dsh-plugin-whale-fenggu
蓝色大肥鱼 · DeepSeek 峰谷提醒:北京时间「梁文峰/梁文谷」实时播报、切换前提前提醒、省 token 小贴士、自由拖动(纯前端,兼容 blue-fantasy 皮肤风格)
11 results
蓝色大肥鱼 · DeepSeek 峰谷提醒:北京时间「梁文峰/梁文谷」实时播报、切换前提前提醒、省 token 小贴士、自由拖动(纯前端,兼容 blue-fantasy 皮肤风格)
鲸鱼不废话,少词办大事 — DSH 极简语模式,节省 60-75% 输出 token
Live token/cost-savings dashboard for the Headroom compression proxy inside the DeepSeek Harness (DSH) Web UI: a settings-page dashboard plus a persistent stats line under the composer. 在 DSH 内实时展示 Headroom 压节省统计:设置页仪表盘 + 输入区常驻统计行。
Ponytail for DSH — the lazy senior dev. Live intensity switching (off/lite/full/ultra) with a toggle in the composer, injecting a minimal-code ruleset before every step to cut token usage.
CodeBuddy-style deferred tool loading for DeepSeek Harness: keep tool schemas out of the model context until the model loads them on demand via tool_search / defer_execute_tool.
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。
dsh plugin: token-efficient prompt-side shim for the official MCP client — folds mcp__* tool schemas out of every assembled prompt and exposes two constant meta-tools (mcp_list / mcp_call) instead
Token optimizer for DeepSeek Harness — condense your context, keep the essence
让用户个人/本地 LLM 接入 DeepSeek Harness:Ollama、KoboldCpp、LM Studio 及任意 OpenAI 兼容端点作为本地冗余算力,本地优先处理一部分信息,难点才交给云端主模型。充分利用本地算力并节省 token。
Token-efficient project reading with symbol/import indexing, PageRank topology, and byte-level slicing for DSH
Lazy-loading MCP tools for DeepSeek Harness (DSH): one loader tool per multi-tool MCP server, per-agent tool masking and description presets