Plugins

Mojibake guard bundle for DSH: feature-based garbled-text detection before writes with review-then-release (an identical retry passes), plus pre-execution pwsh encoding audit (ANSI/GBK/UTF-16/Default), Windows and Chinese first.

Translation toolkit for DSH agents: sentence segmentation, term and glossary extraction, source-target QA (numbers, units, brackets), tone guides, and a durable workspace translation memory.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

Restore archived sessions to their original workspace from the Web GUI sidebar.

Read-only side-by-side comparison of related DeepSeek Harness conversation histories, including messages, tool calls, responses, timing, and usage.

Auto-fills reasoning-effort levels, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Anime skin pack for the DSH Web UI: five AI-generated HD themes (Ninja, Sakura, Bamboo, Ronin, Ryujin) with per-theme accent palettes, a top-right shirt-icon switcher, and an adjustable transparency slider.

Wallpaper skin for the DSH Web UI: presets, image URL or upload, and an opacity slider that fades the interface to reveal the wallpaper.

DSH Web skin manager for mainstream DSH skin packages: import local paths or GitHub collections, scan installed skins from the web profile, preview/use/disable/refresh/delete, with host-side persistence.

Persistent wallpaper skin for the dsh web profile: static image or muted looping video as the app background, with translucent panels and a floating picker panel.

Token usage statistics for DeepSeek Harness. Per-channel usage with balances and plan quotas for mainstream providers, CNY cost estimates, and daily charts — a settings-sidebar section.

Bottom-right 余额 badge for the DSH Web UI: on expand it fetches the currently-selected provider's OpenCode Go plan limits or DeepSeek prepaid balance, plus local token usage and pricing-based spend estimates.

Persistent provider-reported token usage totals with per-session, per-model, and daily activity statistics.

DeepSeek wallet balance at the sidebar foot: a credit-card icon with the amount tinted by remaining balance (green over ¥2, amber ¥0–2, red below), refreshed on mount, per turn-end, and on click; a signed delta floats up and fades on each balance change.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

Multi-provider LLM API balances under the chat input, with presets for DeepSeek, OpenRouter and SiliconFlow.

Adds a "用量" section to the DSH Settings page that shows your MiniMax Token Plan usage (5h and weekly windows with reset countdowns), per-model breakdown, and video bonus credits; fetches `/v1/token_plan/remains` via a trusted plugin that holds the API key, auto-hides when no key is configured. MIT.

DeepSeek account balance in the dsh web sidebar footer with live config hot reload and an editable Settings → Plugins card.

Per-turn and session-wide LLM cost metering: a dollar cost line under each message, a session cumulative total with hover breakdown, and an LLM+web price auto-refresh tool.

Official-style composer model trigger with a floating reasoning-effort slider popup.

Folds each DSH Web turn's thinking, tool calls and context into bordered process boxes cut at every piece of model text; a collapsed box shows its latest two items, the stacked lines above its border open that one box, the border itself folds it back, and user dialogue, interactive questions and model text stay outside.

Model sampling sliders (temperature / maxTokens) in the composer: override every model request for all providers via the agent/request hook, with hot/persist modes.