Plugins

Long-conversation memory for DeepSeek Harness (DSH): keeps settled decisions, user corrections and exact numbers, with their conditions and sources, available across compaction and restarts in 100-1000+ turn sessions; one small budgeted evidence block per model step, with enabled skill rules re-applied in the same block.

Export the current session as a readable Markdown file with dialogue only: user messages, assistant text, and ask_user_question answers, from a session-header button or the /md command.

Adds edit and delete to your own message bubbles: editing truncates the following turns and resends the new text, deleting removes the message and those turns, and either can optionally roll back the recorded file changes of the removed turns (refusing when a file has changed since). The sidebar keeps a single conversation.

Regenerates a session's title from its last 10 user prompts using the model the session itself last used, with an editable preview before the new title is written back.

Lists every DSH workspace and its conversations on a settings page with checkboxes, and deletes the checked conversations or whole workspaces together with their session logs, projection caches and workspace registrations.

Smart naming for sessions and workspaces: one click asks the profile model for short name candidates from the item's own content, then renames in place.

DSH Session Fork Tree Arrangement: forked sessions sit under their parent with an indent and a rounded connector, sessions that own forks carry a green "+" that collapses by default and expands level by level, and hovering a child highlights its ancestor chain.

Writes one short line into the system prompt only when a stress, energy or reward value crosses a threshold; the values rise on real session events and decay over time.

Turns the MiniMax Code (Mavis) subscription already signed in on this machine into a DSH model provider, renewing the OAuth token itself so the desktop client can stay closed, with points, check-in and subscription-quota panels.

Connect a self-hosted Magpie gateway with one provider route per upstream owner, so the stock model picker shows Magpie (Claude), Magpie (Codex) and other groups, plus automatic multi-line failover, read-only usage cards, per-model default effort, a per-session fast switch for priority-tier models, and optional Cloudflare Access.

Declarative provider/model fallback chains for the model picker: an ordered root chain plus named pools, failure-code triggered switching, per-model cooldowns, time-slot presets, and subagent role routing. A fork of omdsh-dev/dsh-llm-fallbacks 0.6.5; do not install it alongside that plugin (both use the "llm-fallbacks" profile row id).

A dark, glassy Scaramouche theme for DeepSeek Harness with static and video wallpapers, opening video, ambient music, particles, and a draggable dock.

K-ON! themed tea-table widget: click it to see the DeepSeek balance, today's spend and peak-hour state; each finished turn pops a cost bubble; double-click shows zh/ja character lines.

Saves tokens in DeepSeek Harness sessions by reading any file by line range or symbol mention instead of whole, and by bounding oversized tool results while keeping a recovery path. Pruning happens at the source, not after content reaches the context. Measured 43.9% fewer prompt tokens in a modelled 30-step session.

Sidebar badge and panel showing the balance, daily spend and remaining runway of a New API relay, with a top-up link.

Alibaba Cloud coupon balance, used amount and expiry in the sidebar footer, read through the read-only BSS OpenAPI.

Tokenrhythm billing center for DeepSeek Harness: account balance and expiring quota, model price cards, a 30-day usage heat calendar, connectivity checks and platform API-key management, with credentials kept on the local host. A single-channel fork of 162568316/dsh-tokenrhythm-bill; the package name, Cordis id and route prefix all differ, so the two can be installed side by side.

Fudan · Desktop: DeepSeek quota and campus-weather status bar, six curated campus wallpapers, and a fully local 知行台 schedule/knowledge workspace with a Fudan editorial UI and week-by-week review.

VS Code style 44px icon rails for the side panels DSH collapses: the left rail keeps the sidebar navigation and the bottom action rows, the right rail lists the sidebarRightTabs ledger so third-party tabs appear on their own, and the right panel is drag-resizable between 300px and 60% of the window. Two switches under Settings → Activity Bar, saved in this browser.

Session-header fishbone panel for sub-agent assignments, live status, available token and duration metrics, shared task-board entries, and native child-session navigation.

Lets the model turn an answer into a web page that lives right inside the chat. The show_page tool either fills one of 8 built-in templates (report, compare, checklist, dashboard, timeline, flashcards, quiz, flow), where the model writes only the content and the plugin does layout, interaction and saving, or saves a full page the model wrote itself (calculators, games, custom layouts). Hand-written pages get the same design as base styles inside a CSS @layer, so the page's own CSS still wins. The page appears under the reply at its content height, interactive and following DSH's light/dark theme. The page's localStorage is stored in DSH per page, so what users tick or type survives reopening and new versions, and the same page open in the chat and the right sidebar stays in sync. Each edit is saved as a new version you can flip back to. After saving, the page is checked in a hidden local Chrome or Edge (script errors, horizontal overflow, dark mode not applied) and problems go back to the model. The right sidebar shows the page full-size with versions, a gallery of all pages and export to PNG, PDF or HTML. Pages run in a sandboxed, separate-origin frame with a strict CSP: no access to DSH data and no fetch, XHR or WebSocket. Works on phones with dsh-mobile.

Shows a dimmed suggestion of the user's next message in the empty composer after a settled turn; Tab accepts it into the draft and Escape or typing dismisses it.

Rewrites the composer draft into a tighter prompt in one click and restores the exact original in another, running on Harness's own models by default or any OpenAI-compatible endpoint, with an editable polishing prompt.

Adds a button to the composer that restates your draft, then asks a few questions with clickable options — every question offers an "I don't know, you decide" escape — and only then rewrites the draft into a request an agent can start on. The whole flow can be finished without typing, and it never sends for you.