Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。
Know what your agent is doing at a glance — 17-segment configurable status bar for DeepSeek Harness: status/model/context/tokens/TPS/cost/jobs. 一眼看清你的 agent 正在做什么:17 段可配置 DSH 会话状态栏。
Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory
Developer tool: live token usage & cost monitoring for DeepSeek Harness - consumed tokens for the current session and across all sessions, read from token-meter projections. No model calls.
Harness agent plugin that acts as a sentinel between the AI agent and MCP servers — polling long-running tasks so token-costly status loops never enter the LLM inference path
A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘:实时看会话压力、按模型估算花费。预算和余额点一下就能改,每天每月用了多少都有记录。
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.
Per-session billing plugin for DeepSeek Harness: token buckets, cache hit rate, and peak-aware cost in the session header + a price-table settings page