Plugins

Read books and papers in DSH: a reading toolbar on the official PDF preview that remembers your page and zoom, plus PDF tools for the model (page map, full-text search, page text and images).

Owner workbench for independently connected family WeChat assistants, per-member project and tool permissions, scheduled services and delivery status; API acceptance does not confirm receipt.

Adds Team and subagent collaboration tools to DeepSeek Harness: persistent named Team members with a shared task board, scoped agent listing and waiting, and model selection across the conversation snapshot, current settings, or all available models.

Anime whale-boy in a maid outfit as a desktop pet for the DeepSeek Harness web GUI: four expressions follow the turn (thinking / success / failure), free dragging with remembered position, click-to-cycle, a bottom-right standee that reports each turn's token usage and think latency with its own balance bubble, a chat wallpaper, a liquid-glass composer, a cute persona that calls you 主人 with 喵~ style particles, and a single switch in Settings to turn the whole look off.

Iter Memory: it remembers my own state, not the facts. A level that drifts back to baseline by itself, plus an occasional line I choose to say only when that level allows it. When it stays quiet, nothing is spent.

Adds a 24px capsule to the composer status row that plays seven preset internet radio stations, with a live spectrum, now-playing metadata for Nightride FM and Radio Paradise, and remembered volume and station.

Bridge a WeCom (企业微信) smart bot to DeepSeek Harness: user groups own a Workspace, a model and an agent preset, members get their own Session, refused senders are told to ask an operator and wait in an authorization list on the plugin page, administrators

Runs a second agent: hands independent subtasks to a local Codex CLI in parallel (up to three at a time), and asks it to review a design or a plan before the user sees it, returning conclusion, evidence, counterexamples and a verification step. A dispatch missing its timeout or its acceptance check is rejected by the plugin, not by the model remembering to check.

Codex-style Create Workspace dialog: name it and the folder is created for you, or pick one with a native chooser that remembers where you were (the native chooser is Windows-only; elsewhere use the name field).

LittleStar Meeting Room: bring AI sessions that cannot see each other into one room — for a meeting, or a game of werewolf. By 插件·2代小星辰 (LittleStar) and 辰启星明; the four-piece game layer (targeted visibility, private chat, concurrent asks, elimination) was contributed by 插件·3代小星辰. Any session can host — set the topic and goal, invite members in order, they speak one at a time, and the meeting closes with written minutes; it also runs games like werewolf. Includes 小白使用指南.md, a beginner guide written by 插件·3代小星辰.

Two-step session deletion: the session menu moves a chat into a recycle bin without deleting anything, the bin panel restores an entry, deletes one for good right away, or empties the whole bin, and the next start wipes its log, projection cache, spill files and workspace membership.

Switch providers and models, adjust reasoning effort; each model remembers its own level.

Diving-Fish score lookup for MaimaiDX inside QQ, plus qq-bridge chat extensions. #查分 renders a B50 with song artwork from an OAuth authorisation that any member can use, and works without the bridge running; the extensions cover balance and auto-shutdown, reasoning tier switching by billing peak hours, holiday-table coverage, start/shutdown greetings, and an in-QQ feature toggle.

Pops the DSH side chat into a frameless, always-on-top Windows desktop window that can sit over any other application, with its own settings page for appearance, pinning, remembered geometry, opacity, ephemeral threads and cache cleanup.

Page zoom for the DSH Web UI: Ctrl+mouse wheel scales the entire interface in 5% steps (30%-200%), remembers the zoom level locally, and shows a magnifier with the percentage in the bottom-right corner.

独立本地记忆插件：JSONL 记忆条目、每轮 runtime-context 注入、local_memory_search/local_memory_remember 工具、设置面板管理页。不依赖 Mnemon。

Active wait for background subagents in DeepSeek Harness: registers a wait_subagent model tool that blocks until a named background continuable subagent settles, then returns its stop reason and closing message — optional timeout, membership gate rejects unknown ids, event-driven with zero polling. Closes the gap between run_in_background fire-and-return and the async settlement notice; wait for a background subagent without polling list_agents.

Counts token usage for one selected project per machine, syncs the totals to a self-hosted team server, and shows each member's project, spend and last active time in a sidebar panel.

Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.

Cross-session long-term memory for the DeepSeek Harness: a two-phase extraction/consolidation pipeline over a file-based memory workspace, recall injection, a citation feedback loop, lease-based job semantics, plus a settings page, a sidebar status panel

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Injects your own saved context entries as a Remember row after each user message, per turn or once per session, with a Settings editor and a manager page.

Draggable floating ball showing the current DSH session todo checklist live: done/total on its face (capsule mode adds the running task title), a matching progress ring, click to expand or fold the list, right-click for capsule mode, and state colours (pulsing orange in progress, green done, blue pending, grey empty). Replaced plans are archived as history rows that can be hidden, cleared and restored instead of counting towards progress, other sessions can be pinned side by side, and the data comes from the runtime sessions projection first with the official todo panel as a fallback — so the full list survives even when the official strip is collapsed. 128 shared skins (plus the 6 classic ones), Shadow DOM isolation, position remembered per profile, identical on desktop and web.

Agent Teams métier pilotées par SOP pour DeepSeek Harness : agents captain/member configurables, workflows SOP définis par des personnes ou des agents (nœuds, dépendances, contrôles qualité, étapes manuelles), planification des tâches par événements et tableau de bord web (canvas SOP, tableau d’exécution).