Плагины

Bi-temporal memory backed by a SodaMem daemon: recall is contributed to the prompt while each turn is assembled and every closed turn is ingested, with no tool call and no model call on the read path; each recalled fact cites the turn it came from and carries validity dates, so superseded facts stop being retrieved.

Rewrites each request against a learned prompt profile and automatically updates habits, anti-hallucination rules, and learning records.

Git-style conversation fork graph in the session header: colored lanes and fork curves show which session branched from which, with click-to-jump navigation.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

DeepSeek wallet balance at the sidebar foot: a credit-card icon with the amount tinted by remaining balance (green over ¥2, amber ¥0–2, red below), refreshed on mount, per turn-end, and on click; a signed delta floats up and fades on each balance change.

Per-turn and session-wide LLM cost metering: a dollar cost line under each message, a session cumulative total with hover breakdown, and an LLM+web price auto-refresh tool.

File-browser web app for DSH: React frontend and REST API served by the host webserver, a /dsh-agfs command that opens at the current session workspace, and a browse_files model tool.

Независимый слой приёмки только для чтения: запускает верификатор только для чтения перед закрытием каждого верхнеуровневого хода и возвращает агенту непройденные проверки.

Multi-style skin collection for the DeepSeek Harness (dsh) web GUI. Each skin registers a theme (Settings → Appearance / sidebar picker) plus scoped decoration CSS keyed to its active state.

A floating whale desktop pet for the DeepSeek Harness Web UI: 94 categorized animations, event-aware actions, custom uploads, click reactions, dragging and screen wandering.

Connects a Feishu self-built app over WebSocket, routes each chat to an independent DSH agent session, and streams replies through a Card JSON 2.0 card with plain-text fallback.

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.

Usage statistics settings panel: 26-week activity heatmap, daily token trend with a cache hit-rate curve, per-model donut and breakdown, plus a one-time historical session backfill.

Cross-border commerce: HS codes, customs invoices, mainland reachability. HS/HTS code lookup and classification, commercial invoices, live exchange rates, IBAN and EAN/UPC checks, amount-in-English for documents, and whether your site is actually reachabl

Lovstudio dev click-to-source for DeepSeek Harness web: runtime-only, reads React _debugSource on Shift+Option click and opens the editor. No build-time markers; works in vite dev (jsxDEV __source).

统一插件市场（Unified Plugin Market for DeepSeek Harness）：聚合精选目录（awesome-dsh-plugin.com）+ GitHub dsh-plugin 生态 + npm registry 三源；对 DSH Desktop（EAC）特化（web-desktop profile）；来源白名单 + 冲突预检 + 试装验证；后台自动检测 + 可配置自动升级 + 市场自更新；一键检查/全部更新/逐个更新，更新进度窗口

Browses the petdex.dev catalog in Settings and runs a floating macOS desktop pet that reacts to agent activity.

Adds a configurable dsh-ui status card before each DSH agent reply, with bilingual templates and a live settings preview. Requires @omdsh-dev/dsh-genui from dsh-market; without it, the card markup is emitted unrendered.

A global Automation Center with fresh, auditable scheduled Agent runs for DeepSeek Harness

DSH plugin: append each answer's token usage to the conversation

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

Bot Mode for DeepSeek Harness: a roster of named bots with avatars, personas and per-bot chats, each backed by one durable continuable subagent session that keeps memory across turns.