failover 7

Model high-availability failover + subagent orchestration (fanout/pipeline/supervisor) for DeepSeek Harness

Two-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback

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

Multi-backend web_search and web_fetch providers for the DeepSeek Harness web seam (ctx.web): Exa (REST with key, anonymous hosted MCP without) and Firecrawl (v2 search/scrape API) today, extensible to more backends (SearXNG, ...), with automatic failover

Provider-level web search+fetch pool for DeepSeek Harness: bypass the official LLM search channel (0 model tokens), failover/rotate across Exa/Tavily/Jina/Firecrawl/Serper/SerpApi/SearXNG/DDG/Brave with quota-aware circuit breaking, multi-key rotation, an

Provider failover for DeepSeek Harness: on rate-limit (429) or quota exhaustion, automatically switch between providers with configurable per-provider models, fall back to the last one (e.g. DeepSeek official), and show a visible notice in the UI.

Free-tier model aggregation for the DeepSeek Harness (dsh): registers the freeroute provider over a pool of free-quota upstreams (OpenCode Zen / B.AI / OpenRouter / SenseNova built in, plus remote catalogs and custom gateways), transparent failover before