model-router 4

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.

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.

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

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