smom-dbis-138/services/bridge/observability.ts

/**
 * @file observability.ts
 * @notice Metrics, logging, and monitoring for bridge operations
 */

import { ethers } from 'ethers';

export interface BridgeMetrics {
    totalTransfers: number;
    successCount: number;
    failureCount: number;
    refundCount: number;
    liquidityFailures: number;
    avgSettlementTime: number;
    routeMetrics: RouteMetrics[];
}

export interface RouteMetrics {
    chainId: number;
    provider: string;
    successCount: number;
    failureCount: number;
    avgSettlementTime: number;
    totalVolume: string;
}

export interface TransferLog {
    transferId: string;
    timestamp: number;
    event: string;
    data: any;
    level: 'info' | 'warn' | 'error';
}

export class BridgeObservability {
    private metrics: BridgeMetrics;
    private logs: TransferLog[] = [];
    private maxLogs: number = 10000;

    constructor() {
        this.metrics = {
            totalTransfers: 0,
            successCount: 0,
            failureCount: 0,
            refundCount: 0,
            liquidityFailures: 0,
            avgSettlementTime: 0,
            routeMetrics: []
        };
    }

    /**
     * Record transfer initiation
     */
    recordTransferInitiated(transferId: string, data: any): void {
        this.metrics.totalTransfers++;
        this.log('info', transferId, 'TRANSFER_INITIATED', data);
    }

    /**
     * Record transfer success
     */
    recordTransferSuccess(transferId: string, settlementTime: number, route: RouteMetrics): void {
        this.metrics.successCount++;
        this.updateAvgSettlementTime(settlementTime);
        this.updateRouteMetrics(route, true);
        this.log('info', transferId, 'TRANSFER_SUCCESS', { settlementTime, route });
    }

    /**
     * Record transfer failure
     */
    recordTransferFailure(transferId: string, error: string, route?: RouteMetrics): void {
        this.metrics.failureCount++;
        if (route) {
            this.updateRouteMetrics(route, false);
        }
        this.log('error', transferId, 'TRANSFER_FAILURE', { error, route });
    }

    /**
     * Record refund
     */
    recordRefund(transferId: string, reason: string): void {
        this.metrics.refundCount++;
        this.log('warn', transferId, 'REFUND_INITIATED', { reason });
    }

    /**
     * Record liquidity failure
     */
    recordLiquidityFailure(transferId: string, chainId: number, token: string): void {
        this.metrics.liquidityFailures++;
        this.log('error', transferId, 'LIQUIDITY_FAILURE', { chainId, token });
    }

    /**
     * Update average settlement time
     */
    private updateAvgSettlementTime(settlementTime: number): void {
        const total = this.metrics.successCount;
        this.metrics.avgSettlementTime =
            (this.metrics.avgSettlementTime * (total - 1) + settlementTime) / total;
    }

    /**
     * Update route metrics
     */
    private updateRouteMetrics(route: RouteMetrics, success: boolean): void {
        const existing = this.metrics.routeMetrics.find(
            r => r.chainId === route.chainId && r.provider === route.provider
        );

        if (existing) {
            if (success) {
                existing.successCount++;
            } else {
                existing.failureCount++;
            }
            existing.avgSettlementTime =
                (existing.avgSettlementTime * (existing.successCount + existing.failureCount - 1) +
                    route.avgSettlementTime) /
                (existing.successCount + existing.failureCount);
        } else {
            this.metrics.routeMetrics.push({
                ...route,
                successCount: success ? 1 : 0,
                failureCount: success ? 0 : 1
            });
        }
    }

    /**
     * Log event
     */
    private log(level: 'info' | 'warn' | 'error', transferId: string, event: string, data: any): void {
        const log: TransferLog = {
            transferId,
            timestamp: Date.now(),
            event,
            data,
            level
        };

        this.logs.push(log);

        // Keep only last maxLogs
        if (this.logs.length > this.maxLogs) {
            this.logs = this.logs.slice(-this.maxLogs);
        }

        // Emit to external logging system (e.g., Loki, CloudWatch)
        this.emitLog(log);
    }

    /**
     * Emit log to external system
     */
    private emitLog(log: TransferLog): void {
        // In production, send to logging service
        console.log(`[${log.level.toUpperCase()}] ${log.event}`, log);
    }

    /**
     * Get current metrics
     */
    getMetrics(): BridgeMetrics {
        return { ...this.metrics };
    }

    /**
     * Get success rate
     */
    getSuccessRate(): number {
        const total = this.metrics.successCount + this.metrics.failureCount;
        if (total === 0) return 0;
        return (this.metrics.successCount / total) * 100;
    }

    /**
     * Get refund rate
     */
    getRefundRate(): number {
        if (this.metrics.totalTransfers === 0) return 0;
        return (this.metrics.refundCount / this.metrics.totalTransfers) * 100;
    }

    /**
     * Get logs for transfer
     */
    getTransferLogs(transferId: string): TransferLog[] {
        return this.logs.filter(log => log.transferId === transferId);
    }

    /**
     * Get logs by level
     */
    getLogsByLevel(level: 'info' | 'warn' | 'error', limit: number = 100): TransferLog[] {
        return this.logs
            .filter(log => log.level === level)
            .slice(-limit)
            .reverse();
    }

    /**
     * Export metrics for Prometheus
     */
    exportPrometheusMetrics(): string {
        const lines: string[] = [];

        lines.push(`# HELP bridge_total_transfers Total number of bridge transfers`);
        lines.push(`# TYPE bridge_total_transfers counter`);
        lines.push(`bridge_total_transfers ${this.metrics.totalTransfers}`);

        lines.push(`# HELP bridge_success_count Number of successful transfers`);
        lines.push(`# TYPE bridge_success_count counter`);
        lines.push(`bridge_success_count ${this.metrics.successCount}`);

        lines.push(`# HELP bridge_failure_count Number of failed transfers`);
        lines.push(`# TYPE bridge_failure_count counter`);
        lines.push(`bridge_failure_count ${this.metrics.failureCount}`);

        lines.push(`# HELP bridge_success_rate Success rate percentage`);
        lines.push(`# TYPE bridge_success_rate gauge`);
        lines.push(`bridge_success_rate ${this.getSuccessRate()}`);

        lines.push(`# HELP bridge_avg_settlement_time Average settlement time in seconds`);
        lines.push(`# TYPE bridge_avg_settlement_time gauge`);
        lines.push(`bridge_avg_settlement_time ${this.metrics.avgSettlementTime}`);

        return lines.join('\n');
    }
}