Plugins

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。

Intelligent sub-agent orchestration for DeepSeek Harness, with model discovery, routing, planning, and parallel delegation.

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Provider-scoped HTTP/HTTPS forward proxy for DeepSeek Harness: configure independent proxy URLs and enable/disable switches per LLM provider, with environment-variable references for proxy credentials and model discovery routing.

Ranks OpenRouter providers for the current DSH model by quantization, speed, cache-heavy price, context, and uptime, with one-click switching to help reduce token costs.

TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus full multimodal and async tools.

Sleev routing observability for DeepSeek Harness

Semantic model routing plugin for DeepSeek Harness

DSH web plugin that ranks OpenRouter upstream providers by quality, speed, cache-heavy price, context, and uptime, then safely switches the active route.

Display companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.

DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog

A DeepSeek Harness plugin for selecting and routing web search providers.

Windows multi-bash plugin for dsh: git_bash / wsl_bash model tools plus a shell-select executor routing the single ctx.shell seat across Git Bash, WSL and pwsh (pwsh stays the default).

Smart provider routing: composer-button one-click enable/disable, any channel error (including 4xx) auto-falls-back to the next channel, chain names shown in the model selector without exposing internal channels/models, multi-chain management with settings UI.

Reasoning-mode routing plugin for V4 Flash on headless: w7 persona anchoring, first-turn tool anchoring and complexity-dispatched guidance.

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness

Two-way Feishu (Lark) chat bridge for DeepSeek Harness over the official WebSocket long connection: messages route to the bound workspace's latest session and replies return automatically; bot credentials and workspace routing are configurable from the settings page.

Provider discovery, matching, health checks, and pre-output failover for DeepSeek Harness.