Плагины

Управление бюджетом токенов для дерева агентов.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

Codex-style token usage panel: whole-instance cumulative/per-session peak tokens, longest chat & streak, daily/weekly/cumulative activity heatmap, and plugin/skill Top5.

Local semantic-token theme editor with palette extraction, WCAG auditing, preview, and export.

dsh的本地用量面板，统计 Token、请求、Agent 活动、工具调用和性能

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprin

Put a dsh (DeepSeek Harness) workspace on ANY machine. Two modes in one plugin: (1) fleet — enroll an off-site machine behind NAT into your dph via a one-time token + reverse tunnel to your own relay VPS, so it appears as a dsh-ssh host; (2) execution wor

Ambient UI for DeepSeek Harness Web: a glassmorphism balance/token floating widget plus a pixel-art agent-trail animation.

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

DSH 全局经验插件（骨架）：自动探测本地依赖/便捷路径/网络/磁盘并沉淀为跨会话环境档案，订阅 session/event 折叠每会话统计，把低开销摘要注入每轮系统提示，env_profile 工具按需查全量——减少重复探测、加快会话、降低 token 消耗。

虚拟 DSH 环境跑分机 — 插件/Skill 加载与工具调用基准（L1 零 token）。dsh-plugin-hub 生态的可扩展类插件：为 hub 提供独立性能评分（加载/工具调用各环节耗时）。

DeepSeek Harness 消耗统计插件：设置页「消耗统计」展示 Token 用量 KPI、半年活跃贡献热力图、按模型堆叠柱状图与模型环形图（Host 投影聚合 + 只读重算会话日志，永不写回）

DSH web plugin: a real-pricing usage-cost line beside the official token stats — per-model cost breakdown with a verified price table. / DSH 费用统计行：在官方 Token 用量行旁按模型显示真实费用（按模型分别标注，价格均来自官方定价页）。

The DeepSeek time-of-use meter for dsh: what this session cost, which tariff is running, when it flips, and the account balance behind it — one line under the composer.

Pokemon-style catch-em-all: your real work is the tall grass — turns, tool calls and errors spawn wild encounters; throw balls, fill a 28-slot dex, walk a team of six. Zero tokens, invisible to the model.

Complete LAN/remote access for the Web UI: 0.0.0.0 binding, crypto.randomUUID polyfill, token gate (401 login page + WebSocket interception, loopback exempt), privileged-fence and settings-persistence exemptions, and an idempotent installer with upgrade recovery.

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

One-click OAuth (PKCE) connect to Qichacha (qcc.com) MCP services in DeepSeek Harness: dynamic client registration, token auto-refresh, and dynamic mcp-client configuration.

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.

Replay sessions on a playable timeline with per-step token usage, audit sensitive operations, estimate cost, view fork lineage, compare sessions, and export standalone HTML replays.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.