Bundle
@dsh-extension/dsh-vision-bridge
On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
sfyyy6
Browse
9 results
Bundle
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
cinob2
Bundle
dsh-llm-qwen-local
DeepSeek Harness LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint: per-model multimodal switch, fully configurable reasoning efforts, and a web settings page (client plugin) for editing the deployment from the frontend
starefinger2
Bundle
dsh-local-vision
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
hyls95271
Bundle
dsh-vision-api-localorweb
DSH 插件：可接入识图模型 API（本地大模型识图工具 + 设置界面）。配置 OpenAI 兼容的识图接口（LM Studio / vLLM / Ollama 等），接口留空即不启用识图模型。
TIPSONG1
Bundle
dsh-llm-openai-completions
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.
drscrewdriver1
Bundle
modelspoke
Local OpenAI-compatible model-server discovery + tiered reasoning-metadata resolution for DeepSeek Harness (dsh).
americanjeff1
Bundle
dsh-model-manager
DSH plugin: manage local model inference servers (llama.cpp / vLLM / SGLang) — registry, safe start/stop, parameter profile versioning with validation. Red lines: never pkill, never stop protected port 11437, never auto-restart dsh.
Ansonfishing
Bundle
dsh-tool-call-guard
Neutralize tool calls with invalid JSON arguments on the wire, so one malformed model generation cannot brick a session against strict OpenAI-compatible servers (vLLM et al).
alchemistwu