Plugins

Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

Source-aware prompt injection guard for DSH: tracks untrusted turn context, detects injection signals, scores sensitive sinks, and blocks high-risk tool calls with explainable audit logs.

Sends a desktop notification and chime when a DeepSeek Harness run completes, errors, or waits for approval, with a configurable duration threshold.

A `/backstory` command and tool that annotate each line with the git commit that last touched it and the agent turn + prompt that wrote it, from a persistent per-line ledger (drift-proof by content hash), DSH-* commit trailers, or the live session log.

Agent-managed procedural memory: a skill_manage tool that creates, patches, disables and deletes the agent's own skills in user or project scope, with delete guards (agent-created marker, pin, path confinement) and a trigger-discipline prompt.

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.

Windows desktop UI context picker for Codex, DeepSeek Harness, and MCP clients: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, and local OCR, then review and approve Markdown/JSON context before output.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

Image-background skin with four shipped wallpapers, a user wallpaper directory, custom image URLs, and live dim/blur controls in Settings.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

DSH Usage Monitor: auto-query provider credit balances and time-window limits from configured API keys, with input capsule and custom provider support.

Re-applies Chinese UI labels to the DSH client modules on every start, so translations survive upgrades.

Windows system-level notifications when the agent finishes a task or needs your input: task-done, question, approval and plan-review alerts via the browser Notification API, click-to-open the session, background-only mode, and a first-level settings page (Settings → 任务提示).

DeepSeek Harness plugin: Superself's `self` CLI as model-facing tools plus a /self command — cross-session, cross-project project state for agents.

Import, install and invoke Agent Skills in DeepSeek Harness from Codex, Claude Code, OpenCode, GitHub or npm — composer-side ⚡ picker inserts /skill-name into the draft, and a Skill 管理 settings page offers per-source/per-skill import, expandable source paths with skill counts, uninstall and one-click restore from .trash.

Cursor-style New Session: every click creates a fresh blank draft session (persisted before the first message) instead of reusing the workspace's single one, plus a sidebar Drafts switcher to keep several empty chats open at once.

Unified plugin marketplace built for the DSH Desktop (EAC) shell, aggregating the curated catalog, the GitHub dsh-plugin ecosystem and the npm registry into one storefront, with source whitelisting, conflict pre-checks, trial-boot install verification, manual/batch/auto updates and .dshpack feature-pack management.

Multi-candidate mode for DeepSeek Harness (test-time scaling): floating panel config, the agent auto-runs parallel candidates plus verifier selection, scoped to the current session.

Static bundle form of the DSH plugin-install security gate: reviews cordis_define/cordis_run with a fail-safe policy, plus review/audit tools and a browser approval popup (agree / agree+whitelist / reject; agree+whitelist writes the plugin family into tru

Screenshot feedback for DeepSeek Harness — let your coding agent SEE what it builds

Customize the PC mouse cursor for every UI state inside DeepSeek Harness. 在 DSH 里自定义鼠标各种状态的图案。

Draft polish for the DSH composer: one-click AI polish of the input draft (sparkles button next to send), with optional conversation context and a configurable model channel.

China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.