Plugins

Folds oversized tool results into on-disk spill files with deterministic head and tail markers, indexes compaction summaries in a searchable ledger, and extracts cross-session memories with per-project scoping. Any folded content is restored byte-for-byte on demand through one tool call.

Multi-channel IM bridge for DeepSeek Harness: each QQ (SnowLuma / OneBot v11, official QQ Bot) or Discord group and private chat becomes its own agent session, bound to a role card whose domain carries knowledge bases with draft approval, shared memory, a read-only GitHub reader and group trigger rules; two built-in personas (customer support, group chat), unified push with broadcast, and human hand-off.

Draggable bubble graph of DeepSeek Harness workspaces and sessions in the Web UI: workspaces are large bubbles, sessions are small ones, and lines show real membership. The canvas supports pan, zoom and fit; filters cover workspace, status, type and archive state; search covers workspace names, paths and session titles; native actions open or create sessions, rename workspaces, and archive or restore sessions. Layouts are saved in the browser.

DeepSeek Harness's own fast mode: a few configs that set how fast a task runs — bound where thinking settles, bound the process narration, bound the steps per task — faster delivery without touching the model or its thinking strength. Measured over 10 task families and 30 complete units: the default reaches 0.72x total time, 0.74x output tokens and 0.71x steps; moving the "write it once" reminder from step 4 to step 2 gives debugfix 0.535x, ledger 0.506x, migrate 0.751x, and 0.625x pooled over 13 pairs with 0.614x output tokens (migrate alone 0.509x with 0.528x output at step 3). Hidden tests passed in every pair. Short 1-5 step repairs and data reshaping do not pay for the reminder, so try it once per task shape.

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

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

Study coach for DeepSeek Harness: turns a course into a knowledge map of subject, module and unit, records mastery per unit in six stages, plans daily tasks against a materials index, keeps a wrong-answer book and spaced-repetition cards, and serves its own web panel.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

Arknights theme for the DSH Web GUI: twelve full-screen wallpapers whose edge blur, feathering and glass opacity are computed per image; ink solved in OKLCH to hold WCAG AA; Rhodes Island iconography throughout; and approval and question cards signed with operator autographs.

Knowledge-base plugin: build auditable KB packages (references + SQL).

Read assistant replies aloud in DeepSeek Harness: text-to-speech providers with streaming playback.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.

Real-time usage, cost and balance meter for DeepSeek Harness: official-API balance, cost accuracy within ¥0.02, per-turn / per-session / per-model cost ledger, live color-tiered token speed and a docked one-click popup.

Conversation minimap docked on the right edge of the dsh Web chat: colour-block and to-scale thumbnail modes, drag-to-resize (10–320px), hover loupe preview, click-to-jump and drag-to-scroll with a live viewport indicator, and collapse to a 4px strip.

Conversational Markdown mindmap workspace: edit complete documents step by step, keep a live right-side visualization synchronized, and open, manage, and export mindmaps from the working directory.

Liquid-glass theme for DeepSeek Harness with SVG edge refraction on the composer, bubbles, queue dock, menus and sidebar, translucent token overrides driven by live sliders for tint, opacity, blur and refraction, custom or built-in animated wallpapers, and desktop chrome extras such as a session bar merged into the system title bar and a fullscreen button.

Vertical message pointer rail on the left edge of the chat: one dash per user message, click to scroll to that message, hover for a preview bubble.

Local code knowledge graph for agents: parse a codebase (Python/JS/TS/Go/Java/Rust) into a SQLite index and answer callers, callees, deps, dependents, impact and full-text questions over it.

兰亭 CLI 命令工具化 + L0 守卫：记忆面 9 工具 + 质量面 6 工具（defineTool 注册，spawn venv _cli.py）+ 直写/直调守卫

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

Complete mobile PWA for DSH, built on dsh-mobile-gate: secure remote-access gateway plus install-to-homescreen (manifest + service worker), offline capability, touch gestures (pull-to-refresh, edge-swipe back, pinch-zoom font), agent-done push notifications, and touch-first layout — desktop unaffected.

Folio (兰亭) @nyantused/folio-dsh-tools: 15 schema-validated tools (memory + quality gates) plus an L0 guard of the consulting document-generation engine; pair with @nyantused/folio-dsh-events for the full session protocol.

Folio (兰亭) @nyantused/folio-dsh-events: session-protocol events — auto session-start reminder + auto-save on session close; pair with @nyantused/folio-dsh-tools.