@dsh-external/dsh-model-router
Thin routing policy for DeepSeek Harness: keyword routing, allowlisted model switching, and isolated image generation. / DeepSeek Harness 薄路由策略:关键词路由、白名单模型切换和隔离生图。
15 results
Thin routing policy for DeepSeek Harness: keyword routing, allowlisted model switching, and isolated image generation. / DeepSeek Harness 薄路由策略:关键词路由、白名单模型切换和隔离生图。
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.
DeepSeek Harness 峰谷定价自动模型路由插件:高峰时段自动使用 deepseek-v4-flash,空闲时段自动使用 deepseek-v4-pro;用户显式选择的模型始终优先。
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 settings-page management panel.
Native DSH provider hub with named API keys, per-key model allowlists, OAuth accounts, failover, and redacted logs
DeepSeek Harness plugin: role-based model routing — both roles default to deepseek-flash (V4.1 Flash, native multimodal) until V4.1-Pro launches.
Deterministic per-turn adaptive model routing for DeepSeek Harness
Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, and observable decisions.
Budget-LLM pool router for DeepSeek Harness: usage ledger, health tracking, Thompson-sampling adaptive failover across free-tier models, quality tier ladder, executor pool, paid-guard, web panel + reroute badge. 穷鬼路由器。
Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.
DSH 插件:按任务复杂度在 deepseek-v4-flash 与 deepseek-v4-pro 之间自动路由(只升不降)
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.
Configurable task-aware model routing bundle for DeepSeek Harness
DeepSeek Harness plugin: route an agent request to a vision model (deepseek-v4-flash-vision-exp) when the user message contains an image, and keep the original model otherwise.
智能体选择器:像模型选择器一样在输入框旁勾选委派目标+具体模型,把对话任务派给外部智能体(Codex CLI / WorkBuddy 内置模型活动价 automation 桥 / WorkBuddy 自定义模型直连 / Claude Code)执行,结果流回 DSH 对话。含 agent_dispatch 工具 + composer 两步下拉 + 设置面板 + 桥健康探活 + 反冒充出处凭证。