Plugins

Guardian state engine for the DeepSeek Harness — assertion counting, edit review queue, and no-feedback-loop monitoring over session events

Persistent image or MP4 wallpaper for the DSH Web profile: a wallpaper card under Settings -> General selects a local image or MP4 (up to 300 MB), tunes surface opacity and blur, compresses video locally to H.264 when ffmpeg/ffprobe are on PATH, stores media under ~/.dsh/wallpapers, and pins the Web server to port 9191 so the saved wallpaper survives restarts.

DeepSeek Harness plugin: manage JumpServer assets and operate on them through KoKo

Custom background (images / GIFs / animated wallpapers) plugin for the DeepSeek Harness (DSH) Web GUI: an enable switch plus a local asset library, with separate display mechanisms for the official theme and skin-center skins.

DeepSeek Harness 管理员验证网关插件 — 自起独立 HTTP 网关，密码登录 + 反向代理 + WebSocket/SSE 透传，防止未授权访问

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Mojibake guard bundle for DSH: feature-based garbled-text detection before writes with review-then-release (an identical retry passes), plus pre-execution pwsh encoding audit (ANSI/GBK/UTF-16/Default), Windows and Chinese first.

Runtime log panel for DeepSeek Harness: live SSE log view in Settings plus bounded date/size rotating JSONL files.

A DeepSeek Harness plugin: model-facing reload_plugin tool that restarts one Cordis Loader entry (by entry id, module name, or MCP serverName) without touching sibling entries — respawns mcp-client server processes

A dsh status plugin with host-plane and browser halves: harness runtime health (process, listener, API-key presence, memory, uptime, plugin inventory) as JSON plus server-pushed SSE alerts, surfaced as a header badge with an expanded panel in the Web UI

Read-only Windows device information tools: one agent tool per Win32 device category (time, system, cpu, memory, disk, gpu, network, battery, processes, usb, audio, printers) via WMI/CIM and Node os collectors.

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

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

Execution flow chart: renders the current session's execution as a vertical node flow (turns, user, assistant, tools, approvals, retries, compaction), appended in real time over SSE with auto-follow scrolling — the chart draws wherever the session executes.

Pre-flight check for a DeepSeek Harness profile's plugin tree: static checks (syntax, package structure, patch references, config-tree assembly) plus optional real-boot smoke (isolated `dsh web` instance) and page-side smoke (headless Edge over CDP), with

Animated whale particle background for the DeepSeek Harness (dsh) Web UI - assembling from its scattered shell, breathing at idle, and being pushed around by the pointer

Shared infrastructure for data assetization plugins: business rules loader, file format adapter, report generator, path validator, audit logger Also known as @deepseek-ai/dsh-data-asset-shared.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Query and manage JumpServer through conversation: assets, users, accounts, permissions, sessions, command audit logs, command filters, and RBAC roles, authenticated with an AccessKeyID/AccessKeySecret pair (HTTP Signature).

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Sound alerts for the DSH web UI: a chime when an answer completes and a three-tone prompt when your approval or question is pending, with optional custom WAV stored only in the local browser (pure client-side, zero assets).

Training attestation — reproducible, attributable, auditable off-site standardized training for asset pricing. Hard-gates four failure modes (half-refresh, hash mismatch, unknown-read-as-pass, master pollution). Ships one skill.