Plugins

Left-sidebar panel that views, edits and saves ~/.dsh/AGENTS.md live, with version-guarded saves and atomic writes.

Unofficial DeepSeek Harness port of the Academic Research Skills plugin (CC-BY-NC-4.0, non-commercial): 5 skills, 16 /ars-* commands, 4 agent roles, write-scope guard, and deterministic Python gates.

Privacy guard for git workflows: before git commit, git push or gh repo sync it scans the content that would enter git (local paths, user info, API keys, private keys, connection strings) and blocks anything not approved in the DSH approval UI; approved items go into a manageable, masked whitelist. Native DSH Config schema with live settings, first-push full-repository scan, fail-closed checks, zero npm runtime dependencies.

Keeps a turn from closing on an unfinished reply: a stream guard turns silent truncation into an in-step retry, and a completion protocol asks the model to declare how each turn ended.

Pause and resume DeepSeek Harness sessions around DeepSeek peak-priced hours (holiday & make-up-workday aware)

System guard for DeepSeek Harness (Windows-first, protected actions via UAC/sudo): classifies core system files and runtime junk, keeps a hidden SHA-256 backup of core files on the largest free disk, patrols integrity and restores damaged files, and asks for administrator rights only to protect the system. On macOS/Linux it only classifies and hashes (no junk deletion; repair prints manual steps), and that path has not been tested on real hardware.

Intercepts startup crashes, isolates broken frontend plugins, and recovers GUI cleanly with revision-bound quarantine.

Grades free physical and commit memory and refuses heavy tools (shell, workflow, subagent) before the machine thrashes. A reserve you set on the panel is held back from heavy tools so light calls still have room. Also shows in the composer how much of the machine dsh itself is using, including whole-machine CPU.

Computer Use for every DSH session: screen capture, mouse and keyboard, app launch, plan and skill replay, an audit log, guards for dangerous actions, a background code agent, and an OCR workflow (text and coordinates) for apps whose accessibility tree is empty. Verified on macOS only: Windows has a basic GUI backend that is unverified, Linux has no desktop backend (calls fail with unsupported_platform), and the window/AX/browser/clipboard tools register on macOS only.

Deterministic review of synthetic AI-agent claims in DeepSeek Harness, reporting bounded verdicts, reasons, and evidence references.

Utilities for DSH sessions: ask another session a question with a context guard, pause the running turn from the UI, restart DSH on Windows and resume automatically (via the scheduled task that install-restart.ps1 creates), enforce peak-hour discipline and per-feature allowed time windows, and periodically scan session logs for interrupted turns.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

Keeps the Auto permission preset across DSH restarts: the auto-review unload migration no longer rewrites a live Auto Session to Full access during application shutdown, and a stored Auto Session no longer fails to open when its integration is absent.

Pre-execute hook that denies writes under a read-only result zone of protected roots; every other path passes through.

Detect and contain runaway symbol streams at the model boundary in DeepSeek Harness, with tooling to repair polluted artifacts and sessions.

检查日志是否开启、是否记录了该记的、是否留够法定 6 个月

按 GB/T 22239-2019 逐项对照代码与配置里可静态发现的等保项

检查告警链路：有没有告警、发到哪、有没有把敏感信息一起发出去

查应用里有没有展示 ICP/APP 备案号、隐私政策入口、运营者信息 —— 都是法定义务

查代码与配置里的境外数据出口：境外端点、个人信息外发、缺安全评估说明

Delete a DeepSeek Harness conversation from the sidebar: a recoverable trash with restore and purge, or permanent removal, with a path-safety guard and an audit trail. | 在 DeepSeek Harness 侧边栏删除对话：可恢复的回收站（支持还原与彻底删除），或永久删除，并带有路径安全校验与审计日志。

Standalone DSH plugin: Codex/Claude continuable CLI subagents, wait_subagent, child exit guard and model tiers. Pure ESM, no build step.

反盲批 / Anti Blind Approval — DeepSeek Harness approval guard: review workspace-write escalation requests with the session model, then gate the Allow button on a strict JSON verdict.

Local tool guard that scores every DeepSeek Harness tool call with an Ollama decision model before it runs; risky calls come back as an approval prompt, and an unreachable model stops all calls. Requires DSH 0.2.x and a local Ollama 0.35.1+ with the default ~6 GB clef-flash model pulled first; without them every tool call is denied.