dsh-localforge
面向 DeepSeek Harness 的高性能 LM Studio（以及任何兼容 OpenAI/Anthropic 的本地服务器）聊天补全适配器，支持实时发现、自动加载、模型回退、并发控制、Prometheus 指标，以及宽松且支持视觉的合作伙伴适配器。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:orfeomorello/dsh-localforge#a12b87c8badb69171e537d704f124ff766b506bcLocalforge 以 dsh-localforge 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
A high-performance, MIT-licensed adapter that connects DeepSeek Harness (
dsh) to local LLM servers — primarily LM Studio, but also any other OpenAI-compatible or Anthropic-compatible endpoint (Ollama, vLLM, llama.cpp's HTTP server, text-generation-inference, etc.).
Three other LM Studio plugins for dsh exist (and we read all of them
carefully — see Inspirations and the
Comparison). LocalForge is the one that adds the
things missing from every other adapter:
/v1/models + native /api/v0/models fallback,
with TTL and explicit invalidation. The other plugins re-probe the server
on every resolveModel.POST /api/v0/models/{id}/load) and poll until
ready.fallback: [primary, secondary]. If the primary
model returns a recoverable error, the next one is tried automatically.code, chat, creative, precise for sane
defaults that you can override per request./metrics with TTFT, TPS, queue depth, error
rates, and cache hits./metrics
up gauge surfaces the state./v1/messages, useful for Claude-style system prompts and tool calls.strict + noUncheckedIndexedAccess, full
test coverage, GitHub Actions CI.dsh), with pnpm install completed at its root.1234) is the most-tested target; any OpenAI- or
Anthropic-compatible server works.# 1. clone the plugin into the dsh checkout's plugins/ directory
cd <dsh-checkout>
git clone https://github.com/orfeomorello/dsh-localforge plugins/dsh-localforge
cd plugins/dsh-localforge
# 2. install (the @deepseek-ai/* deps are `link:` to the parent checkout;
# --ignore-workspace keeps pnpm from treating this as a workspace root)
pnpm install --ignore-workspace
# 3. link the plugin into the web profile
cd ../..
pnpm dsh plugin --profile web add link:./plugins/dsh-localforge
# 4. start the web UI; refresh http://127.0.0.1:3080
pnpm dsh web
In the model picker at the top of the page you'll now see LocalForge as a provider; pick any model LM Studio has loaded.
Minimal ~/.dsh/settings.yaml section:
llm-localforge:
defaultConnection:
baseURL: http://localhost:1234/v1
models:
- id: qwen/qwen3-8b
preset: code
fallback:
- qwen/qwen3-4b
- llama-3.1-8b
That's it. Point dsh at any conversation, select "LocalForge" as the provider, and traffic flows to LM Studio. Your DeepSeek API balance is untouched.
See docs/CONFIGURATION.md for the full reference (every section, every field, every default).
See docs/ARCHITECTURE.md for the design notes — the per-request resolver trick, the dual-endpoint discovery, the SSE parsing, the Prometheus metric set, and the testing strategy.
LocalForge is a clean-room reimplementation. We read three existing plugins to learn the patterns, then wrote everything from scratch with our own license. The inspirations are:
No code was copied. See docs/COMPARISON.md for the full feature-by-feature matrix.
MIT © 2026 The LocalForge authors.