插件

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.

DSH 的 Windows 系统盘（C 盘）清理能力：按规则库扫描、五级安全分级、带台账可回滚的暂存区、UAC 提权与迁移到其他盘 —— 既有模型工具，也有 Web 面板。

Codex-style DeepSeek Harness model and reasoning selector with model-advertised effort levels, DSH-native themes, left-clipped radiation effects, and copy-ready reasoning-effort declaration guidance for custom-provider models.

godchen520/dsh-web-search-bing 的维护 fork，适配 DSH 0.1.5-rc.1：为内置 web_search 工具提供 Bing 搜索源，直接解析 cn.bing.com 公开 HTML 结果页，无需 API Key，国内可直连，不消耗模型自带搜索额度。端点与结果数量可配置。

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.

面向软件工程师的 DeepSeek Harness 插件：注册两个模型可直接调用的 Host Tool——受工作区约束的 `git` 运行器，以及按 lockfile 自动识别 npm/pnpm/yarn/bun 并选择正确动词的包管理器运行器（`dev`）。两者都经 dsh 沙箱 shell 执行，返回规整的 stdout/stderr/exitCode，让 agent 拿到聚焦、可复核的结果而不是裸 bash；再加一个工具只需复制一个 register 块。

Keyboard shortcut that injects an encouraging message into the running dsh-TUI conversation: steer when a tool is in flight, interrupt-and-deliver when the model is only streaming text

A Models settings companion page listing every model's input modalities in one place, editable for both LLM adapter families

DSH (DeepSeek Harness) Web GUI plugin: global model token usage stats as a dedicated "Token 用量" page in Settings — incremental session-file scanning with a persistent fold cache, date-range picker with presets, model/provider filters, per-day and per-mode

新增「替我审批」访问模式：审批请求由独立的复核模型裁决而非人工，复核者可只读工作区，复核跑不起来时把请求交回人工，每次裁决的理由记录在「审批」页签中。

Named, file-defined subagent roles for DeepSeek Harness: persona, subagent-only skills, tool permissions, an ordered model chain with failover, and derived groups.

A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, and adds quota/balance lookups plus a provider management UI

gopkg fork：接入 WorkBuddy / WorkBuddy AI 模型，支持按模型选择上下文窗口与桌面客户端请求格式。WorkBuddy models for DSH with selectable context windows.

模型训练与结论阶段——资产定价与机器学习研究的端到端分析、模型训练与估计。附带一个 skill。

按步骤设置 DeepSeek flash 模型的思考等级：短小的廉价请求关闭思考，普通请求用 low，工程类工作用 high，只有反复出现工具失败才继续升档。模型本身不会改变，max 档需要手动开启。

DeepSeek Harness Web GUI plugin: real-time spend for the current session, priced from per-model token rates and shown as a pill under the composer

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。

DSH 插件：按模型名在运行时查一次目录，把你在自定义网关上声明的模型该有的能力元数据补上——上下文长度、输出上限、推理等级、能否看图；插件自己不写你的设置文档。

会话标题 provider 替换插件：先把过长或代码密集的首条 Prompt 压缩再调用模型（实测 DSH 版本的内建 provider 在超过 4096 bytes 时直接拒绝、不调用模型），遇到纯问候则等待真正的任务。默认使用该会话自身的 provider 与 model，保护人工标题；标题规则支持字数上限、可选日期前后缀、风格、语言与排除词，并可按会话锁定标题。还可批量重优化历史会话标题，进度浮层在关闭设置页后继续运行。

用颜色标记 DSH 侧栏每个会话标题的状态：未读（模型运行中＝蓝色渐变，已跑完＝绿色渐变）、置顶（黄色）、有存活后台 shell 任务（紫色）；多种状态并存时按固定语义顺序合成一条从左到右的渐变。另含侧栏第三排序模式「模型更新」、Deep diving 计时器的「距 agent 上次输出」第二列，以及集中查看全部未读会话的设置分节。

基因组尺度代谢模型（GEM）构建插件：输入细菌全基因组（蛋白FASTA，支持多质粒/多染色体），自动构建+验证+补洞+出报告（SBML + 模型卡），供 dsh-bio-genie 消费工具加载使用 | Genome-scale metabolic model builder for dsh

Anchored Standard preset with GPT Patch mode: task-aware first-request anchors using the bundled OpenAI Codex apply_patch instead of edit/write. Built for GPT/Codex models.

DeepSeek Harness Skills & MCPs Group Manager: group skills, filter the model skill catalog, toggle MCP servers, settings-page management UI

DSH plugin: sync model settings, plugin manifests, patch layers and lockfiles across devices through a private Git repository (manual push/pull; https+token or ssh public-key auth).