所有实时 LLM 提示和响应都会经过第三方网关
原文依据:3 处Skill 要求将每个实时 LLM 调用点的基础 URL 改为 Caveman。网关因此处在应用与模型提供商之间,能够接收请求内容和返回内容;“byte-preserving”及“不转发认证头”只是 Skill 中的产品声明,所给源码无法独立验证。
发送给模型的源代码、用户对话、文档、个人信息或其他机密数据可能进入 Caveman 的处理和计量系统,并受其日志、留存、访问控制及司法辖区约束。
该 Skill 的实时指令要求把每个活跃 LLM 调用点改为经过 Caveman,并称网关会测量应用发送的内容及其成本。因此,启用后请求和响应会进入第三方代理的处理路径,可能包含提示、模型输出及其他敏感业务数据。“byte-preserving”等描述只是 Skill 自身对服务行为的声明,所给材料没有独立证明数据保留、访问或日志策略。用户可要求作者提供数据处理、保留和删除条款,并限制送入网关的数据类别。
You are wiring this repository through the Caveman gateway. Caveman is abyte-preserving LLM proxy: in record mode it measures what your app sends andwhat it costs, and changes nothing else. Your job is a minimal, verifiedintegration — not a refactor.查看另外 2 个位置
1. **Coherent integration.** Wire every live LLM callsite through existing configuration and responsible seams. Touch each layer correctness requires. No drive-by refactors or formatting sweeps; add an abstraction only when itTwo facts that make the wiring safe (both are gateway-enforced, not hopes):the gateway rebuilds upstream auth headers from scratch, so a client's`Authorization`/`x-api-key` value is never forwarded to the provider; and with`stored`, upstream auth comes from the encrypted connection server-side. So in`stored` mode, where an SDK insists on an api-key parameter, set it to theCave key — it authenticates the gateway and goes no further.