import type { CompletionStats } from '../../../../schemas/index.js';
import type { LlmStats } from '../../../../utils/addon-responses.js';
export declare function normalizeCompletionStats(stats: LlmStats | undefined): {
    timeToFirstToken?: number | undefined;
    tokensPerSecond?: number | undefined;
    promptTokensPerSecond?: number | undefined;
    cacheTokens?: number | undefined;
    promptTokens?: number | undefined;
    generatedTokens?: number | undefined;
    emittedTokens?: number | undefined;
    avgConcurrentSeq?: number | undefined;
    toolDefinitionsDropped?: number | undefined;
    backendDevice?: "cpu" | "gpu" | undefined;
} | undefined;
/**
 * Attach the count of non-empty pieces the addon streamed without
 * overwriting `generatedTokens` (`llama_perf` `n_eval`). Length / KV-cache
 * decisions keep the decode count; usage reporting prefers `emittedTokens`.
 * Zero is attached explicitly so inflated `n_eval` cannot be used as usage
 * when nothing was streamed.
 */
export declare function withEmittedTokens(stats: CompletionStats | undefined, emittedPieces: number): CompletionStats | undefined;
export declare function stoppedByLength({ cancelled, effectivePredict, generatedTokens, stoppedAtContextBoundary }: {
    cancelled: boolean;
    effectivePredict: number | undefined;
    generatedTokens: number | undefined;
    stoppedAtContextBoundary: boolean;
}): boolean;