Plugins

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

会话注入门控：给 DeepSeek Harness (dsh) 加一个会话级上下文裁剪闸门，按会话取消/恢复插件贡献的 skill、tool、系统提示词段落——3 条影子通道、5 条本地路由、零依赖零配置。Per-session injection gate for DeepSeek Harness (dsh): trim skills, tools and prompt sections per session. Zero-config, zero dependencies.

本地优先的 Harness 运行遥测插件：记录请求、模型、工具与插件生命周期指标（延迟、Token、成本、错误、缓存），默认不采集内容。Local-first Harness telemetry plugin for DeepSeek Harness. npm 包 dsh-local-telemetry（dsh-telemetry 名已被第三方占用）。

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.

Web UI for capturing and reviewing raw LLM requests, streamed responses, token usage and tool calls.

WPS / 金山文档 cloud-docs integration for DeepSeek Harness: official SkillHub MCP (https://mcp-center.wps.cn/skill_hub/mcp), custom browser authorization (auth-guide + exchange-poll token), WPS cloud-doc tools under mcp__wps__*, wps_status/wps_oauth_start/wps

Sakura-afternoon pastel skin for the DSH Web UI: light and dark sakura token palettes, a click-through falling-petal overlay with a soft vignette, a header petal toggle and a General-settings master switch.

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).

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.

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.

Session cost chip in the DeepSeek Harness conversation header showing live token usage by bucket, peak/off-peak tariff pricing, and a countdown to the next tariff switch.

Shows MiniMax Token Plan usage in the Settings page through webServer routes and reads either subscription key name from environment or credentials file.

DeepSeek Harness 插件：生成前注入「人味」风格约束 + AI 味检测报告（纯代码、零 token、结果可复现）。dsh plugin: human-flavor style injection + AI-flavor detection report, judged by code.

精准 Token 洞察，实时追踪，智能优化提示和用量归因 Sharp token insights, real‑time tracking, smart optimization signals & attribution

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.

a plugin of token insight for deepseek harness.

DeepSeek Harness plugin: per-day token usage statistics — 13-week heatmap, stacked daily chart, /token-usage command

ServerChan3 (Server酱) push notifications when a turn finishes — title, model, project directory, git branch, status and a reply excerpt, with subagent filtering and fire-and-forget delivery.

Git Changes tab for the DSH web GUI: staging, diffing, AI-drafted commit messages, branch/merge/stash/worktree operations and sync, with live updates via fs.watch plus a changeToken poll.

Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.

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

Context compaction / headroom for DeepSeek Harness — compress the live context so the prompt stays small without losing the state that matters (layer 3).

Session context handoff for DeepSeek Harness — stop re-reading and re-deriving context every session. A single skill (layer ①) that keeps the next session warm.