Plugin

Makes the AI default to Mermaid diagrams in development conversations — system prompt guidance, a mermaid_validate syntax-check tool with real-parser validation, and an output gate that auto-fixes or removes broken diagrams. Rendering via dsh-mermaid.

Digests the images in a prompt with a vision model before admission, so any model — a text-only one included — can read them without the session ever switching models, and adds a describe_image tool for image paths.

Trims historical images in outgoing chat requests down to a recent-image count, learns the provider per-prompt image cap from HTTP 400 responses, and retries with fewer images so image-heavy sessions keep working.

Embeds external AI chat sites in a DSH side panel through the same-origin reverse proxy with per-site DOM adapters, and adds a composer button that either rewrites the draft with the host model or runs a two-round loop: compress the conversation, optimize, send to the embedded site, capture the reply, then finalize it into the composer.

Tavily search and page fetch: tavily_search queries with a rotating pool of up to eight API keys that backs off per key on 401/403/429 so one exhausted account does not take the tool down, and web_fetch retrieves a single page through curl, returning its HTTP status with de-tagged text.

AnySearch-backed search tools for agents: general and vertical-domain search, parallel batch queries, vertical-domain capability discovery, and page-to-Markdown extraction, plus an API key panel in Settings. It registers its own tools instead of a web_search provider, so it cannot be installed alongside @anysearch/anysearch-dsh.

Ten live-data tools over eight keyless public APIs: FX rates, weather, npm/PyPI versions, GitHub repo stats, Bilibili video stats, A-share/index/gold quotes, and IP geolocation. Tool defaults are configurable in settings.

Ships the Zhouli-mode agent preset, which runs a session in three phases (declaring roles on opening, citing authorities while working, a six-item self-audit at the close), plus one tool with seven actions over a bundled 49,384-character 《周礼》 corpus that returns every passage with a stable 篇序.职官序 coordinate, a per-office establishment index and collation between two Kanripo witnesses.

Unit conversion as a `convert` tool: 10 categories (length, area, volume, time, angle, speed, temperature, pressure, energy/heat, power) and 82 units with English and Chinese aliases, plus a locale-aware Unit Converter tab in the DSH web view with one module per category and a temperature-difference (Δ) switch.

Give the agent a priority-ranked, coverage-honest map of any codebase before it edits.

Windows desktop control exposed as native DSH tools - whole-screen and single-window capture (the window one goes through PrintWindow, so a covered window still captures), click, drag, typing, keyboard shortcuts, scrolling, window management, pixel and window polling, and UIA queries that can invoke a control or read its value instead of clicking coordinates. 11 tools over a PowerShell 7 child process; no MCP server, no resident process, no API key.

Session-row unread mark for DeepSeek Harness: the session menu gains Mark unread and Unmark, pinning a red dot before the session title that survives reload and opening until cleared, both entries disabled while the built-in green finished-unopened dot is present.

Makes Enter insert a newline in the DSH 0.1.5 Web composer while Cmd/Ctrl+Enter keeps submitting messages.

Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.

Groups the model picker by provider: the menu lists sources first, and each source opens its models in a slide-in side panel (default) or inline below the title, switchable by double-clicking the source title.

Search and select models in the DeepSeek Harness WebUI with a native settings card.

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.

Capy-style ambient background for DSH with wallpaper, bottom black gradient, and composer aura.

An ink-wash theme for DeepSeek Harness inspired by Luzhou Moon, a guofeng song by the Chinese singer Vae. Built on dsh-theme-customizer, it repaints the app background, sidebar, composer, new-session button, settings panel, Cordis panel and floating panel with generated ink-landscape artwork, adds gold filigree frames and a full-screen rain effect, and rotates vertical lyrics drawn from 24 of his Chinese-style songs.

Per-wallpaper offset for dsh-dream-skin - nudge the current wallpaper along X and Y in pixels from Settings, remembered separately for each image, URL or gradient.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Peak and off-peak billing season in the composer statistics row, right after the cache-hit reading, with a coloured dot, a countdown to the next switch, and a panel that shows the account balance split into total, granted and topped up in the currency the API reports.

DeepSeek Harness plugin for querying LLM service provider usage: reads DeepSeek and Moonshot balances plus Kimi For Coding and OpenCode Go quota windows on the host and shows them in an always-visible card with three view modes, edge docking and a collapsed letter bubble.