Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
8 plugin trovati
dsh-thinking-levels
drscrewdriver/dsh-thinking-levels
Controllo per round del livello di ragionamento (reasoning_effort) per DeepSeek Harness: Auto pianifica low/high/max dalla cronologia recente dei tool calls, oppure permette di fissare un wire level (off/on/minimal/low/medium/high/xhigh/max), con mappatura wire personalizzata, guard delle capacità in base al modello e preset della finestra di contesto (64K–1M); la capability card per modello si abbina a [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installabile da dsh-market) per provare il reasoning con gateway compatibili OpenAI (vLLM / LM Studio / self-hosted). La card scrive le capacità llm-pi-ai, l'adapter guida il wire (compat.thinkingFormat) e il plugin mantiene la lista di takeover.
dsh-llm-qwen-local
starefinger/dsh-llm-qwen-local
Plugin adattatore LLM per modelli Qwen distribuiti localmente dietro un endpoint vLLM compatibile OpenAI, con switch multimodale per modello, reasoning effort completamente configurabili, più una pagina web di impostazioni da cui si può modificare il deployment dal frontend.
dsh-plugin-thinking-api
qjf44/dsh-plugin-thinking-api
API compatibile con OpenAI con un clic (CodeBuddy/vLLM/proxy) e modalità thinking, evitando il rifiuto content_filter del contenuto con ruolo developer.
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.