dsh-mcp-lens
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
113 results
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters
DeepSeek Harness (dsh) 插件:接入 Agnes AI 模型网关,并一键把 dsh 注册为 Paseo 的 ACP provider
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
DeepSeek Harness-native Feishu (Lark) gateway: chat with the DSH agent from Feishu via long connection, with persistent sessions, /new, Markdown replies, live streaming progress cards, native Typing reactions, click-to-answer approval / Q&A cards, and proactive push.
Bidirectional DSH Connection and Typert Gateway integration
AutoRouter (model routing gateway / relay) LLM adapter for the DeepSeek Harness
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
dsh heartbeat plugin: periodic proactive checks + message tool (send iMessage) + settings UI. Independent of the iMessage gateway.
Login wall and public gateway for DeepSeek Harness cloud deploys.
Password gate for dsh-web: opening the web port requires a username/password login; account credentials are stored salted+scrypt-hashed and AES-256-GCM encrypted in a local config file under $DSH_HOME. Host-only cordis plugin, no dsh source changes.
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
Access-password gateway plugin for DeepSeek Harness Web: every request on the gateway port requires authentication (no unauthenticated surface besides the login/setup page), first visit sets the password, and it can be rotated from the dedicated Security settings page.
Live remaining balance and actual spend from the provider for the current API key, not a local token estimate.
微信读书 (WeChat Reading) integration for DeepSeek Harness: connect the official WeRead Skills Agent Gateway with a wrk- API key, then browse your bookshelf, export highlights & thoughts, query reading stats, and send highlights to flomo — agent tools plus a web settings panel
DeepSeek Harness plugin: AnySearch-backed web search provider (aggregates exa/tavily/firecrawl via one MCP gateway) registered into ctx.web.
LAN access plugin for the DeepSeek Harness (dsh) web host: binds all interfaces and serves a token-gated /m/api route family for the companion mobile app
A standalone Lark/Feishu gateway and persistent cron bundle for DeepSeek Harness
FreeLipSync 对口型口播视频面板 —— 在 DSH 界面内嵌的上传/文本/音频/选模型/免费生成/最近生成操作面板。免 Key 免登录,不消耗模型 token。
DeepSeek Harness (dsh) bundle that routes the harness through the OpenLLM gateway — an `openllm` provider on the in-box pi-ai adapter (via the local daemon gateway) plus the OpenLLM MCP server. Pure config; install OpenLLM first (see README).
Agnes AI image and video generation for DeepSeek Harness — agnes_image and agnes_video tools over the Agnes OpenAI-compatible gateway.
dsh 多平台聊天网关插件:将 SillyTavern Gateway 的 QQ/Telegram/Discord/飞书/QQ官方/钉钉适配器移植到 DeepSeek Harness,实现通过 IM 远程指挥 dsh 会话。
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
模型路由网关:一个端点连接 290+ AI 提供商(90+ 免费、1200+ 模型),Claude Code/Codex/Cursor/Cline/Copilot 全兼容——配额感知自动回退、19 种路由策略、RTK+Caveman 叠加压缩省 15-95% token、免费层聚合预算(~1.5B tokens/月)、MCP/A2A、本地优先。受 diegosouzapw/OmniRoute(51k★ MIT)启发。