Plugins

A Bilibili companion that keeps its own schedule. A 60-second tick in the plugin host wakes a dedicated agent session at a random moment inside the configured time windows (opting out of a day is a configurable chance), then hands it a bundled CLI of 38 subcommands — feed, subtitles, danmaku, comments, ffmpeg frame grabs, and two diaries. Shares at most N items a day by commenting on them and @-mentioning the owner (default 3, enforced from a written quota log, and it stops on rate-limit or captcha signals). Also polls comment replies, direct messages and live-room danmaku; replies to anyone but the owner are queued for approval in Settings. Settings → 养鱼 writes ~/.dsh/bili-whale.config.json; cookies live separately in ~/.bili-ai/credentials.json and are never echoed back. The HTTP routes are loopback-only behind DSH's trust fence. Needs Node 18+ and ffmpeg on PATH for frame extraction.

Chat meme stickers: text-only send, mood auto-send, QQ/WeChat-style picker, auto-learn, custom packs.

OpenMAIC: classrooms, slides, interactive widgets, and Socratic teaching.

Mobile-first UX polish for the DSH Web UI: composer auto-fold, enter-as-newline on phones, compact sidebar/header/settings, zoom and overscroll lock, plus approval/question/completion notifications via in-page cards, Web Push, and webhook — zero dsh changes.

Log query card for the DSH Web GUI over Elasticsearch / OpenSearch: one query surface with per-dialect query strings and clickable examples, field-name completion, filter chips, a time histogram whose bars zoom into that window, field facets that turn a bucket into a filter, and a result list with level colors, stack-continuation rows, columns and paging; Docker container logs are a collection source that reuses the docker plugin. Ships five read-only loglens_* tools (sources / search / fields / facets / context) sharing the same execution layer as the panel. Outbound requests only reach configured sources, judged on the resolved IP, without following redirects and with size and timeout caps.

DeepSeek Harness appearance toolkit. Independently tune opacity + frosted-glass blur across 8 surfaces (main background, sidebar, cards & panels, inputs & controls, settings, conversation frame, trajectory view, produced/highlights — 9 with dsh-better-sidebar). Use any image or video as wallpaper with a drag-to-pan, scroll-to-zoom position editor and 5 layout modes (Fit/Fill/Stretch/Tile/Center); videos loop muted, survive refresh, and capture a live frame for preview, color extraction and framing. Rotate a pool of images (shuffle/order, every refresh/daily/weekly). Also: PS-style color wheel, one-click wallpaper color extraction, 6 presets + saved profiles, day/night auto switch, and full theme export/import.

Bloom Morandi theme: ten variants (mist, cinnabar, petal, ripple, sage, stone, lapis, amber, aurora, lavender) built on OKLCH so light and dark stay perceptually even, switchable from the top bar, with all 20 foreground/background pairs measured at WCAG AA or better.

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

Conversation rendering: every fenced block is rendered by the plugin itself (markdown for text fences, language-banner code blocks with highlight.js for others), mermaid fences become zoomable diagram cards, plus context-body rendering, whole-content copy and a MarkdownView export (npm: `dsh-md-render`).

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

Mobile UI shell for the DSH Web GUI: turns the desktop three-column layout into a touch-friendly phone layout (overlay drawers, draggable FAB, full-screen dialogs, infinite-scroll history) under a 1024px viewport, with zero desktop impact. - 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.

Render Mermaid code fences as SVG diagrams with streaming support, diagram/code switching, fullscreen zoom and pan, SVG export, and a bundled same-origin runtime.

Barrage-meme skill distilled from 22,771 real messages in the 6657 live room: wanjiqi-style banter, CS and DOTA cross-memes, player roasting and casting commentary.

Signs in to Huawei Cloud CodeArts and registers CodeBuddy, WorkBuddy, LobsterAI, Qoder (global and China), TRAE, Cline, Loomy, Raccoon Work, MiniMax Code, TeleAgent, ZCode, Step Code and Antigravity as LLM providers, with per-provider account pools; several of them also show quota balance and daily check-in in the same panel.

Agent teams: spawn named long-lived teammates, coordinate them with a shared task list, member mailbox, and virtual workspaces, and watch the team live in a team-room tab.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory.

Model-facing display_file tool that renders 36 file extensions inline in the web UI: images with a click-to-zoom lightbox, seekable video, audio, PDF, Office and OpenDocument files converted to PDF on the host via LibreOffice, and local HTML in a sandboxed frame; bytes stream from a signed HTTP route with range support, and PNG/JPEG/WebP/GIF also enter model context on image-capable routes.

Connects DeepSeek Harness to OOMOL-managed apps and services, with progressive Connector Action discovery and execution plus an in-app panel for managing Provider connections.

Standalone wallpaper background for the DSH Web UI and desktop app: built-in wallpapers, local image/video uploads stored in IndexedDB, and a read-only local Wallpaper Engine library served by the bundled wallpaper-engine-api service in the repository; renders images, video and scene workshop previews, with light-fog/dark-overlay, blur, brightness and safe-zoom controls plus a read-only follow-desktop-wallpaper mode.

Display read_image results in DSH Web and Desktop: complete previews, grouped multi-image galleries, transparency checkerboards, keyboard and touch zoom, and session-authorized loading. Verified with DSH Desktop 0.11.1 / Harness 0.2.0-rc.2.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

dsh 插件（DeepSeek Harness / cordis bundle）· 模型接入 —— 把 CodeArts、CodeBuddy / WorkBuddy、LobsterAI、Qoder / Qoder CN、TRAE、Cline、Loomy、Raccoon、MiniMax Code、ZCode、Gemini、OfficeAce、Accio Work 十五个账号渠道接进 dsh 的模型选择器，并保留数据看板、运行日志与本地网关（含局域网中继）。上游 2.1.0 的匿名免费车道、EAC 协付车道、