/**
 * Context Compaction with RLM (Retrieval-augmented Language Model) pattern.
 *
 * Strategy:
 * - Keep last N messages verbatim (the "hot window")
 * - Compact older messages into summaries (the "cold archive")
 * - Use keyword retrieval to pull relevant archived messages back
 *   into context when the current prompt matches them
 *
 * This lets conversations go much longer without overwhelming context.
 */
export interface CompactedMessage {
    role: "user" | "assistant";
    content: string;
    /** Original message ID for deduplication */
    originalId?: string;
    /** Whether this is a compacted summary vs original */
    isCompacted?: boolean;
}
export interface ContextWindow {
    /** System prompt pieces */
    systemParts: string[];
    /** Messages to send to the model */
    messages: CompactedMessage[];
    /** Total estimated tokens */
    estimatedTokens: number;
    /** Number of messages that were compacted */
    compactedCount: number;
}
export interface CompactionConfig {
    /** Messages to keep verbatim (the hot window). Default: 6 */
    hotWindowSize: number;
    /** Max estimated tokens for the full context. Default: 8000 */
    maxContextTokens: number;
    /** Number of archived messages to retrieve via RLM. Default: 3 */
    rlmRetrievalCount: number;
    /** Trigger compaction when message count exceeds this. Default: 8 */
    compactionThreshold: number;
}
export declare const DEFAULT_COMPACTION_CONFIG: CompactionConfig;
/**
 * Build an optimized context window using RLM pattern.
 *
 * 1. Keep last `hotWindowSize` messages verbatim
 * 2. Archive older messages
 * 3. Use keyword retrieval to find relevant archived messages
 * 4. Compact remaining archived messages into a summary
 */
export declare function buildContextWindow(allMessages: CompactedMessage[], currentPrompt: string, config?: CompactionConfig): ContextWindow;
//# sourceMappingURL=compaction.d.ts.map