heavy model tiers with DoD verification, cross-provider fallback, background delegation, and per-conversation budget modes.

Kimi K3 routing fixes for DeepSeek Harness: recover context/quota errors and rescue premature natural turn endings.