router 10

Delegate light subagent tasks to cheaper models: automatic Flash/Pro routing for DeepSeek Harness subagent calls, with /delegate overrides, budget caps, and a routing-ledger panel.

DeepSeek Harness plugin: read-only GitHub access for agents (github_probe / github_pr / github_issue / github_file / github_api). Routes every request inside the tool — api.github.com (direct or proxy), gh CLI, git protocol (plugin-owned fetch cache plus

Per-turn model and reasoning-effort routing for DeepSeek Harness -- one Jev choice question per turn

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL

Cortex — 低成本高质量多模型递归任务编排、模型评测与智能路由平台（DSH 插件）：任务画像/策略匹配/递归拆解/动态路由/四级质量门控/批量监督/恢复引擎/预算控制/策略沉淀/KPI

Tool Guardian as a native DeepSeek Harness (DSH) bundle: keeps tool definitions out of the context window by fronting your MCP servers behind a small native router. A bridge to the Python tool-guardian, not a rewrite.

Route and rewrite the harness's outbound HTTP requests by host and path, with a native right-sidebar monitor.

Routes each DSH agent request to the least powerful model that can handle it — flash for simple work, pro for complex, vision for images — with a settings page and live composer readout.

Omni - a reliability and orchestration control plane for DeepSeek Harness, designed to turn fast models into dependable long-horizon software-engineering agents.