Plugins

DSH 设置面板：一个页面里管理技能（SKILL.md）与 MCP 服务器，全局 / 项目级分层，改完即生效。Manage skills and MCP servers from the DSH settings panel — global and per-project tiers, effective immediately.

Opens the DSH settings dialog as a full-page screen and moves the close control to a back row at the top left.

MACKORN 美矿液压圆锥破（NH/NS）与破碎筛分生产线选型：21 个工具覆盖客户需求表录入、机型/腔型/CSS 选型、整线配置、粒度曲线仿真（Whiten 1972）、实测数据标定、能耗成本估算、衬板磨损设计、经销商评估与 14 章方案书生成。DeepSeek Harness 插件 + MCP 服务器（stdio 与远程 HTTP 双通道），零依赖。

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

DSH 输入框下方的计费时段与余额药丸：常显账户余额与本次对话花费（余额差值记账）、峰价/谷价（含中国法定节假日与周末规则）、下一次切换倒计时（桌面端账号登录态优先，API Key 兜底）。

Scheduled task dispatcher: a dsh host plugin that drives recurring agent tasks from a single task table, dispatching each run as an independent dsh session (scheduling itself uses zero model calls)

Multi-model local speech-to-text for the DSH Web composer: Whistle and Voz, user-selectable, with lazy per-model download. Ships as a DSH bundle.

Plugin security review for DeepSeek Harness: dependency advisories, contextual static evidence, a call-time gate for high-risk plugins, and reversible review-gated enforcement.

Sign in with ChatGPT inside DeepSeek Harness, and use your ChatGPT subscription to serve models.

核心：信封／签名／握手／幂等／落盘 · Core: envelope, signing, handshake, idempotence, on-disk store

VibeDev 影视工作台：在 DeepSeek Harness 和 VibeDev 的右侧栏打开画布式影视工作台（剧本、分镜画布、图片/视频/音频生成、剪辑成片），模型与费用统一走 VibeDev 账号 · VibeDev Film: a canvas film workbench in the right sidebar of DeepSeek Harness and VibeDev (script, storyboard canvas, image/video/audio generation, e

Create Blender product scenes in DSH with editable recipes, model imports, previews and PNG/MP4 delivery; includes workbench and agent configuration.

Cross-session long-term memory backed by a local Go service (~50MB RAM, SQLite-vec + verify-augmented claims): zero-lag recall injection on every user message, session-end transcript ingest, and memory_search / memory_logs / memory_ingest tools. Install with `dsh plugin --profile web add @djasdh/interest-memory-dsh-bridge`. Protocol bridge only: the Go service is not installed by `dsh plugin add` — install and start it per the repository README first; until it runs, the tools silently return nothing.

Adds hover Recall / Delete / Delete-onward actions to every message row: removes content from the model context and the transcript together via durable append-only tombstones, with an empty-content guard so old deletions can never break strict providers. Tested on the DSH 2.0 desktop.

Codex-style appearance for the DSH Web interface: window edge hairlines and shadows, sidebar colours and row alignment, a model picker with a reasoning-effort power rail, composer and right-panel geometry, a full-page settings-modal pass, a Trajectory view exit, and a settings card for theme, accent, background, foreground, fonts, sidebar translucency and contrast.

Native DeepSeek Harness plugin: feeds every prompt into the local agent-feedback-loop capture pipeline and injects compiled recurrence rules back as context.

让 DeepSeek Harness 以 WSL 子系统作为会话的执行环境：shell、文件读写与命令执行均在子系统内完成，目录选择器与 GUI 终端同样定位到子系统路径，并通过子系统内的 bubblewrap 对命令进行沙箱隔离

Niubash-only shell executor and Bash-dialect teaching for DeepSeek Harness (dsh 0.2.0-rc.2, and the 0.1.7-rc.x line it shares its shell seam with): every ctx.shell execution runs as `niu -c`, PowerShell/cmd/WSL/nu handoffs are refused, PowerShell habits a

DeepSeek Harness 输入框的下一句建议：助手回复完，空输入框里出现一句灰色建议，按 Tab 填入。Prompt suggestions for the DSH composer.

Coding-learn floating panel: edits and runs Python/JavaScript/TypeScript/PowerShell with exit code and timing, grades JSON course lessons with progress export, keeps Markdown notes and snippet library, and sends code plus a question into the current conversation for the main model to answer.

Real-time disaster alerts for DeepSeek Harness: Japan earthquakes (P2PQuake) and JMA EEW, tsunami and weather telegrams, global earthquakes (EMSC/USGS) and NOAA tsunamis, mainland China earthquakes (CENC via Wolfx) plus nmc.cn rainstorm and geological-hazard warnings, and US/Canadian NWS and ECCC flood, rainfall and storm-surge warnings — matched against your watch regions and thresholds.

OpenBKN business knowledge-network context for DeepSeek Harness

Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake

DSV4.1 reasoning support with multimodal context and bounded artifact acceptance for DeepSeek Harness