Plugins

Telegram, Discord, Slack, Mattermost, Zulip and Matrix channels in one plugin, with per-conversation sessions that survive restarts, a Settings page that adds, tests and saves channels without YAML, and a fail-closed allowlist that rejects every sender until one is configured.

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`.

Structured image recognition: local sharp measurements plus a cloud vision model return description, OCR with coordinates, object locations and fine-grained attributes in one call; a fingerprint cache makes repeated images return in milliseconds without spending model quota.

Multi-source image search and download (14 engines + 7 aliases covering Baidu, Bing, 360, Duitang, Huaban, Iconify, DuckDuckGo, Yandex, Openverse, Wikimedia, Pixiv, Wallhaven, Konachan and Safebooru) that saves the picked images into the session workspace with a per-file meta.json and renders them inline in the conversation; ships a standalone CLI as well.

In-chat image viewer for the web UI: takes over content image clicks (Markdown images, message attachments rendered as blob: URLs, and read_image results) and opens a dialog with pointer-centered wheel zoom and an editable percentage, drag pan, 90° rotation, download with progress, copy as PNG, open with the default app, and ←/→ gallery browsing across the conversation.

Adds a right-column panel that compares a set of images the user picks from the workspace — 1/2/3/4/6 per page, per-image zoom and pan, the zoom and viewed position of one image synced onto the whole set, and a reorderable filmstrip. The browser loads every image, so none of it reaches the model.

Import the copied connection information from the new API site with a single click.

Inlines an image block as base64 only in the one request where it first appears, and marks that same block offloaded on every later request so DSH's own image-offload projection renders it as the placeholder text carrying the read-only local path. An occurrence is keyed by session id, message id, content-tree path and attachment id, and a request is only counted after it produces its first chunk, so retries do not count as sent. Requests carrying a purpose are neither rewritten nor counted, a later read_image of the same file is a new occurrence and inlines once more, and only that request's copy is rewritten, so nothing is written back to the session.

Image generation for DeepSeek Harness through an OpenAI-compatible relay (configured for `api.ykh.ai` / `gpt-image-2`).

Re-encodes WebP attachment images to PNG so alpha-channel images load on LLM backends that cannot decode WebP (e.g. llama.cpp).

Runs git in the Host process so push, pull and fetch work inside the agent sandbox; exposes 8 agent tools (status, diff, log, stage, commit, push, fetch, pull) and 11 slash commands including /git-status, /git-commit, /git-tag and /git-name-set.

Shows oversized images to the model at readable resolution instead of one downscaled copy: before admission, a large upload is split into as many tiles as the attachment store allows (an 8000x8000 screenshot becomes 20 tiles of 2000x1600), so small text survives. Replaces the local attachment store; adds no settings of its own.

Displays generated images in a conversation gallery with a lightbox viewer.

Ask the user a question about a local image; the DSH Web card offers zoom, pan, box, brush and lasso annotation, NG/OK/unsure verdicts and a note, and the agent receives annotations back in source-image pixel coordinates.

Digests the images in a prompt with a vision model before admission, so any model — a text-only one included — can read them without the session ever switching models, and adds a describe_image tool for image paths.

Trims historical images in outgoing chat requests down to a recent-image count, learns the provider per-prompt image cap from HTTP 400 responses, and retries with fewer images so image-heavy sessions keep working.

Configure multiple image providers in Settings and call image_generate with the one selected model; images save under generate/image and show inline in the conversation.

Two-way agent bridge for Feishu (Lark) and DingTalk groups: chat with a DeepSeek Harness agent from IM groups via long-connection / Stream Mode — no public port needed. Workspace selection/creation, session switching, archiving (synced with DSH GUI), configurable from the DSH settings page. Feishu uses interactive cards, DingTalk uses text commands.

Model-facing image-generation tool with a configurable channel and normalized image parameters.

腾讯 IMA 是一个非常好的知识库应用，但是他们提供的skill版本针对公开知识库的检索方式只提供了基于文件标题的关键字检索，好一阵无语。为了补足在harness的这种知识库检索能力，基于tencent-ima-copilot-mcp迭代了对应的dsh版本。

Adds a paperclip image-picker button to the conversation composer - pick reference images through the system file dialog and feed them straight into the official attachment pipeline (thumbnails, limit checks, upload with message).

Scheduled bilingual financial reports for DSH: market quotes, news and macro calendar, with per-target timezones and delivery through eight dsh-im channels.

A DeepSeek Harness web plugin: set a background image and adapt the UI's text, background, brand and border colors to the image palette automatically.Built with DeepSeek Harness

Show the image a read_image call returned, inline in the tool row it belongs to