Plugin

DeepSeek Harness (dsh) 右侧账户计量小框：多账户（DeepSeek / Kimi 等）余额 + DSH 内消费统计，当前接入账户高亮，消费口径标注「DSH 消耗」，设置页可视化账户配置。A right-side account meter for the DeepSeek Harness Web GUI: per-provider balance, DSH-local spend, active-account highlight and a visual account edito

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.

Character skins with an editable decoration board — Yukino warm daily and occult editorial themes, each with dual character sprites + sticker sheets, drag/resize/rotate coordinate editor, custom asset upload, and shareable diorama packs (assets + layout bundled).

Project knowledge base plugin for DeepSeek Harness: Open Knowledge Format (OKF) bundles per project, agent search/read tools, a Web UI browser/editor, and a bundled OKF authoring skill

FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.

VS Code-style workbench inside DeepSeek Harness Web: activity bar, explorer file tree, source-control (Git) panel and editor tabs — backed by real filesystem & Git routes.

文件改动确认机制（双面插件）：write/edit/str_replace_editor 写入前弹出确认条，内嵌 GitHub 风格 diff（行号 + 红删绿增），允许本次 / 拒绝。File-change confirmation with inline diff for DeepSeek Harness.

The rich `edit` tool for DeepSeek Harness (replace / patch / apply_patch / hashline modes) with embedded format-on-write and diagnostics — a standalone plugin with no upstream harness changes required.

Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

Update checker (npm edition): a settings page comparing local and latest versions of @deepseek-ai/dsh and every installed plugin, with a red-dot nav reminder and ready-made update commands.

Open registered workspaces from the Web UI in a detected or configured local editor, terminal, or file manager, with a remembered per-browser preference.

A strip above the composer listing files modified in the current session (collapsed by default), with a Review button opening a per-session change panel showing before/after hunks from the session's own edit/write tool results, no git required.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Notes and todos as plain Markdown files in your workspace: type /ml plus a sentence to jot into today's journal; todos come in three flavors — deadline, sleep-until-a-date (auto-wakes when due), and anytime; /ml view fuzzy-opens any file with a few keystrokes. Zero tokens throughout — nothing goes through the model, and your notes stay ordinary local files that git and any editor can read.

Observational file-mutation rollback for the fs tools: write/edit pre-images are checkpointed as git blobs or snapshots and restored through a model-facing rollback_files tool or a /rollback command.

OpenAI-compatible image generation in DSH Desktop chat: generate inline, edit reference images or chain-edit previous results directly (image-to-image) without re-uploading, with storage cleanup.

Turns markdown into a WeChat Official Account (微信公众号) draft: inlines every CSS rule onto its element because the editor discards `<style>` blocks and class names, uploads each local image through WeChat's own endpoint so it is not filtered out, and creates the draft; it never broadcasts.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Manage DSH rules from the web settings panel — edit global/project AGENTS.md, or auto-split pasted rules into layered AGENTS.md and skills via LLM.

Floating workspace file-preview window for the Web client: lazy file tree, CodeMirror preview and in-window edit with save, Markdown and image preview, Quick Open search, and opening paths clicked in the conversation.