@juspay/neurolink/dist/context/contextDecision.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

/**
 * Relevance-driven context compaction.
 *
 * Every stage of the existing compactor is *positional*: prune protects the
 * most recent 40K tokens, truncation drops the oldest half, summarization
 * keeps a trailing ratio. None of them has any notion of what the current
 * request is about, so a fifty-turn conversation that ends with "now rename
 * that variable" keeps the forty turns about database migrations and drops
 * nothing that matters less.
 *
 * A decision model changes the economics of asking. Latency is flat in
 * question count — one question and four hundred questions cost the same
 * round trip — so "is this message needed to answer the current request?" can
 * be asked about *every* message at once, for about $0.00002.
 *
 * What it must never do is lose something the turn needed. The guards below
 * are therefore deliberately conservative, and every one of them is a veto:
 *
 * - only plain user/assistant text is ever eligible; tool calls, tool
 *   results, summaries, pinned skills and system messages are untouchable,
 *   because dropping half of a tool-call pair produces a malformed request
 *   rather than a smaller one
 * - the most recent messages are never eligible, whatever the model says
 * - a message is dropped only on a CONFIDENT no, never on silence or a
 *   near-coin-flip
 * - at most a bounded fraction of eligible messages may go in one pass
 *
 * @module context/contextDecision
 */
import type { ChatMessage, ContextRelevanceOptions, ContextRelevanceResult, DecisionCallerFn } from "../types/index.js";
/**
 * Ask which earlier messages the current request still needs, and return the
 * ones to drop.
 *
 * Returns `null` when nothing should change — no decision provider, a failed
 * call, nothing eligible, or no confident drop. A null return is the signal
 * to carry on with positional compaction exactly as before.
 */
export declare function selectIrrelevantMessages(messages: ChatMessage[], currentRequest: string, decide: DecisionCallerFn, options?: ContextRelevanceOptions): Promise<ContextRelevanceResult | null>;
/**
 * Gate a generated summary before it replaces the messages it covers.
 *
 * Stage 3 accepts any non-empty string today, so a summarizer that returned
 * an apology, a refusal, or a truncated fragment silently destroys the
 * conversation it was meant to preserve — and the messages are gone by the
 * time anyone reads the summary.
 *
 * Returns `true` when the summary may be used and `false` only on a confident
 * rejection. Anything else — no decision provider, a failed call, an
 * unanswered or uncertain verdict — returns `true`, because refusing a
 * summary means falling through to truncation, which loses strictly more.
 */
export declare function summaryPreservesContext(summary: string, replacedMessages: ChatMessage[], decide: DecisionCallerFn, options?: {
    timeoutMs?: number;
    minConfidence?: number;
}): Promise<boolean>;