model-router 8

Tiered model router for DeepSeek Harness: routes auxiliary calls (session title, compaction) and subtasks to light models, escalates hard tasks to strong ones — automatically, per request, across providers.

Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a set

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

DSH plugin: a virtual model-router provider that aggregates every configured provider and model, routes each request to the model's currently active provider, and ships a settings page for per-model provider ordering and switching.

Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, and observable decisions.

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

Cordis-native Lead/Worker model routing for DeepSeek Harness: a replaceable `ctx.llm` provider route plus an observable, interceptable routing service.

Model router for DeepSeek Harness: keep a pool of models and every step is routed to one of them with its reasoning effort set — a click-only composer panel, three authorization scopes (a manual pick only counts in the scope that owns it, and effort scope