DeepSeek Harness Plugin

devhang/dsh-llm-sampling-params

Category Models & Providers Added 2026-11-15

Injects per-model sampling parameters into chat-completions requests to OpenAI-compatible gateways: a fetch wrapper looks the request body's model id up in a configured models table and sets temperature, top_p, top_k, min_p, repeat_penalty, presence_penalty and frequency_penalty on requests whose URL carries /v1/chat/completions, plus repetition_penalty for SGLang and vLLM.

Install

# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)

dsh plugin --profile web add github:devhang/dsh-llm-sampling-params

Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).

Links

More in this category

View the whole category →

Community comments

Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.