Plugins

Small-window mode for DSH NEXT on Windows: a 425px-wide always-on-top sticky window with a drawer sidebar and animated transitions. Requires DSH NEXT; the other desktop client (dsh desktop) is not supported.

Turns the composer send button into a tomato button while a task is running and the draft is empty. One or two taps hand the model a hidden note on its next step asking it to reflect on the approach and to finish by asking the user how to continue; three taps within a second stop the run first and send the same kind of note. Thrown-tomato animations and sound can be switched off in settings, which also counts every tomato thrown.

Send by dragging instead of clicking. Press the composer and pull up to arm the gesture; releasing sends, dragging back into the composer cancels, and dragging outside the conversation area cancels on the spot. Mouse and pen only.

Composer prompt refinement: rewrite the draft through the harness LLM, preview the result, then apply or send it, with style presets, model-aware reasoning effort, cost estimate and a settings page.

在 DSH 侧边栏底部用两行极简文字显示 DeepSeek 余额与当前峰/谷时段。Minimal balance and peak/off-peak readout at the DSH sidebar foot.

Use your ChatGPT subscription in DeepSeek Harness. Sign in, choose GPT, and work with images and built-in tools.

Local image/video wallpaper plus a token-based frosted-glass UI for the DeepSeek Harness Web client.

Review AI-generated Word, PowerPoint, PDF and HTML in the official preview: box problems, edit the text in place, and hand the notes to the agent. PDF and images are annotate-only; editing relies on the Harness bundled LibreOffice kit and Python.

An x_archive tool that turns an X (Twitter) post link into a permanent Markdown snapshot via the 2100laike archive service: images are re-hosted so they never break, snapshots survive post deletion, resubmits dedup-hit and return the latest version without spending quota, and refresh forces a refetch with a PAT. Needs the third-party 2100laike service; anonymous use is limited to 8 archives per day per plugin instance and a registered PAT raises that to 100 per day.

A wb_archive tool that turns a single Weibo post link (m.weibo.cn/status/...) into a permanent Markdown snapshot via the 2100laike archive service: long posts are fetched in full, images are re-hosted so they never break, snapshots survive post deletion, and resubmits dedup-hit and return the latest version without spending quota. Needs the third-party 2100laike service; anonymous use is limited to 8 archives per day per plugin instance and a registered PAT raises that to 100 per day.

Cross-session memory for DeepSeek Harness: a three-tier store (behavior notes, deep details, session archive) plus a 600-character core card injected every step, work/companion/learning state lines, multi-person and multi-group records with visibility partitions, session-scoped suppression or deletion of memory fragments, summaries and fact candidates that can route to a separate model, and backup plus self-check tools. Data is plain text under the home directory, and entries can carry images and audio stored by content hash.

Edit and regenerate: adds an edit action to user message bubbles, regenerating from that message with images and files carried over and the original model inherited.

Alibaba Cloud DashScope provider for Qwen language models, embeddings, reranking, speech, and image generation through native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Meta's Muse Code CLI inside DSH: a composer switch starts muse serve, a right-sidebar panel and five chat tools (muse_open, muse_prompt, muse_read, muse_status, muse_interrupt) share one Muse session, approvals are decided only in the panel, and a local spend guard hard-stops at $10 by default. Windows only; needs the Muse Code CLI installed and signed in. The $10 cap is a local estimate for the muse serve this plugin starts.

Generate images and frontend HTML demos through a real ChatGPT Pro web session, saved locally with a design gallery panel in DeepSeek Harness.

Whale-girl desktop pet for the DSH Web UI, drawn with hand-written SVG + CSS (no image or audio assets, zero runtime dependencies): swims while a turn runs, blows labeled bubbles on tool calls, taps the glass with an amber pulse when an approval is waiting, jumps with a turn duration/tool-count report on success and droops on failure, naps after dark or when idle. Click to poke, double-click to pet (affinity hearts), drag with remembered position, right-click menu (feed / mute / reset / hide), hover card with level, title, XP bar and per-turn stats. A `whale_say` tool lets the agent make her speak or act as a lightweight visible notification. Read-only over sessions and workspace; only ~/.dsh/whale-girl/state.json is written.

LAN co-op for the dsh-pet desktop pet: see colleagues' pets on the same network, wave at them, and drag their desktop windows anywhere; an optional included patch adds live animation, bubble and meme sync. Requires dsh-pet 0.3.7.

Animated pixel-art blue and white whale pet that sits on top of the composer in a new session.

Agentic roleplay for DSH with structured worlds, autonomous characters, persistent sessions, world authoring, speech, and image generation. Requires Firefox2100/dsh-agentic-roleplay#state to be installed and enabled.

Bridge an official QQ bot to DeepSeek Harness in-process: a QQ message starts or resumes a real DSH session inside the host (it appears in the desktop sidebar when its working directory is a registered workspace) and the answer is sent back to QQ as text, image or file. Requires a QQ official bot application (AppID + AppSecret).

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

Shows what each installed skill costs in the model context and hides a skill from the catalog without deleting it. Lists every skill found on disk with the exact catalog line the model receives (description normalized and truncated at the catalog cap), its body size and token estimate; previews the catalog message byte-for-byte as the agent will receive it, compares that with the copy already published in the current session, and reports skills on disk that never reach the catalog (invalid frontmatter, or shadowed by a higher-priority root). Hiding writes disable-model-invocation into frontmatter and keeps the file, so the skill still works via /name. Also imports skills from ClawHub, Skills.sh and GitHub URLs and uninstalls user-owned ones.

Publish size check skill: verifies a deliverable's geometric specs against a target platform before publishing - pixel dimensions, aspect ratio, dpi, file size, format, physical print width and colour mode. Geometry only: it does not review content compliance (QR codes, text-to-image ratio, copyright and prohibited content are out of scope). Pure Python standard library, no third-party packages, and inputs are never modified. Python 3.8+. Covers 10 platforms and 20 slots with per-platform confidence labels - WeChat MP, Xiaohongshu, Bilibili, Zhihu, Weibo, Douyin, WeChat Channels, journal submission, print and client delivery - and resolves a platform by id, Chinese name or alias with fuzzy matching. Two trigger modes: asked directly, or as a parasitic self-check that runs by itself once an image, poster, chart or export workflow has written a file and the user mentioned a publishing target, reporting in one line when everything passes and only expanding when something is wrong. For journal submission and print it judges by physical width (pixels / dpi), which catches files whose dpi metadata passes but whose actual printed size is too small; for multi-image posts it checks whether the whole set is consistent and names the odd one out rather than listing every file.

OCR for scanned, image-only PDFs into Markdown, built around the fact that a book takes about an hour: every page is checkpointed so an interrupted run resumes, a progress log reports live status, and a quality report names empty pages and low-confidence lines. Requires Python 3.10+ and pip install -r requirements; the first run downloads the OCR model.