Plugins

In-session cd for DeepSeek Harness: re-base relative paths on the fly (the file tools and the bash/pwsh default workdir follow) or move the session to another workspace for real — a `cd {"workspace": true, "confirmed": true}` call the user has agreed to, or the user's own `/cd <directory>` command, relocates the session's stored log, sandbox root, AGENTS.md and skill discovery and sidebar grouping. Per-session, persisted across restarts, without moving the session for a plain re-base.

Full upstream REA 6.4.0 integration over the official DSH MCP bridge: all 170 tools, the version-matched reverse-engineering skill, and the six original MCP prompts with argument completions reachable from the composer / menu, all sharing one REA process and complete structured Evidence. External analysis engines are bring-your-own.

Finishes 头歌 (EduCoder) homework over the platform JSON API, with no browser automation. educoder_sweep scans every course for homeworks that still have unfinished challenges — complete homeworks are skipped without reading a single challenge, so a full-account scan costs no model tokens — and can finish them; multiple-choice challenges also cost no model tokens, because the platform returns the answer key in any submission response, while code challenges are generated by the model, uploaded with evaluate:0 and graded once per challenge, then retried using the error report the platform returns. Three tools: educoder_sweep, educoder_homework, educoder_account.

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.

Hierarchical workspace tree plus browser-style session tabs for the DSH sidebar: a "/" in a workspace or session title creates a virtual folder, with sections, pinning, time buckets, drag ordering, unified 6px status dots, per-row appearance customization (colour, glow, weight, icon) and a floating full-text search over session titles and message bodies. Several settings switches restore any behaviour to the host default, and a host-side route deletes sessions permanently (DSH ships archive only). Fork of KannaKuron/dsh-better-workspace.

Category tree for the DSH sidebar workspace browser: workspaces and their sessions nest under user-made categories (collapsed state remembered), rows drag between categories, a new workspace can be created straight into one through the directory picker, categories rename and delete in place, sessions archive and unarchive from their own row (the built-in browser's stop-active-work confirmation included) alongside a hide / show / only-archived filter, row buttons carry the app's own hover tooltips, and a footer toggle switches the panel back to the built-in list.

Adaptive topology multi-agent preset for DeepSeek Harness with peer messaging, task handoff and live network visualization.

Injects a small continuity pointer at the start of a new session, naming the previous session and any handoff file, and reuses DSH's own compaction summary when there is no handoff file.

Role-play plugin for DeepSeek Harness: imports SillyTavern character cards (JSON/PNG) and world books (lorebooks), binds DSH skills to a character, and registers the combination as a native agent preset.

Heads-up Texas Hold'em training with an independent AI opponent, persistent public-action memory, and decision reviews.

Turn a set of DSH plugins into one pasteable share code, then install it plugin by plugin — with a QR code to carry it to a phone.

Discovers rule files from every convention OMP supports and injects them into the system prompt as an always-apply layer plus a rulebook index, then enforces them with time-traveling stream rules that abort violating output mid-turn, deny a matching tool call, fold a reminder into that call's result, or ask a judge model about the finished reply. The same tool lets the model write new rules, and an audit panel on the Plugins page says why each rule is in force.

Chinese multi-agent workflow with per-role model fallback, versioned Mermaid task plans, independent Agent and Jev reviews, persistent expert collaboration, and pure-function calculation tools.

Delivery board for client-project teams: stage pipeline (default or governance template, or custom stages), cards with owner, due date, acceptance criteria and DoD, an automatic handoff audit log when a card changes stage, a progress/risk/blocker/decision log, a weekly Markdown client report, a loopback-only drag-and-drop board and a read-only HTML export; state lives in delivery.json in the workspace (11 delivery_* tools plus a /delivery command).

Video editing toolset for DSH: probe, trim, concat, audio handling, subtitle burn-in, transform, transcode and frame grabbing, powered by ffmpeg downloaded on first use.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

OpenCode Console (Zen) models for DeepSeek Harness: paste a Console API key under Settings → Plugins and the Console's chat models become selectable, with the catalog synced automatically, each model routed to the endpoint the official docs assign, and free *-free models hidden by default because they only run inside the OpenCode client.

Full-interface whale skin pack for the DSH Web UI — layered wallpaper, metallic trim, lace and bows, a corner mascot that reacts to agent state, ambient particles, plus an installable third-party skin-pack format.

Full-screen boot animation for the DSH web client: the boot HTML paints a cover-fit artwork on its first frame, adds a slow settle, a scanning light sweep and a progress HUD, then hands the viewport over when the app mounts. Click or press Esc / space / Enter to skip.

Todoist-style todo management in the sidebar with projects, labels and priorities, CJK-aware natural-language quick-add, repeat rules, a stats dashboard, import and export, seven agent tools and due-time reminders.

Turns each long dsh conversation into a three-level trail (topic to progress steps to milestone timeline) and shows it in a draggable overlay, where one click jumps back to the matching message in the transcript. Topics are distilled by the DeepSeek model with a zero-cost rule-based fallback, can be renamed, locked, merged by drag and drop, and support per-conversation notes plus a vector drawing board.

SapBuddy —— SAP ABAP AI 全能助手（DeepSeek Harness 插件）：41 个 SAP 工具 + 8 个 ABAP 技能 + SapBuddy preset + 连接设置页。一个包名装完。

Shows the DeepSeek account balance at the bottom of the sidebar, with a configuration card on the Plugins page.

Engineering intelligence for coding agents — persistent, evidence-aware, project-isolated engineering memory with unified hybrid search (memory + RAG documentation) for DeepSeek Harness.