dsh-llm-gateway-compat
OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness
120 results
OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness
DeepSeek Harness plugin: AnySearch-backed web search provider (aggregates exa/tavily/firecrawl via one MCP gateway) registered into ctx.web.
MCP stdio gateway exposing AI CLI agents to DSH as MCP tools
Authenticated LAN reverse-proxy gateway for the DeepSeek Harness Web UI
DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.
Unified trusted settings and password access gateway for DeepSeek Harness
Source-filtered remote gateway for DeepSeek Harness behind an authenticated reverse proxy
One-shot Pi subagent provider and true-gateway over the Pi RPC protocol
DSH LLM provider hub with a native model-configuration panel, gateway routes, model catalogs and live model discovery. Supports three wire protocols, custom User-Agent, model overrides and live routing without hand-editing settings.yaml.
DSH Mobile Remote plugin: Host Gateway, Public Endpoint pairing, WebRTC Direct, encrypted Tunnel Fallback
DeepSeek Harness plugin: transcodes images to a base64-safe format (PNG) before a vision request, fixing gateways like LM Studio that reject non-PNG/JPEG/GIF data URLs with "'url' field must be a base64 encoded image."
One-shot Codex subagent provider over the official app-server protocol
Patient auto-retry for DeepSeek Harness: honor the upstream gateway's retry_after_seconds on a 429 capacity cooldown instead of giving up after two fast retries, and wait out the mislabeled modality 400 a saturated gateway replays from its client-error circuit. Optional floating countdown badge included.
DSH plugin: manages the Windows llama-server.exe model lifecycle (start / stop / switch / recover) behind a stable OpenAI-compatible gateway, with graceful Ctrl+C shutdown that actually frees VRAM.
DeepSeek Harness plugin that serves every gpt-load model from one provider group, each model on its own wire protocol (OpenAI Chat Completions or Anthropic Messages), synced from /api/models
DeepSeek Harness compatibility plugin: send the x-opencode-session header opencode.ai's gateway requires on opencode / opencode-go routes.
WorkBuddy (workbuddy.ai / codebuddy.cn) subscription quota as a DSH model provider: supervises the local OpenAI-compatible gateway and exposes it as a settings page.
Capability metadata for hand-declared gateway models, resolved at runtime by bare model name (context window, output cap, reasoning levels, vision) — matched against the official DeepSeek route's catalog, the installed pi-ai catalog, opencode and models.dev, without writing to your settings.
DeepSeek Harness 插件:AI 聚合网关可视化控制台——集成 Google Antigravity 与 OpenAI Codex 反代、多账号轮换池、5h/周额度看板与故障转移。
Reuse the Qoder desktop app's sign-in or run the Qoder device login from the card to bring Qoder's models into DeepSeek Harness — 10 live-verified model keys over the Qoder model gateway, with an expandable settings card in the Web UI.
LANtern(局域网模型灯塔):把本机 DeepSeek Harness 已注册的全部 AI 模型,以 OpenAI / Anthropic 兼容接口照亮给同一局域网。只读复用 DSH 的模型注册表,全部产物写在插件自己的 data/ 目录内。
Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.
DSH plugin: Docker Desktop MCP gateway with a UI profile picker (wraps @deepseek-ai/dsh-mcp-client)
Resilient web search and page extract tools for DeepSeek Harness with a Tavily → Firecrawl → Exa → SearXNG fallback chain and SSRF-safe extract.