Plugins

Codex App Server model provider using a local Codex login, with session reuse, Harness tool bridging, native action traces, and durable generated-image projection.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Customizable brand area for the Web UI: replace the whale logo and DeepSeek wordmark with local images, and edit the HARNESS badge text (double-click to change, right-click to reset).

DeepSeek account balance and session cost under the composer, with a live peak/off-peak pricing badge (Beijing time), a countdown to the next pricing switch, hover price tables, and usage advice.

Configurable DSH usage statistics: a sidebar text/card widget plus a detail dialog with per-provider and per-model breakdowns, cache-hit rates, token trends, and latency details (TTFT and duration).

Multi-window wall for the DSH Web UI: run and monitor N conversations side-by-side in one screen, with auto-discovery, per-window controls, and an authenticated LAN gateway for phone/tablet access.

Your DeepSeek Harness web UI, rebuilt for the phone in your hand. Built for developers who code in Termux on Android: single-column layout, sidebar drawer, one-line composer, fullscreen scrollable settings & trajectory details, tap-to-open session stats. Desktop untouched.

Portable Agent Skill for developing and auditing DeepSeek Harness plugins, with an optional profile-installable DSH bundle adapter.

可配置子代理 profile 系统，单一 subagent 工具 + profile 参数，含 Web UI 设置/实时进度/子代理树 | Configurable subagent profile system: single subagent tool + profile param, with Web UI settings/real-time progress/subagent tree

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

Per-session billing plugin for DeepSeek Harness: token buckets, cache hit rate, and peak-aware cost in the session header + a price-table settings page

A writable, git-versioned self for DeepSeek Harness: persona files injected every turn, a persona-only memory layer, topic-keyed journal→dream promotion gated by your 👍/😑/👎 ratings, whitelisted self-upgrades, and a Settings persona tab.

Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.

Registers DeepSeek Search and Fetch API providers for the ctx.web seam, replacing both the web_search and web_fetch backends with DeepSeek's Search and Fetch JSON APIs, with configurable retries and backoff, settings that apply to the next call, and a configuration page on the bundle page. Requires DSH 0.2.1-rc.5+ and a DeepSeek API key with access to /v1/tools/search and /v1/tools/fetch (calls are billed by DeepSeek; account sign-in is not supported).

Zotero skill for DeepSeek Harness: page-anchored Q&A, full-text translation and close reading, native highlights and Chinese notes, bilingual PDF and paragraph Markdown, evidence comparison tables, and reviews with citation tracking; finds papers on OpenAlex or Crossref, imports Chinese CNKI export files, classifies the library into research-direction folders, surfaces research gaps, and runs a ranked daily digest of new papers. Python-based (basic library management uses the standard library; the reading workflow downloads its PDF/OCR components on first use); writes need a one-time Zotero authorization, and daily scheduling is Windows-only. Adapted from the OpenAI MIT Zotero plugin.

Connects DeepSeek Harness to QQ over OneBot 11/12, Satori, Milky or the official QQ bot API, with a separate session per group or private chat and nine built-in tools: group management, chat history with image understanding, web search, page fetching, reverse image search and image generation. Optional proactive chatter reads recent messages on an interval and decides whether to join in, with the judging and speaking stages able to use different models. Models, proxy and allowlists are configured in the DSH settings page. First run requires an owner (auth.owners): with it empty the plugin drives no sessions at all (deny by default, so installing it does not expose the bot); once set, private chats and groups work immediately, guests only reach the guest tool allowlist while qqbot and qqconfig stay owner-only.

Long-term memory for dsh via a local Hindsight service: each turn is retained with local timestamps and relevant memories (time-aware, reranked) are recalled into context before replies; each workspace binds to one memory bank, several workspaces can share a bank, and banks can have Chinese names; what gets retained is configurable (default: user messages and AI replies); history is imported only when you choose to; includes a three-step setup page with one-click local deployment (uv + Python 3.12), a sidebar status card and a panel to browse and search memories. Needs a SiliconFlow API key for the default embedding and reranker models; only Linux is verified so far.

On the first real work message of each chat window, asks for the missing goal, deliverable, constraints and acceptance criteria, then turns the answers into a short task sheet and injects it into the chat. Pure greetings are ignored.

Adds an independent settings page to update npm-stable dshmarket through the DSH plugin manager, with version verification and best-effort recovery on installation failure.

A long-form Chinese novel workbench inside DeepSeek Harness: read, edit and annotate the manuscript in place; AI reports problems with ready-to-adopt revision drafts, and the text changes only when you accept. A ledger for characters, facts and foreshadowing plus a world map keep a long novel consistent, and AI can continue, expand or rewrite chapters.

Usage statistics: a usage and reference-cost panel for DeepSeek Harness with today, 7-day, 30-day, all-time and custom ranges aggregated by hour or day; a model filter and a per-model breakdown of requests, input and output tokens, cache, reference cost and share; a model-share card showing the top four models by total tokens with the rest grouped as others; a reference price list generated from opencode Zen and DeepSeek's published rates, with DeepSeek models billed by Beijing weekday peak/off-peak windows and Chinese public holidays; a pricing-match dialog to point an unmatched model at a reference model or type per-million rates by hand; reference cost switchable between ¥ and $ at a fixed 1 USD = 7 CNY; and a yearly heatmap drawn only with theme variables, with no third-party chart library.

Study workbench for exam prep and research: three-column task board with tags and filters, a spaced-repetition queue (simplified SM-2) that keeps finished cards coming back, a heatmap lit by actual focused minutes, weekly reports, per-day review notes, a pomodoro timer that survives panel switches, and Markdown export/import for Obsidian. Installable via dsh plugin add (dsh-study-desk on npm).

Reversible delivery contract: rewrites operator authority and execution rules when enabled, byte-identical to stock when off, with host and profile clean.