Plugins

Ecosystem infrastructure: a thin browser console for managing official repository plugins (zero patches) plus a make-dsh-plugin skill for guided plugin development.

Commit-time audit harness for AI coding agents: 28 git-diff rules (secrets, out-of-scope edits, prompt injection), HMAC-signed audit trail, snapshot rollback, and a full MCP toolset. Installable via dsh plugin add.

Data quality checking for DeepSeek Harness — profiling, cleaning, and verification pipelines with structured reports.

Aggregated IM gateway for DeepSeek Harness: drive agents from WeChat, Feishu, Telegram, Discord, QQ, WhatsApp and 20+ chat platforms with unified sessions, remote approvals and interactive questions. By default, anyone who can message a connected bot can drive the agent; configure allowedUserIds to restrict access.

Lets the AI insert streaming-generated UI into the conversation or a side panel, written in TSX — already one of the model's native languages, so there is no JSON schema to teach it. Rendered without flicker, state kept across frames with no hard remount, and a click in the card driving the next chat turn. Inline is where streaming matters most; the side Canvas is the more agentic shape. Cards get agentic capabilities of their own — run bash, curl, call the model, read and write files.

Lets the agent start a conversation on its own, using a local dice roll on a set interval to decide whether to speak into a chosen session, with quiet hours and a dry-run mode.

Personal assistant for DeepSeek Harness that turns conversational commitments into cross-session plans, reminders, and an auditable dashboard.

DeepSeekBot: the open-source Grok Bot alternative for DeepSeek Harness. PersonaBots with their own identity, Git Memory, Groups and Lark, Slack, Discord and WeChat identities.

Remote DeepSeek Harness with full server-side API access (`settings.*` / `credentials.*` / `host.listDirectory`). Token-gated reverse proxy, per-device sessions, phone invite QR, fence self-check, optional approval / CIDR / idle timeout / local TLS, WebSocket/SSE.

QA pipeline as 10 agent skills: requirement analysis, test strategy, case writing and review, E2E (Playwright) and API automation, exploratory, regression scope and bug analysis, backed by a shared knowledge base with format rules, risk model and schema validators.

Per-round cache billing inside the composer context-meter popover: what the current call spends on cache hits, misses, and output in CNY, with automatic official peak/off-peak and per-model pricing; hidden on non-official DeepSeek routes.

ChatGPT account sign-in for DeepSeek Harness through a Codex browser OAuth flow with no API key and no workspace selection: subscribes the login to pi-ai's Codex provider, lets you set the global default Codex model and reasoning effort for new sessions, refreshes the model list from the signed-in account's own catalog endpoint, and shows the five-hour and weekly usage windows in the composer.

Keep branching from any completed answer at any depth while the main session stays untouched.

DeepSeek Harness appearance toolkit. Independently tune opacity + frosted-glass blur across 8 surfaces (main background, sidebar, cards & panels, inputs & controls, settings, conversation frame, trajectory view, produced/highlights — 9 with dsh-better-sidebar). Use any image or video as wallpaper with a drag-to-pan, scroll-to-zoom position editor and 5 layout modes (Fit/Fill/Stretch/Tile/Center); videos loop muted, survive refresh, and capture a live frame for preview, color extraction and framing. Rotate a pool of images (shuffle/order, every refresh/daily/weekly). Also: PS-style color wheel, one-click wallpaper color extraction, 6 presets + saved profiles, day/night auto switch, and full theme export/import.

Skill-driven harness/loop engineering workflow agent plugin.

Normify · DSH 插件：把项目架构写成归一化的分形模块树，三层校验（写时 / 校验 / 冻结回执）、30 个 normify_* 工具 + normify-gen 技能，一键渲染单文件交互式架构图；支持伴随式开发（change_open → brief → check → 实施 → refresh → change_close）。

TapTap Maker integration for DeepSeek Harness: bundled MCP tools, Maker workflow and feature skills, plus a packaged CLI path for project initialization and diagnostics.

Zotero as an evidence store for agents: search your library, inspect metadata and notes, retrieve evidence passages, open source PDFs, and generate citations and bibliographies.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.

Local Obsidian vault as the agent knowledge store, with read-only DSH tools that route status, preference, correction, memory, project, search, and suggest to the matching page.

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Say goodbye to copy-pasting and DSH Token anxiety. Let ChatGPT on the web connect directly to your local project, code on its own, and hand complex tasks to DSH for sustained execution.

A Claude-persona desktop pet pinned to the bottom-right corner of the DSH web GUI — shows balance, today's usage, peak/off-peak pricing and per-turn cost, with editable bubbles (text, balance, usage, pricing, images, random lines and weighted choices), per-line styles and fonts, a floating quick editor, sound effects, and custom character/audio. Ships animated roles that breathe and blink, plus a balance-alert variant that switches to a crying face when the balance falls below the alert line; 256/384 animation tiers and an optional 512 HD pack installed from the resource manager. 63 Claude-flavored lines. A derivative of MeteorNOX/DeepSeek-Balance-Whale-Widget (MIT).

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.