DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B/Flash-Next): per-request thinking budgets, a compaction backend that stops burning the output cap on thinking, and a settings tab. 本地 Qwen3.8 线的 DSH QoL 插件：逐请求 thinking 预算、不再把输出帽烧在 thinking 上的压缩后端、设置 tab。
Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, budget caps with threshold alerts and over-limit policies, carbon footprint estimation, per-model latency benchmarks, a Settings budget tab, and the /budget command
Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel
Replace dsh's built-in web search with search MCP servers (Tavily/Brave/Exa/Perplexity/DuckDuckGo/custom), configured from the web Settings page. Disables the built-in DeepSeek search provider while enabled.
Self-evolve memory plugin for DeepSeek Harness: learns from your own sessions, injects token-budgeted preference summaries into every step. /memory commands, memory tool, settings panel. Local-only data.
为DSH接入本地大模型能力：在「设置→插件」页一键启停本地 llama.cpp 大模型（双槽x双模态x双预设），卡片内配置、一条命令安装、自动注册，装完即用| Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to use
🌐 Multi-provider web search plugin for DeepSeek Harness: Zero-key Bing/Baidu direct search, free-tier APIs (Tavily/Brave/Serper/Bocha), SearXNG token auth, auto-fallback, and a built-in Web Settings GUI.
The research plugin market for DeepSeek Harness (dsh): a Research plugins page in Settings that installs a curated, hand-read catalog into the profile you are running. Catalog at dsh-research.com.
