Плагины

Global real-time Token HUD for DeepSeek Harness Web: draggable floating window showing live output tok/s, cumulative tokens, and per-session running/retrying status across all DSH sessions.

dsh plugin: persistent whole-machine LLM usage ledger with a markdown /llm-stats report (GFM tables + emoji: tokens, cache hit, model/tool time, per-day bars)

Adds Token Market as an OpenAI-compatible model provider with DeepSeek V4 Pro, Kimi K3, and GLM-5.3.

DeepSeek Harness dashboard: per-session statistics (tokens, timing, tool and skill calls) as a dedicated Statistics view tab. Compatible with dsh v0.1.2-alpha.1 ~ rc.1 (see README).

Windows-only tray monitor for DeepSeek Harness: deploys and manages the standalone DshTaskWatcher tray app - four-state tray icon (gray=disconnected, green=idle, amber=running, red=attention), a per-task panel with live duration/tps/tokens, and completion & outcome notifications. Start/stop switch in Settings > Plugins; the watcher is an independent process that survives DSH restarts.

Context-window attribution for DSH Web: a Mini Utility Dock panel that ranks the user messages, assistant turns, reasoning blocks and tool results of a session by the tokens each one occupies, so it is clear which entries hold the window. It also shows the share by entry type, the heaviest entries across the live sessions of the host, and, where the host provides them, provider usage and the estimated system/tools/messages composition. The panel is read-only: it does not estimate cost, modify a session, or trigger compaction.

Input redundancy pruning for DeepSeek Harness — drop repeated/redundant tokens before they reach the model (layer ②).

Terse prose for DeepSeek Harness — compress the agent's own output so every reply costs fewer tokens (layer 4). Style, never substance.

Resolves unique kebab-case skill substrings in slash tokens, so /oneshot can load game-package-oneshot.

Real-time token estimates for the DSH conversation composer, combining the current context baseline with the draft and showing exact or heuristic counts.

Provider health dashboard as a Settings page: read-only per-provider status, health (time-decayed from recent errors), thinking capability, max tokens and latest error, sourced from the llm-pi-ai config and the compat-healer error log.

Mobile remote pairing for DSH with QR offers, a loopback Host Gateway, encrypted Relay or Quick Tunnel transport, same-LAN WebRTC Direct, and revocable Device Tokens for the Android client.

DeepSeek balance and per-session cost in the DSH web composer dock, with official peak/off-peak pricing (peak hours Mon-Fri BJT 9-12 / 14-18, weekends off-peak) and built-in deepseek-v4-flash-vision-exp vision model rates billed at flash price (images billed as tokens, max 384 tokens each).

Native SuperGrok / X Premium OAuth provider for DeepSeek Harness. Reuses local grok-bridge tokens; no xAI API key.

Login gate for the DeepSeek Harness web GUI: username/password entry page (DeepSeek style), 12-hour session tokens, slash commands for user management. Background tasks keep running while logged out.

Secure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.

把长文本渲染成图片发送，利用每图 384 token 封顶压缩 LLM 输入 token，专为DeepSeek Harness设计的插件；Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.

山海系列 DeepSeek Harness 用量统计插件：总量徽章、每日走势、GitHub 风格热力图、按模型/提供商分组明细

macOS system notifications for DeepSeek Harness: aborted, max-tokens, blocked, interrupted and error events, pending questions and approvals, and completion or subagent-end via terminal-notifier; clicking a banner opens a configured app and returning to the page auto-dismisses them.

DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key.

dsh usage & performance statistics: settings-panel plugin + TUI (tokens / TTFT / TPS / cost)

Notes and todos as plain Markdown files in your workspace: type /ml plus a sentence to jot into today's journal; todos come in three flavors — deadline, sleep-until-a-date (auto-wakes when due), and anytime; /ml view fuzzy-opens any file with a few keystrokes. Zero tokens throughout — nothing goes through the model, and your notes stay ordinary local files that git and any editor can read.

Codex-style @file/@folder mentions for the DSH web composer: workspace file/folder picker menu, plain-text colored mention tokens via the platform lexicon scan, and a nested-git-aware file index.

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