dsh-liquid-inference
Liquid Inference for DeepSeek Harness：一个 `liquid` 模型路由，以及只读市场工具
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:architect-xyz/liquid-dsh-plugin#9a225c6a7662024f85e1830995257da0ab98a57cLiquid Inference 以 dsh-liquid-inference 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。
Liquid Inference for DeepSeek Harness: a liquid model route plus read-only market tools.
export LIQUID_API_KEY=sk-liquid-... # buyer key with the `spend` scope
dsh plugin --profile web add dsh-liquid-inference
Pick Liquid Auto (liquid.auto) in the model picker.
Model route liquid — no adapter code. The bundle patch configures the stock llm-pi-ai adapter with api: openai-completions, baseURL: https://router.inference.ai.exchange/v1 and apiKeyEnv: LIQUID_API_KEY.
x-liquid-cap-usd, the most it can cost, locked before the first token. The default is 1 USD; set LIQUID_CAP_USD in the launching environment to change it.liquid.auto plus its ranking variants :cheapest, :economy, :balanced and :premium (documented in the description of GET /v1/exchange/routers), and deepseek-v4-flash as a pinned model. Add any id from GET /v1/models with a models entry in your profile's cordis.patch.yml.low, medium and high are sent as reasoning_effort. The exchange passes the level through unchecked, so a level the winning provider rejects fails that request.Tools (plugin liquid-inference)
| Tool | Endpoint | Key |
|---|---|---|
liquid_get_book | GET /v1/exchange/offers | no |
liquid_get_markets | GET /v1/exchange/markets | no |
liquid_get_routers | GET /v1/exchange/routers | no |
liquid_get_job | GET /v1/jobs/{id} | yes |
Chat, image, speech and video purchases are deliberately not tools: the harness's own model route is the one place that spends.
Full prompts and tool results go to router.inference.ai.exchange, which forwards them to whichever third-party provider wins the auction. The key is read per request, from the credential store when the profile mounts one and from LIQUID_API_KEY otherwise (headless profiles disable the store). It is never written to config.
llm-pi-ai row's whole config. If another bundle also configures pi-ai providers, restate them in your profile's cordis.patch.yml.pnpm install && pnpm run check. pnpm run test:install packs the bundle, installs the tarball into an isolated profile of a real dsh (DSH_VERSION picks the release, default next) and boots it; it needs network access.