Plugins

arXiv paper survey assistant with a settings-page UI, a local knowledge base, a feedback loop, keyword search plus optional local-embedding semantic search, and per-paper deep-read notes. Requires a configured DSH LLM provider; semantic search and full-text deep read need an optional Python environment (pymupdf + fastembed), otherwise they fall back to keyword search or are skipped.

Cross-session long-term memory for DSH: eight memory layers, four notebooks, hybrid SQLite FTS5/vector/graph retrieval, agent-driven automatic capture, write lifecycle hooks, optional write audit, project spaces, forgetting and a visual management page. Full FTS5/vector/graph retrieval needs the bundled Go service, which ships only as a Windows x64 prebuilt; on macOS/Linux, build it from source or the plugin falls back to Node SQLite without FTS5 and retrieval degrades.

Makes DSH's OpenAI Responses calls stateful: after the upstream confirms it stored a response, each turn sends only the newly added input items plus previous_response_id, and a stateless upstream is detected on the first response so every later request falls back to the full history.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.

Claude-style palette and typography for the DSH Web GUI — paper-white surface, near-black ink and terracotta accent derived from the Codex absolutely theme, warm neutral and accent ramps bound to 82 native token overrides for both light and dark, Anthropic Sans/Serif/Mono typography, and interface chrome sized with the content font setting. The fonts are not bundled — install them separately, otherwise the UI falls back to system fonts.

A dedicated background-job dashboard for the DSH Web UI: merges jobs from every session, shows producer-reported or parsed progress with an honest estimate fallback, groups by status, purpose, session or kind, streams live output, and keeps a local history ledger.

Replaces the sidebar brand mark with a custom one and registers a Vietnamese locale covering 45 namespaces and 1897 interface strings, falling back to English for anything untranslated.

Russian (Русский) language pack for the DeepSeek Harness web GUI: 59 translated namespaces, English fallback per key

Adds a right-sidebar tab to the DSH web UI with the daily Japanese anime broadcast calendar from Bangumi (api.bgm.tv), grouped Monday through Sunday with today highlighted; hovering a card shows a details popover (cover, score, rank, air date, episode count, tags and synopsis), and clicking opens the title on Bangumi; the host caches the calendar for 10 minutes and subjects for 24 hours on disk so the last successful table still displays offline, and falls back to common local proxy ports when the direct connection fails.

OpenCode Go control panel: an account pool that rotates A-to-B when a key runs out or stops authenticating, per-account 5-hour/weekly/monthly allowance, per-model spend with remaining quota, capability tags (image, video, text-only, tools, reasoning), a live OpenCode-vs-official cost comparison, and quota routing that falls back to a DeepSeek official subscription on an upstream limit or degradation, then returns after 10 stable minutes - shown as a current-route banner, a status card and desktop switch notices, in 10 UI languages.

First-paint splash for DSH: pushes a branded splash page into the boot HTML as an index-injection row, so the desktop window opens already showing the splash instead of a white/loading flash. Fades out and hands over once the startup-animation plugin starts (checked via `window.__DSH_STARTUP_RUNNING__`), with a 6-second fallback (configurable via `maxMs`) so it can never trap the app behind the splash. A normal dsh.bundle plugin: no host changes, no app.asar patching.

Bilibili music player for the DSH composer dock: import your Bilibili login cookie and a listening-profile JSON for profile-based recommendation with like/skip/dislike feedback and 192k playback; without a profile it falls back to genre-based online search and progressive playback.

Bundles the PrismSearch MCP server and its agent skill. Web search over Bing and Baidu with no account or API key, plus Google and Brave when API keys are set and DuckDuckGo, Sogou, 360 and Yandex when enabled in config; automatic engine fallback and an aggregate mode. Also image search, WeChat Official Account article search, and fetch_page, which returns web pages and PDFs as Markdown in segments.

Annotates bash results whose exit code 1 is an answer rather than an error (grep with no match, diff with differences, false test) so the agent does not re-investigate them.

A local ComfyUI workbench for DeepSeek Harness (DSH): image/audio/video generation, W2/W3 sprite cards with Qwen back-view walk-up, local Flux.2 Item Studio assets with guided SDXL fallback, Hugging Face downloads, inspection and arbitrary workflows.

Sends one system notification when a DSH turn ends: per-outcome switches for completed, error and interrupted, a minimum-duration threshold, silent subagents and unfocused-window-only delivery. Works on Windows, macOS and Linux, delivered through a connected page or a native fallback (PowerShell toast, osascript, notify-send; the Linux native fallback needs libnotify). Clicking the notification brings DSH back to the front on the page/Electron channel; PowerShell and notify-send notifications are not clickable.

Sends a QQ direct message through a local NapCat (OneBot) instance when DeepSeek Harness asks for permission, after verifying the bot QQ; requires owner/bot QQ ids plus the NapCat endpoint and token, and falls back to a Windows notification when NapCat is unreachable.

Posts a follow-up prompt into opted-in chats that fall silent, and offers a secret-protected HTTP API that posts a message into any chat. Requires Node.js 22.5+.

DeepSeek Harness tools and a Skill for md-report/1: validate and render Markdown plus declared SQLite/CSV datasets into one offline interactive HTML report or dashboard, with AntV G2 charts (ECharts fallback) and chart/table data and source-SQL views.

Failure memory for DeepSeek Harness. Captures tool failures as they happen, classifies them with 16 built-in rules into lessons pairing a symptom with a fix, adds session/daily/weekly summaries, and injects a short briefing into later sessions through systemPrompt context. Ships 5 pitfall_ tools and a web settings page.

Replaces the built-in compaction provider: at a configurable fraction of the context threshold (85% by default) a detached task summarizes everything up to the previous turn, and the next step boundary commits that held summary as a checkpoint with zero model calls, so the swap itself takes milliseconds. /bcompact \[message] starts the same generation on demand and then sends the message. A settings page sets the trigger ratio, the summarization model, and how many consecutive failures stop background generation until a half-open probe gets through. Subagent sessions, a changed prefix or an expired summary fall back to the built-in synchronous path.

Routes DeepSeek models in dsh through an OpenCode Go subscription and falls back to the DeepSeek account per model when that model's allowance runs out; a plan-wide fallback covers bad credentials.

Matrix-style binary (0/1) digital rain for the Harness interface: columns spawn only while a task is running, fall off screen when it stops, and leave a blank canvas; frosted-glass token layer with adjustable digit and panel opacity.

Fairy III (Zenless Zone Zero) H.D.D skin for DeepSeek Harness: boot video, an eye-core dock that can be dragged vertically so it never covers text, and time-of-day greeting voices written by a model every day (5 lines, each <= 20 characters) and synthesized locally with GPT-SoVITS, with a fallback chain of today -> latest -> bundled audio so there is always something to hear. Replies can be spoken: a trailing marker line takes priority over length heuristics, and long replies can be compressed into one sentence first. The reader hashes the utterance it just played (MD5) so each reply is voiced exactly once, and switching sessions stays silent. Personal fork of dsh-fairy-zzz with its own package, route and storage namespace, plus a rate-limited summarize endpoint, POST-only engine control and bounded TTS and greeting caches. Two diagnostic logs (client revision, decision trace) are written next to the plugin and stay on the local machine. A personal fork of AssassinVIX/fairy-zzz-plugin (upstream package dsh-fairy-zzz): install this fork or the upstream, not both - both mount the full-screen skin on the same DSH surfaces. Dynamic greetings and spoken summaries need a DeepSeek-compatible API key in ~/.dsh/fairy-tts.json (or DEEPSEEK_API_KEY); without it only the bundled greeting audio plays.