Plugins

Per-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.

Session-based task board in the sidebar: drag sessions into todo/doing/review/done columns, create sessions with model and reasoning-effort selection, trash with restore, notes, export/import.

Compact Codex coding mode for DSH: light prompt guardrails against GPT over-explaining, with an editable prompt and native Codex-style tools.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Skin manager for the DSH web GUI: discovers installed skins and switches the active one from a dedicated Settings page, mutually exclusive, hot-reloaded without restart.

Dead-code detection for AI-generated codebases: graphlint builds a dependency graph, finds code unreachable from any entry point to enable codebase cleanup and functional‑effectiveness understanding, and exposes graphlint_query / graphlint_build / graphlint_config tools plus a graphlint skill to DSH agents.

WeChat automation for DSH: push task progress to WeChat, listen for messages with keyword auto-reply, and a WeChat ↔ DSH two-way bridge controllable from the settings page, built on wxauto4.

Complete wuyun-liuqi (five-evolutions-six-qi / 五运六气) Traditional Chinese Medicine skill pack as a DeepSeek Harness Cordis plugin: annual and guest-qi calculation, clinical pattern differentiation, and pathogenesis reasoning.

Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, needs-your-input, and error tones; silent for plain chat, system-level playback (works in background), cross-platform (Windows/macOS/Linux), custom TTS sounds.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Database tools for agents: list/query/exec/schema/stats/health across SQLite/MySQL/PostgreSQL, with lexer-grade read-only protection, row caps, CSV/JSON query output and an approval-gated write path.

Biomimetic memory system for DeepSeek Harness: a single SQLite store (node:sqlite, WAL) whose Markdown tree is kept as a read-only mirror; memory tools, frozen-snapshot injection at session start, graded approval gating, on-demand extraction of the current session, near-duplicate merging, an archive and supersede lifecycle, memory metabolism (dream), memory pins, semantic recall over local embeddings, and the /memory command.

LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged over MCP.

Web theme and file workspace plugin with global typography controls, @file mentions, a project file tree, Markdown preview, and a resizable side panel.

Nine complete dsh-web-ui skin replicas with custom skin-pack import, preview, apply, delete, restore-default, and readability fixes for bubbles and code blocks.

Configurable DSH usage statistics: a sidebar text/card widget plus a detail dialog with per-provider and per-model breakdowns, cache-hit rates, token trends, and latency details (TTFT and duration).

Codex-style tool call folding, collapsing multiple tool calls into a single line.

Windows XP Luna desktop for the DSH Web UI: a floating window manager with taskbar and desktop icons, plus the era-accurate Luna skin.

A floating balance widget for the Web UI: live DeepSeek account balance with manual refresh and a Y/N-confirmed graceful exit.

LLM-free lossless* compaction engine for DeepSeek Harness

DeepTutor tutoring bridge: deep explanations, self-test questions, learning-path planning, personal knowledge-base search (RAG), and note archiving via deeptutor_run / deeptutor_kb / deeptutor_note tools.

Codex-style desktop pet: a floating animated sprite in the corner that mirrors the agent's running state (working, waiting, failed, done).

Chat with, monitor, and approve your DSH agents from WeChat via the iLink gateway: text both ways, session targeting, digest heartbeats, and numbered approval prompts.

Bring your existing Agent Skills (SKILL.md) library to DSH: discover skills across Claude/Codex/Cursor/Gemini paths, inject a progressive-disclosure index, and load bodies on demand.