dsh-plugin-custom-provider-enhancer
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
6 results
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model over its native wire protocol (OpenAI / Anthropic / Gemini) via the pi-ai SDK
会话 token 用量与费用速览:每轮结束显示本轮 token/费用 chip,输入条上方显示会话累计费用。价格自动拉取(LiteLLM 价格表,host 侧缓存)+ 按模型手动覆盖 + 汇率换算。纯 UI 展示,不进入模型上下文。
LiteLLM /v1/search-backed web search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request — no model turn.
每天自动巡 RSS:AI 简报 + 脑神经/意识简报,关键词过滤后压成速览+详情。DSH 插件形态;巡检脚本仍用 Python / 计划任务。
LiteLLM provider for DeepSeek Harness