@juspay/neurolink/dist/utils/toolResultStatus.d.ts

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

/**
 * Classification of a tool result that the loop received as a normal return
 * but that reports a failure in-band.
 *
 * `neurolink.executeTool` converts a thrown error and a circuit-breaker
 * refusal into `{ isError: true, content: [...] }`, MCP servers return the
 * same shape for a failed call, and the documented custom-tool pattern is
 * `return { error: "User not found" }`. Every consumer that decides "did this
 * tool succeed" — the `tool:end` event, the stored `tool_result` row, the
 * replayed marker, and `toolExecutions[].isError` — has to read those shapes
 * the same way, so the rule lives in ONE predicate, `isErrorShapedToolResult`,
 * and this module only extracts the text to report for it.
 */
/**
 * The error text carried by an error-shaped result (`isError: true`, an
 * `error` field, or a failing `status`), or undefined when the value is not
 * one. Prefers an `error` string, then a serialized non-string `error`, then
 * the joined text parts of an MCP `content` array, then a fixed fallback.
 */
export declare function extractIsErrorText(output: unknown): string | undefined;
/**
 * Same classification for a serialized result: the memory stores keep
 * `tool_result.content` as a JSON string, so a row written before the store
 * learned to flag error shapes can still be recognised at replay.
 */
export declare function extractIsErrorTextFromContent(content: unknown): string | undefined;