Plugins
Navegue, filtre e instale plugins do DeepSeek-Harness.
8 plugins encontrados
dsh-thinking-levels
drscrewdriver/dsh-thinking-levels
Controle por rodada do nível de raciocínio (reasoning_effort) para DeepSeek Harness: Auto agenda low/high/max pelo histórico recente de tool calls, ou permite fixar um wire level (off/on/minimal/low/medium/high/xhigh/max), com mapeamento wire personalizado, proteção de capacidade por modelo e presets de janela de contexto (64K–1M); seu capability card por modelo funciona com [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (instalável pelo dsh-market) para testar raciocínio em gateways compatíveis com OpenAI (vLLM / LM Studio / self-hosted). O card escreve capacidades llm-pi-ai, o adapter controla o wire (compat.thinkingFormat) e o plugin mantém a lista de takeover.
dsh-llm-qwen-local
starefinger/dsh-llm-qwen-local
Plugin adaptador de LLM para modelos Qwen implementados localmente atrás de um endpoint vLLM compatível com OpenAI, com comutador multimodal por modelo, esforços de raciocínio totalmente configuráveis e uma página web de definições para editar a implementação a partir do frontend.
dsh-plugin-thinking-api
qjf44/dsh-plugin-thinking-api
API compatível com OpenAI em um clique (CodeBuddy/vLLM/proxies) com modo de raciocínio, evitando rejeição de content_filter em conteúdo de função de desenvolvedor.
dsh-wsl-hostsvc
173787247/dsh-wsl-hostsvc
Probes Windows-host Ollama, LM Studio, vLLM, and llama-server from WSL, compares ctx, and reports /v1/models apiReady versus TCP.
dsh-wsl-docker
173787247/dsh-wsl-docker
Reports Docker CLI, context, and daemon reachability in WSL, plus vLLM :8000 /v1/models health and GPU runtime hints.
dsh-llm-openai-completions
drscrewdriver/dsh-llm-openai-completions
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).
dsh-image-guard
mafeis/dsh-image-guard
Trims historical images in outgoing chat requests down to a recent-image count, learns the provider per-prompt image cap from HTTP 400 responses, and retries with fewer images so image-heavy sessions keep working.
dsh-model-manager
ansonfishing/dsh-model-manager
Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.