Plugins

Adds a balance-checking tool, injects a per-turn DeepSeek account balance snapshot with a low/critical power-saving and stop policy, and provides a settings page for thresholds and FX-linked currency conversion. Requires a signed-in DeepSeek account for balance reads; API-key-only profiles return an unreadable result.

Registers the models of a local workbuddy2api-hub gateway into DSH as one OpenAI-compatible provider per gateway API key, each key keeping its own model selection, and shows the main key's credit balance plus today's and this week's tokens, credits and API-equivalent cost in a sidebar badge. Requires workbuddy2api-hub running locally.

Composer meter for the DeepSeek Harness Web UI: a pill under the input shows draft character count, estimated tokens and this session's estimated cost from DeepSeek's published prices (peak/off-peak, Flash/Pro or custom rates), and opens a panel with the token breakdown, a six-snapshot per-session draft vault and a draft cleaner; every write goes through the host setDraft API instead of touching the editor DOM.

Zero-key web search provider for the built-in web_search tool: scrapes Bing China, 360 and SearXNG through a backend fallback chain and returns real URLs with snippets and publish dates. No API key and no settings card are required. SearXNG is used only when you set your own instance URL, and installing this plugin switches web_search to it and turns off the official DeepSeek search row.

Manage API providers and enabled models, with provider-grouped model switching and keyword search in the native model menu.

A DSH plugin that turns one provider API key into a managed pool + more built-in LLM Providers

DeepSeek Harness provider for a copilot-api gateway

Hyperliquid trading desk for the DeepSeek Harness (dsh) - market workspace, native agent conversation, guarded live / paper trading and an autonomous watch-loop over the Hyperliquid API.

Web GUI enhancement bundle: a standalone password gateway with optional HTTPS for LAN and remote access, PWA install and icons, desktop plus Web Push notifications, and optional session-id request-header injection for third-party API routes, configured from a settings page.

Blocks API keys pasted into the composer or written by tools, logs leak events, and scans the workspace for exposed secrets.

Merge requests, review threads and pipeline job logs for GitLab over its REST API with a personal access token, in a side panel, with comment, reply, resolve and approve actions that wait for confirmation. Reads need the read_api scope, writes need api.

Windows only. Bilibili video summarizer: downloads the audio track, transcribes it locally with faster-whisper (Python + faster-whisper, about 725 MB of models on first run), then writes the analysis markdown and renders a one-page infographic PNG.

Agnes AI image and video generation tools for DeepSeek Harness, where long video jobs can be resumed in a later call. Requires an Agnes API key (AGNES_API_KEY).

Switch DSH's built-in web_search between the DeepSeek Search API (/v1/tools/search) and the default account search, with automatic fallback, a settings page and a sidebar switch.

Hides tool schemas from the model's prefill and reveals one tool at a time through a decision model API. Requires a running decision-model API endpoint and pnpm on PATH.

Adds DSH 0.2.x kernel support to the SenseTime XiaoHuanXiong desktop-app models, reusing that app's stored sign-in so no API key is needed.

New API gateway provider: several gateways with one active at a time, per-gateway model lists with context and modality details, quota, and image and video generation tools.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy, supervises the local wb2api gateway, and runs a bundled Responses-to-chat-completions bridge so Codex CLI can use the same gateway. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.

Adds the Liquid Inference auction exchange as a model route, with liquid.auto and its ranking variants, and four tools that read offers, markets, routers and job receipts. Requires a Liquid Inference API key (LIQUID_API_KEY, spend scope).

Reads the API balance or subscription quota behind the current DSH route — including OpenDesign (AMR) wallet and Design Plan windows via the control plane — and never guesses a figure: a miss reports its cause (the raw response is echoed only when parsing fails). OpenDesign needs `vela login` or a desktop `controlKey` in `~/.amr/config.json`.

Alibaba Cloud / Qwen balance card above the Settings row in the DSH web sidebar: account available and cash balance, coupon balances with expiry dates (student vouchers included) read through the BSS OpenAPI, and OpenAI-compatible relay quota. An official DashScope sk- key has no balance endpoint at all, so real money and coupons require an Alibaba Cloud AccessKey with bss:DescribeCoupons + bss:DescribeAcccount (AliyunBSSReadOnlyAccess is enough); secrets stay in the host process, the browser only sees a masked AccessKey ID, and /api/dsh-qwen-balance/* is loopback-only.

DeepSeek balance and usage monitor for DSH: a corner widget showing topped-up balance, per-model period consumption, token breakdown, and a Beijing-time peak/off-peak price reminder. Add a DeepSeek API key in the settings first.

Full-page OpenCode Go usage view in the DSH Web UI opened from the sidebar: official 5-hour, weekly and monthly used-percent rings, reset countdowns, a local pacing forecast and a 7-day sampling trail, with multiple API-key accounts you can switch between. Add your key as OPENCODE_GO_API_KEY in DSH credentials first.

DeepSeek Harness plugin that trims tool output (head/tail plus grep folding), adds optional prompt shaping (Caveman and Ponytail), instant local responses, RTK command-output compaction, context-pressure handling, optional LLM-summary compaction, stable prompt-cache layout, a Web settings UI, and persisted savings telemetry.