Plugins

Adds a "Text Injection" section to the DSH Settings sidebar: user-maintained blocks in a standalone Markdown file are injected into the system prompt every turn or into session context with keyword gating, with hot reload and automatic history backups.

A股数据 API 官方 DeepSeek Harness 插件 —— 桌面端 / Web UI 输个包名即装，24 个 A股工具（行情 / K线 / 财务 / 资金 / 龙虎榜 / 板块 / 因子选股），免费工具无需 Key

DeepSeek Harness Web: raise an OS notification when a task finishes (or needs your input) while the harness page is not focused

多个AI Agent各干各的，消息靠你手动搬？建一个飞书群把它们拉进来，自动认领、自动交接。直连互@与Gateway路由双路线，兼容OpenClaw/AutoClaw/CherryStudio等8个框架，含8条实测踩坑，MIT

NetEase Cloud Music (music.163.com) player and AI DJ for DeepSeek Harness: a sidebar page with in-app playback, QR sign-in, and agent tools that curate the queue.

DSH plugin: model-generated session titles that follow the latest task, remember manual renames, persist their settings, and never fail silently.

Maintained fork of dsh-prompt-enhance, brought up to DSH 0.1.7 — the plugin would not even load on current hosts (InputState.imageIds became attachmentIds, so the composer button crashed the input box; settings.get() was removed; /enhance read a session id the agent no longer exposes). Rewrites default to reasoningEffort off, which measured 252 output tokens for a draft where the model default spent 2897, and a Settings page for all 17 fields is bundled. Verified on a real 0.1.7-rc.2 host: activation, a live HTTP enhancement request, /enhance in the GUI, and the Settings page reading and persisting configuration. 204 tests.

为短上下文窗口的对话提供更轻量的 Agent 预设，能降低78%的固定开销。由 Deepseek 制作

Chain-of-thought panel for the DSH Web right sidebar: folds the live reasoning stream of each session into turn → step groups carrying the reasoning text and the tool calls made in that step. Only the newest turn is expanded by default and earlier turns collapse to one line; steps are grouped into activity phases by a local rule, the step waiting on a tool is marked, tool failures show their reason, full reasoning text is fetched per step on demand, an all-turn directory searches turn titles, user text and turn numbers locally, and a whole turn can be summarised into a Chinese title with one model call.

A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers. Fork adds answer message bubbles with a settings switch.

Gear-based autonomy governor for the DeepSeek Harness agent: the entropy-sdk EntropyRuntime core (gear ladder G0-G4, utility gate, slow-up/fast-down policy, tamper-evident audit chain) bound to the Harness tool registry, with a live Web UI and paper-ready

DeepSeek Harness plugin: host-owned process & port lifecycle for local agents. start/stop/list/logs/wait-ready, tracked port reclaim, Processes rightbar + dock chip.

deepseek harness的插件安全性自查

DeepSeek Harness plugin: bounded-file memory for local agents. ME.md + project MEMORY.md vault, cache-stable inject, plain-line inbox, Memory rightbar. No embeddings, no LLM calls.

Retrospective agent-session evaluation — grades the sessions that already happened: deterministic grade cards, regression diffs, /eval-history trends, and /eval --report straight from exported artifacts; no benchmark runs, no LLM judges.

DSH会话悬浮窗：实时显示运行中会话的当前工作与批准提示（WinUI 3，可拖动缩放、置顶、跟随系统主题）注：主要部分均为ai编写

EchoCat Prettier：为 DSH AI 回复提供多风格排版、emoji、主题表情包与长回复性能保护。

Tokens remaining widget

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

Control how the DeepSeek Harness Web GUI is reachable: local only, Tailscale, all local networks, or off.

Creates local, content-addressed workspace checkpoints with diff previews and two-phase restore confirmation.

Manages Git worktrees in DeepSeek Harness with branch deletion controls and scoped workspace management.

A planner board as a third tab beside chat and trajectory: a Monday-first month calendar above per-day cards holding title, note, times, three importance levels and a completion checkbox. Plans repeat daily, weekly or on weekdays with an optional end date; editing or deleting asks this occurrence versus the whole series; completion is tracked per day; one button clears a day while only skipping recurrent series. Five model tools let the agent read, write, delete, clear and undo plans in conversation.

A browser that lives inside the DSH host: every session gets its own tab, the AI drives it with lazily published browser_embedded_* tools, and a human watches or takes over that same tab in an on-demand right-Sidebar tab — no GUI, no external browser, log