Plugins

Switches to the next healthy model candidate before the next agent step when the current model has been marked unhealthy.

Realtime ocean skin for DeepSeek Harness, rebuilt from d-dev0101/open-sea-skin 1.2.7 under MIT. Wave height follows the live session load, the sky comes from a local NOAA ephemeris, the star field is a real 2851-star HYG subset with 88 constellations, one boat per running subagent, plus a searchable 11-group settings panel and three quality tiers. Published to npm as "open-sea-skin-dsh"; it keeps the upstream bundle id, so uninstall d-dev0101/open-sea-skin first — the two cannot be installed side by side.

Durable workspace Plan/Backlog todos for DeepSeek Harness, with a sidebar board, agent tools, and /todo commands.

A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.

Model console panel: switch the model for every conversation at once or one at a time, filter sessions by idle time, fold subagents under their parent session, and bulk archive or release sessions.

Composer tweaks for the DSH input box: a Markdown source/view toggle, Markdown rendering for user messages, one mixed file-and-folder picker backed by the macOS open panel, a GenUI prompt switch inside the plus menu, an open-in-new-window action on sidebar Session rows (needs the separate `dsh-popout-window` host plugin), and a collapsible subagent tree. Requires DSH 0.2.x.

Digital Study: a private WeRead study in the DSH sidebar, in a calm light-green paper palette. The shelf folds into ten categories and carries a slightly deeper paper tint of its own; highlights and thoughts page through, copy per item, and export as front-matter Markdown (one file per book or a cross-book batch) into a folder you choose; the whole study backs up and restores as a single JSON bundle. Thoughts read like handwritten notes: looser line height, the source book shown in full, long entries folding behind a show-all control, and a same-chapter highlight block for context. A five-shade reading heatmap draws only the days up to today, keeps its numbers on one line underneath, and a year-scoped KPI dashboard sits above it. Sync is incremental: a local ledger plus per-book counts mean an unchanged library refreshes in 2-3 seconds instead of a full pull, and a banner reports progress and dismisses itself after eight seconds. Search covers shelf, books, highlights and thoughts with type filters. Reads WeRead through the official agent gateway using your own API key, keeps everything in local JSON and never writes back. Requires DSH >=0.2.2-rc.1.

Article Review page in DSH's native right sidebar: turns Markdown, Word, PowerPoint and PDF articles into sentence-addressable text, lets you comment on any sentence, and hands the open review to the agent as a composer draft. Six agent tools let the model read every comment, revise the article (in place for Markdown, as a sibling <name>.revised.md for binary formats), resolve the comments, and record recurring wording preferences into a long-term writing-style memory injected into later prompts. Extraction includes a dependency-free DOCX/PPTX reader; PDF text extraction runs locally through the host's Python + pypdf (or poppler's pdftotext) and is unavailable without one of them. No network calls, no telemetry.

A three-scope TODO board for DeepSeek Harness (user, workspace and session) with nested folders that can reference one item from several places, T0–T9 priorities, drag reordering, batch actions, a floating panel that also opens as a right-sidebar tab, Markdown preview windows that can stay open with autosaving title and body editing, and agent read/write tools, with every write gated by DSH approval.

Adds a 无界画布 page to the DSH left sidebar with a bundled front-end, local workbench status/start, and DSH Agent tools that read and edit the open canvas; the canvas has no built-in Agent. Requires a local 无界工作台 installation with ComfyUI; the plugin bundles neither ComfyUI, CUDA, models nor API keys.

Trims each tool result to a token budget derived from the active model's context window (ratio of window minus reserved output, clamped), keeping head and tail with a notice on how to fetch the rest; mount globally or inside one agent preset.

一个持久化的 DSH 插件：用一页优雅的中文/英文界面看尽当前设备的一切——硬件、系统、软件、 网络、安全与权限、进程——并对非硬件的一切直接操作（结束进程、退出/启动/卸载应用、启停登录项、 修改主机名/音量/深色模式、开关 Wi-Fi/防火墙、设置 DNS、卸载 Homebrew 包、清空废纸篓、睡眠/锁定、 跳转系统设置……）。同一套操作同时暴露给 Agent 模型，作为 device_info / device_control 两个工具。

DeepSeek-Harness 插件：轮次收尾时若模型未声明目标状态，注入续行提醒而非放行。处理思考泄露、工具调用畸形、上游断流导致的任务静默中断；上游中断类型可重试错误耗尽后自动续行，默认上限 3 次，跨进程共享计数。含设置界面与判定留痕

Back up and restore the whole $DSH_HOME: one-click or scheduled ZIP archives (optional password encryption applies to manual and agent-made backups only; scheduled ones are not encrypted), a settings section, agent tools to create, list, restore and prune backups, and a standalone restorer (Windows .bat or POSIX .sh) that runs without DeepSeek Harness installed.

DeepSeek Harness plugin: an agent-facing say tool that makes the agent speak one sentence out loud (local offline Xiaoxiao, Edge TTS, or Windows built-in), plus a desktop bubble and event-driven auto announcements.

odoo-lint for DeepSeek Harness: lint and fix Odoo addons, and lint every addon file the agent edits

DSH 本地记忆插件：自动记忆、遗忘曲线、关键词关联、可检索可编辑，数据留在本机。

Agent-asked secrets for DeepSeek Harness: a masked card stores API keys and tokens in the local credential store without them entering the chat, then injects them into one command.

Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, project state, evidence and credential references; reports drift, duplicate facts, broken pointers, paths left unverifiable in prose, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on the dimensions that belong to it; and turns findings into reviewable migration plans that back up every file before moving it. The format contract behind the metrics is written down as a versioned spec (CTX rules, markdownlint-style IDs) that follows open conventions — AGENTS.md for instruction files, llms.txt-shaped link indexes. Also scaffolds a deliberately small hub for durable knowledge and project state. Ships a stdlib-only Python CLI plus two skills, with credentials referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.

Blocks the end of a turn while temporary files from that turn are still lying around: it registers a listener on the serial agent/turn-stopping hook and, if anything is left, steers the model with the file list and two ways out — delete them, or justify each one and move it somewhere deliberate. Candidates come from two narrow temp-file sources, plus a backup-retention channel that is on by default and flags excess .bak copies of files touched this turn. The first is the .agent-tmp/ convention directory under the session cwd: whatever is left in it is reported outright, because that directory exists only for throwaway files. The second is the paths this turn actually wrote, captured through the fs/write-intent hook; those are reported only when they sit under that cwd, fall outside .git, node_modules, .tmp-sessions and out, match a temp-file pattern, and the file is still present — which is what keeps junk already sitting in the workspace from being resurrected as a complaint about this turn. One steer per turn, subagent sessions skipped, nothing deleted by the plugin in the default steer mode (only the opt-in mode: prune deletes backups), and the check is readdir plus stat only.

Screen frames, log lines and (on Windows) key/mouse input on one millisecond timeline: record, mark the failing seconds, box the problem on the frame, then hand the agent a keyframe strip, an animated GIF and the aligned log slice.

GitHub console inside DSH: token sign-in, repositories, issues, PRs, commits, notifications, stars and activity, one-click cloning that keeps itself up to date, and a categorized skill library that installs GitHub skill projects for the agent.

AI-native iteration cycle: 24 anic_* tools and 77 HTTP routes that run evaluation, convergence gates, and auto-fix loops across projects, with a live white-box panel (interactive workflow graph, invocation feed, autonomy gauge, gate ledger, HITL queue) and an inline installable SKILL.md workflow kit.

Long-form manuscript verification team for DSH: installs 10 skills that run a read-only content/structure check, three-tier revision proposals, a human-selection gate, exact replacements and a final re-check; it never edits the manuscript by itself and requires Agent Teams to spawn teammates.