Plugins

Aggregated web-search provider for the built-in web_search tool: one prioritized queue over nine providers (AnySearch, TinyFish, Tavily, Brave, Exa, Firecrawl, Jina, SerpApi, Serper), with multi-key rotation per provider, ordered fallback on failed attempts, and a live settings card.

Context7 MCP bridge: gives the model up-to-date, version-specific library documentation and code examples through the Context7 MCP server, keyless by default.

Multi-backend web_search provider (Exa + Firecrawl) for the built-in web_search tool, with automatic failover, per-backend 429 cooldowns, and key-free anonymous access.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

Quality-aware in-agent plugin discovery: a find_dsh_plugins tool that ranks the whole dsh-plugin topic through a daily quality-scored index (installable manifest, curated listing, license, activity) merged with a live gh search — zero LLM API cost, risk flags and exact install commands in every result.

One-click start/stop button pinned to the window bottom-right corner: restarts DeepSeek Harness in place via a detached helper that relaunches the exact boot invocation (loopback same-origin guarded), with an optional stop-only action.

Query 64 Chinese exams (高考/考研/四六级/CPA/法考…) with rule-aware date math (2nd-Saturday, 1st-Sunday) and countdowns.

Generic Companion-protocol bridge from DeepSeek Harness to phones/IoT/legacy agents (includes Termux companion example).

A chemistry workbench panel in the DSH web UI. Draw structures on a Ketcher canvas (a script downloads the build; it renders locally in the browser with no backend), then compute on the current molecule with RDKit without calling a model — formula, molecular weight, exact mass, logP, TPSA, hydrogen-bond donors and acceptors, ring counts, Fsp3, stereocentres, Lipinski and Veber rule-by-rule checks, QED, PAINS/BRENK structural alerts and the Murcko scaffold, plus SMARTS substructure matching, fingerprint similarity, format conversion, standardisation and batch clean-up. A retrosynthesis tab talks to a pluggable backend (Retro* by default) over a single JSON-in/JSON-out process, and states what is missing when the backend is not installed instead of inventing a route. The calculations run in this repository's Python package (rdkit), which is installed with pip separately.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

English word bank for one or more children: words marked on textbook or workbook photos (highlighter, red pen) are found by their marks, then translated and stored in a local SQLite bank with an occurrence count; the clipboard picker, the photo route and dictation all land in the same bank. High-frequency words surface by count, three correct answers in a row flag a word as learned, and any selection prints as a memory card set (a word split into chunks, real IPA per chunk, a mnemonic hook, an A4 sheet of eight) in HTML, PDF or Word, with a print-and-answer exam page whose four options are set against each other for meaning. Requires DSH 0.1.7 or newer (1.0.3 moves to the 0.1.7 settings contract); on 0.1.5 the settings panel does not appear - install dsh-word-vault@1.0.2 instead.

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.

Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Split-screen workspace for the DeepSeek Harness web GUI - chat with several agents side by side in panes that look and behave exactly like the stock conversation: drag-to-split, live sessions with queued messages and in-pane ask_user/approval cards, per-pane view tabs (Chat/Trajectory/plugin views), a compact TUI composer mode (Alt+T) and pane-focus shortcuts. Requires DSH 0.1.5+.

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

Unified quoting for DeepSeek Harness Web: select file-editor text or chat messages → annotate → 「引用#N」chip → the AI receives a formatted quote block with file path and exact line range (source line hidden on the user side); sent quotes collapse into a hov

Daoist Canon (DaoZang) retrieval skill: keyword or semantic search over 285,117 scripture chunks with exact original-text extraction (line numbers, hit markers), and one-command workspace setup from the Godners/DaoZang dataset.

RSS/Atom digest bundle for dsh: subscribe to feeds, fetch on a schedule, dedupe exact and near-duplicate stories, and get LLM-summarized daily Markdown briefings delivered into conversations and/or files (with a standalone CLI).

Persistent read-only side conversations anchored to exact prose in DeepSeek Harness

Multi-provider web search for DeepSeek Harness: Baidu, Doubao, Tavily, and Exa backends for ctx.web.

Slacking-off companion: a floating mini player that streams Bilibili videos (native player, danmaku, comments, search) and pauses when your agent needs you, resuming exactly where you left off.

One-click skin switching for DSH Web settings: auto-detects installed themes, keeps exactly one active at a time, and falls back to the official look when all are off. Changes apply instantly and survive restarts.