@juspay/neurolink
Version:
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002
19 lines (18 loc) • 942 B
JavaScript
/**
* Pre-call tool routing — configuration and catalog types.
*
* Host applications can register large numbers of custom tools (typically MCP
* server tools) whose names are prefixed with their server id
* (`${serverId}_${toolName}`). When tool routing is enabled, a cheap router
* LLM call runs once per `stream()` turn, picks the servers relevant to the
* user query, and the tools of every unpicked server are appended to the
* request's `excludeTools` denylist before the main model call.
*
* Denylist semantics are deliberate: the router only knows the declared
* server catalog — a strict subset of the real tool set. Excluding unpicked
* servers leaves NeuroLink's built-in direct tools, always-include servers,
* and any tools outside the catalog untouched. The whole mechanism fails
* open: any router failure resolves to an empty exclusion list (all tools),
* identical to routing being disabled.
*/
export {};