Plugins

Token usage dashboard for the whole harness: billed tokens from every session are rolled up per session and turn (uncached input, cache read, cache write and output) with a peak/off-peak CNY cost estimate, and a "Token 用量" entry above Settings in the sidebar opens the dashboard at /token-stats, in a new tab on the web and in an in-app popup on the Desktop. The page recollects and repaints every 60 seconds while the tab is visible. Usage is read from the same session event stream dsh-token-meter consumes, accepting 0.1.x assistant/chunk and 0.2.x assistant/message and assistant/attempt, and counting an attempt repeated after an llm retry as its own billed call; cold history is seeded once from a persisted rollup file and afterwards only logs whose mtime or size changed are re-parsed. Host half and client half ship in the one package.

Shows DeepSeek account balance and today's token usage in the sidebar footer, and reconciles locally estimated spend against the balance the account actually lost over the days it has sampled.

Routes web search and fetch, records estimated costs, and provides local budgets, circuit breakers, and diagnostics. Requires Node.js >=22.19 and DSH 0.2.1-rc.2 or 0.2.1-rc.3.

A Usage page in DSH settings that folds every model call into a local ledger and reports requests, tokens, and estimated cost by day, route, and model, with editable unit prices and CSV export.

Launch splash screen for DSH — a row of white marquee dots lights up, then the DeepSeek Harness wordmark is written stroke by stroke before the main window takes over. Installs as a runtime-injected overlay plugin; the repository also ships an optional native build.

Adds a corner card that estimates how much a session spent repeating a failed or empty tool call with the same arguments.

Boot film for the web UI: a blue whale floods black from below as the page loads, then glides left and pulls the | deepseek HARNESS wordmark out of itself before the app appears.

Adds a draggable restart button and a plugin panel to the DeepSeek Harness desktop app: it prompts when the profile plugin list changes, records additions and removals per profile, tracks trials, reports host startup state, and offers rollback, minimal boot and recoverable cleanup.

Right-click menu for DeepSeek Harness conversation content: copy the selection or the whole message, copy message images and the preview lightbox to the clipboard as PNG (or save them), open file paths (absolute, relative to the session working directory, or ~/), reveal them in the file manager, open them with another registered application, and copy paths or links. Every candidate path is verified by the Host filesystem before an open action appears.

A companion playlist panel for the dsh-boot-animation intro-video plugin: add clips without leaving the app, order them, and switch between sequential, random and single-clip playback. Sequential order is made deterministic by parking every clip except the one due to play in a disabled/ subdirectory of the same asset folder and rotating it back in on each boot, leaving the upstream plugin unpatched. Also supports recycling instead of deleting, pinning one clip for every launch, per-clip opt-out, and .mp4/.webm/.m4v/.mov files including non-ASCII names.

PWA icon: sets the icon (and manifest app name) used when the Web GUI is installed or added to the desktop; ships a default icon set and accepts a custom image.

Keeps the DSH desktop window the size you left it: records the last outer frame of the main window in physical pixels and restores it, centred on the work area, on the next start - and it acts before the window is ever shown, so the boot animation plays at the right size. The settings page offers 12 presets (1024x768 to 3840x2160), free-form custom width and height, a centre-on-restore switch and an apply-now action; a choice takes effect immediately and persists. Resizing goes through a small helper executable compiled on the user's own machine: the C# source ships inside the plugin, is built on first run with the in-box Windows csc.exe (measured ~110 ms once, cached next to the state file, ~90 ms to start), and falls back to a short-lived powershell.exe process when that is not possible. The package ships no binary, declares no npm dependencies and makes no outbound network request. Windows only.

Go (weiqi) for the DeepSeek Harness: a full rules engine, a three-level built-in AI, a dead-stone estimator, optional LLM review, SGF import/export, and an optional KataGo GTP bridge.

DSH pet plugin that adds an Arknights operator library and custom image pets: pick one of 486 operators and the plugin downloads that operator Codex v2 atlas from the pinned upstream revision, verifies every Git blob hash and installs it locally, or import your own Codex atlas (1536x1872 or 1536x2288) or a plain PNG/WebP/GIF; the pet then follows session activity, shows a bubble while a decision is pending, and can be dragged and resized.

Converts Office and PDF files in the DSH workspace to Markdown locally — no network, no API quota — before the model reads them. Writes each .md next to its source so only a file path enters the context, and returns byte size, line count, token estimate and a heading outline, for a single file or a whole directory.

Bridge to the local doc2md (markdown_monitor) CLI — one doc2md tool with convert, read, scan and status actions over docx, doc, xls, xlsx, pdf and image files.

Add PaddleOCR vision to text-only LLMs like Agnes, DeepSeek, MiniMax, GLM and Mimo. Supports local files and URLs. Free tier of 20,000 pages/day; needs a PaddleOCR API token you apply for (free, 1-3 business days).

Local art pipeline for DSH: drives the locally installed SD WebUI and ComfyUI backends through ten image_* tools and an Art Studio sidebar panel with an embedded ComfyUI canvas, post-processes with the Python shipped with those installs (rembg cutout, Real-ESRGAN upscale, seamless tiling), and writes Godot-ready assets with res:// paths once a project root is set.

Registers one `ocr` tool for text-only models: it runs the offline script bundled in the repo over a single image or PDF and returns the recognized text — Windows native OCR first, then RapidOCR, then Tesseract. Recognition runs locally with no network request and no API key. Needs Python 3.11 on PATH plus `pip install winocr pillow` (winocr is the preferred engine; RapidOCR and Tesseract are fallbacks). Per-line results for images, per-page results for PDFs.

Open the extension side panel and it takes over the page you are browsing right now. On top of upstream it adds: hover, coordinate clicks, drag, batched action chains, whole-page screenshots, local file upload, image listing, and switching between several connected browsers. Pages reach the model as structured text with a numbered element list; actions wait for your approval and sensitive fields stay masked. Ships as the bridge plugin, with the extension in the same release. This project is a fork of omdsh-dev/dsh-browser: https://github.com/omdsh-dev/dsh-browser

NewAgentUniverseByDeepSeek nodes inside DSH: five read-only tools covering provenance (both upstream releases this build names), a data directory's restored state and ledger audit, the conformance vectors, exact decimal conversion, and node reachability. Driving the node -- starting or stopping a daemon, depositing funds, sending bus messages -- is deliberately not exposed, because those are audited privileged operations in this project.

Complementary web-search provider: every web_search merges the DeepSeek Search API (primary) with serper.dev Google results (secondary) at a fixed 2:1 ratio. Both sides are direct HTTP retrievals with no auxiliary model turn: URL-deduped sources, long DeepSeek summaries clipped into snippets, per-backend timeouts and graceful degradation to whichever backend answers.

Add MiniMax image understanding, image generation, speech synthesis, and transcription tools to DeepSeek Harness.

Read-only attachment library: lists every image and file attachment stored on this machine, its size, and which conversations (including those in the session trash) still use it, with Show in Finder and Open in Preview.