플러그인

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.

Windows system-drive (C:) cleanup for DSH: rule-based scan, five-tier safety grading, a staging area with a rollback ledger, UAC elevation, and migration to another drive — a model tool plus a Web GUI panel.

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.

Maintained fork of godchen520/dsh-web-search-bing adapted to DSH 0.1.5-rc.1: Bing-backed provider for the built-in web_search tool, scraping the public cn.bing.com HTML results page with no API key, reachable from mainland China, and keeping searches off the model's own search quota. Endpoint and result count configurable.

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.

Engineering work-tools for DeepSeek Harness: registers two model-facing Host Tools — a scoped `git` runner, and a package-manager runner (`dev`) that detects npm/pnpm/yarn/bun from the workspace lockfile and picks the right verb per manager. Both run through dsh's sandboxed shell and return structured stdout/stderr/exitCode, so the agent gets focused, reviewable results instead of raw bash, and adding another tool is a copy-paste of one register block.

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

Adds an "approve for me" access mode whose approval requests are answered by an independent reviewer model instead of a person: the reviewer can read the workspace read-only, a reviewer that cannot run hands the request back to the human, and every decision is recorded with its rationale in an Approvals tab.

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.

Model training stage — end-to-end analysis, model training, and estimation for asset pricing and machine learning research. Ships one skill.

Sets the DeepSeek flash model's reasoning effort per step — thinking off for short cheap prompts, low for a plain request, high for engineering work — and raises it only on repeated tool failures. The model itself never changes; effort max is opt-in.

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 plugin: matches a model you declared on a custom gateway to the capability metadata it should have — context window, output cap, reasoning levels and image support — by looking the bare model name up at runtime; the plugin never writes your settings document.

Replacement session-title provider that compresses oversized or code-heavy first prompts before calling the model (in the tested DSH version the built-in provider rejects inputs above 4096 bytes without a model call) and waits for a real task instead of titling a greeting. Titles use the session’s own provider and model by default and manual titles are protected; title rules cover a character cap, an optional date affix, style, language and exclusion words, plus a per-session lock. Also re-titles stored sessions in bulk, with a progress overlay that keeps running after Settings is closed.

Colors each session title in the DSH sidebar by state: unread (a blue gradient while the model is running, green once it has finished), pinned (yellow), and sessions holding live background shell jobs (purple); overlapping states are composed into a single left-to-right gradient in a fixed order. Also adds a "Model updated" sort mode, a "since agent output" column to the Deep-diving timer, and a settings section listing every unread session.

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).