@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
23 lines (22 loc) • 1.07 kB
JavaScript
/**
* Read-only git toolset (N4.4) — types.
*
* A reviewing agent needs git constantly: what changed, who wrote it, what the
* merge base was. Handing it a shell to run `git` in is the wrong shape twice
* over — it can then run anything, and git itself has write-capable options
* (`--output=<file>`, `diff.external`) that a free-form argument string would
* carry straight through.
*
* So these tools are BOUNDED: the model supplies validated values (a ref, a
* path, a line range), never flags, and each tool assembles a fixed argv from
* them. The whole surface is six read-only subcommands. Execution goes through
* the same hardened runner as {@link BackgroundCommandPolicy} — argv arrays,
* no shell, a cwd sandboxed to the repository, a timeout, a byte cap — and the
* full output is banked, so a 40 MB diff costs a bounded preview plus a
* pointer.
*
* Naming: nothing else in the types folder claims `Git`, and `tools.ts` owns
* the unprefixed `Tool*` names, so these carry the `GitTool` prefix
* (Critical Rule 9).
*/
export {};