@juspay/neurolink/dist/types/backgroundCommand.js

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

/**
 * Background commands (N4) — run a command detached, bank its output, monitor
 * it — types.
 *
 * A long-running agent has to run real commands: a build, a test suite, a
 * linter whose output is the evidence for a review finding. Two things make
 * that safe and useful, and both are in these types.
 *
 * 1. **Nothing is discarded.** Both streams go straight to files and the FULL
 *    files are banked as artifacts when the command settles. What reaches the
 *    conversation is a bounded `tailPreview` plus a {@link BankedArtifactRef}
 *    per stream — a pointer, never a replacement. `maxOutputBytes` is the one
 *    bound, and hitting it is a loud state (`output-limit`), not a silent cut.
 * 2. **Execution is a contract, not advice.** `argv` arrays only, no shell
 *    ever; an executable allowlist; a cwd that must resolve, through symlinks,
 *    inside a declared root; a timeout that actually kills.
 *
 * Naming: `cli.ts` already owns `CommandResult` / `CommandDefinition` and
 * `action.ts` owns `ActionCommand`, so everything here carries the
 * `BackgroundCommand` prefix (Critical Rule 9).
 */
export {};