pn-new-crm/src/lib/services/system-monitoring.service.ts

import { db } from '@/lib/db';
import { auditLogs, errorEvents } from '@/lib/db/schema';
import { redis } from '@/lib/redis';
import { getQueue, QUEUE_CONFIGS, type QueueName } from '@/lib/queue';
import { createAuditLog } from '@/lib/audit';
import { env } from '@/lib/env';
import { sql, desc, eq } from 'drizzle-orm';
import { NotFoundError } from '@/lib/errors';
import { logger } from '@/lib/logger';

// ─── Types ────────────────────────────────────────────────────────────────────

export interface ServiceStatus {
  name: string;
  status: 'healthy' | 'degraded' | 'down';
  responseTimeMs: number;
  details?: string;
}

export interface HealthStatus {
  overall: 'healthy' | 'degraded' | 'down';
  services: ServiceStatus[];
  checkedAt: Date;
}

export interface QueueStatus {
  name: string;
  waiting: number;
  active: number;
  completed: number;
  failed: number;
  delayed: number;
}

export interface QueueJobSummary {
  id: string;
  name: string;
  data: unknown;
  status: string;
  timestamp: number | undefined;
  processedOn: number | undefined;
  finishedOn: number | undefined;
  failedReason: string | undefined;
}

export interface PaginatedQueueJobs {
  jobs: QueueJobSummary[];
  total: number;
  page: number;
  limit: number;
}

export interface ConnectionStatus {
  totalConnections: number;
}

export interface RecentError {
  id: string;
  source: 'audit' | 'queue' | 'request';
  message: string;
  timestamp: Date;
  metadata?: Record<string, unknown>;
  /** Set for `source: 'request'` rows so the UI can deep-link to
   *  /admin/errors/<requestId>. */
  requestId?: string;
  /** Set for `source: 'request'` rows. */
  statusCode?: number;
  /** Set for `source: 'request'` rows. */
  errorCode?: string | null;
}

// ─── Timeout helper ───────────────────────────────────────────────────────────

function withTimeout<T>(promise: Promise<T>, ms: number): Promise<T> {
  return Promise.race([
    promise,
    new Promise<T>((_, reject) =>
      setTimeout(() => reject(new Error(`Timed out after ${ms}ms`)), ms),
    ),
  ]);
}

// ─── healthCheck ──────────────────────────────────────────────────────────────

export async function healthCheck(): Promise<HealthStatus> {
  const checks = await Promise.allSettled([
    checkPostgres(),
    checkRedis(),
    checkMinio(),
    checkDocumenso(),
  ]);

  const services: ServiceStatus[] = checks.map((result) => {
    if (result.status === 'fulfilled') return result.value;
    // Should not happen since each checker catches internally
    return {
      name: 'unknown',
      status: 'down' as const,
      responseTimeMs: 0,
      details: String(result.reason),
    };
  });

  const hasDown = services.some((s) => s.status === 'down');
  const hasDegraded = services.some((s) => s.status === 'degraded');
  const overall = hasDown ? 'down' : hasDegraded ? 'degraded' : 'healthy';

  return { overall, services, checkedAt: new Date() };
}

async function checkPostgres(): Promise<ServiceStatus> {
  const start = Date.now();
  try {
    await withTimeout(db.execute(sql`SELECT 1`), 5000);
    return { name: 'PostgreSQL', status: 'healthy', responseTimeMs: Date.now() - start };
  } catch (err) {
    return {
      name: 'PostgreSQL',
      status: 'down',
      responseTimeMs: Date.now() - start,
      details: err instanceof Error ? err.message : 'Unknown error',
    };
  }
}

async function checkRedis(): Promise<ServiceStatus> {
  const start = Date.now();
  try {
    const result = await withTimeout(redis.ping(), 5000);
    const status = result === 'PONG' ? 'healthy' : 'degraded';
    return { name: 'Redis', status, responseTimeMs: Date.now() - start };
  } catch (err) {
    return {
      name: 'Redis',
      status: 'down',
      responseTimeMs: Date.now() - start,
      details: err instanceof Error ? err.message : 'Unknown error',
    };
  }
}

async function checkMinio(): Promise<ServiceStatus> {
  // Health-checks the ACTIVE storage backend (S3 or filesystem) via
  // the abstraction so a port running on filesystem still gets a
  // useful "Storage" status row instead of a meaningless "MinIO down".
  // Probe key is a sentinel that's never written; head() returns null
  // for a missing object on both backends, which counts as healthy
  // (the connection itself worked).
  const start = Date.now();
  try {
    const { getStorageBackend } = await import('@/lib/storage');
    const backend = await getStorageBackend();
    await withTimeout(backend.head('__health_probe__'), 5000);
    return { name: 'Storage', status: 'healthy', responseTimeMs: Date.now() - start };
  } catch (err) {
    return {
      name: 'Storage',
      status: 'down',
      responseTimeMs: Date.now() - start,
      details: err instanceof Error ? err.message : 'Unknown error',
    };
  }
}

async function checkDocumenso(): Promise<ServiceStatus> {
  const start = Date.now();
  try {
    const controller = new AbortController();
    const timer = setTimeout(() => controller.abort(), 5000);
    try {
      const res = await fetch(`${env.DOCUMENSO_API_URL}/api/v1/health`, {
        signal: controller.signal,
        method: 'GET',
      });
      clearTimeout(timer);
      const status = res.ok ? 'healthy' : 'degraded';
      return { name: 'Documenso', status, responseTimeMs: Date.now() - start };
    } finally {
      clearTimeout(timer);
    }
  } catch (err) {
    return {
      name: 'Documenso',
      status: 'down',
      responseTimeMs: Date.now() - start,
      details: err instanceof Error ? err.message : 'Unreachable',
    };
  }
}

// ─── getQueueDashboard ────────────────────────────────────────────────────────

export async function getQueueDashboard(): Promise<QueueStatus[]> {
  const queueNames = Object.keys(QUEUE_CONFIGS) as QueueName[];
  const results = await Promise.allSettled(
    queueNames.map(async (name) => {
      const queue = getQueue(name);
      const counts = await queue.getJobCounts(
        'waiting',
        'active',
        'completed',
        'failed',
        'delayed',
      );
      return {
        name,
        waiting: counts.waiting ?? 0,
        active: counts.active ?? 0,
        completed: counts.completed ?? 0,
        failed: counts.failed ?? 0,
        delayed: counts.delayed ?? 0,
      } satisfies QueueStatus;
    }),
  );

  return results.map((r, i) => {
    if (r.status === 'fulfilled') return r.value;
    const name = queueNames[i] ?? 'unknown';
    logger.warn({ queue: name, err: r.reason }, 'Failed to get queue counts');
    return {
      name,
      waiting: 0,
      active: 0,
      completed: 0,
      failed: 0,
      delayed: 0,
    };
  });
}

// ─── getQueueJobs ─────────────────────────────────────────────────────────────

type JobStatus = 'waiting' | 'active' | 'completed' | 'failed' | 'delayed';

export async function getQueueJobs(
  queueName: QueueName,
  status: JobStatus = 'failed',
  page = 1,
  limit = 20,
): Promise<PaginatedQueueJobs> {
  const queue = getQueue(queueName);
  const start = (page - 1) * limit;
  const end = start + limit - 1;

  const jobs = await queue.getJobs([status], start, end);
  const counts = await queue.getJobCounts(status);
  const total = counts[status] ?? 0;

  const summaries: QueueJobSummary[] = jobs.map((job) => {
    // Truncate job data to prevent huge payloads
    let truncatedData: unknown;
    try {
      const dataStr = JSON.stringify(job.data);
      truncatedData =
        dataStr.length > 500 ? JSON.parse(dataStr.slice(0, 500) + '...(truncated)') : job.data;
    } catch {
      truncatedData = '[unparseable]';
    }

    return {
      id: job.id ?? '',
      name: job.name,
      data: truncatedData,
      status,
      timestamp: job.timestamp,
      processedOn: job.processedOn ?? undefined,
      finishedOn: job.finishedOn ?? undefined,
      failedReason: job.failedReason ?? undefined,
    };
  });

  return { jobs: summaries, total, page, limit };
}

// ─── retryJob ─────────────────────────────────────────────────────────────────

export async function retryJob(queueName: QueueName, jobId: string, userId: string): Promise<void> {
  const queue = getQueue(queueName);
  const job = await queue.getJob(jobId);
  if (!job) throw new NotFoundError('queue job');

  await job.retry();

  void createAuditLog({
    userId,
    portId: null,
    action: 'update',
    entityType: 'queue_job',
    entityId: jobId,
    metadata: { queueName, jobName: job.name, action: 'retry' },
    ipAddress: 'system',
    userAgent: 'system',
  });
}

// ─── deleteJob ────────────────────────────────────────────────────────────────

export async function deleteJob(
  queueName: QueueName,
  jobId: string,
  userId: string,
): Promise<void> {
  const queue = getQueue(queueName);
  const job = await queue.getJob(jobId);
  if (!job) throw new NotFoundError('queue job');

  await job.remove();

  void createAuditLog({
    userId,
    portId: null,
    action: 'delete',
    entityType: 'queue_job',
    entityId: jobId,
    metadata: { queueName, jobName: job.name, action: 'delete' },
    ipAddress: 'system',
    userAgent: 'system',
  });
}

// ─── getActiveConnections ─────────────────────────────────────────────────────

export async function getActiveConnections(): Promise<ConnectionStatus> {
  try {
    const { getIO } = await import('@/lib/socket/server');
    const io = getIO();
    const sockets = await io.fetchSockets();
    return { totalConnections: sockets.length };
  } catch {
    return { totalConnections: 0 };
  }
}

// ─── getRecentErrors ──────────────────────────────────────────────────────────

export async function getRecentErrors(limit = 20): Promise<RecentError[]> {
  // Fetch permission-denied audit log entries
  const auditErrors = await db
    .select({
      id: auditLogs.id,
      action: auditLogs.action,
      entityType: auditLogs.entityType,
      entityId: auditLogs.entityId,
      metadata: auditLogs.metadata,
      createdAt: auditLogs.createdAt,
    })
    .from(auditLogs)
    .where(eq(auditLogs.action, 'permission_denied'))
    .orderBy(desc(auditLogs.createdAt))
    .limit(limit);

  const auditResults: RecentError[] = auditErrors.map((row) => ({
    id: row.id,
    source: 'audit' as const,
    message: `Permission denied on ${row.entityType}`,
    timestamp: row.createdAt,
    metadata: (row.metadata as Record<string, unknown>) ?? {},
  }));

  // Fetch failed jobs from all queues (sample - top 5 per queue)
  const queueNames = Object.keys(QUEUE_CONFIGS) as QueueName[];
  const failedJobResults = await Promise.allSettled(
    queueNames.map(async (name) => {
      const queue = getQueue(name);
      const jobs = await queue.getJobs(['failed'], 0, 4);
      return jobs.map(
        (job): RecentError => ({
          id: `${name}:${job.id ?? ''}`,
          source: 'queue',
          message: `Queue job failed: ${job.name} in ${name}`,
          timestamp: job.finishedOn ? new Date(job.finishedOn) : new Date(job.timestamp),
          metadata: { queueName: name, failedReason: job.failedReason },
        }),
      );
    }),
  );

  const queueErrors: RecentError[] = failedJobResults
    .filter((r): r is PromiseFulfilledResult<RecentError[]> => r.status === 'fulfilled')
    .flatMap((r) => r.value);

  // Captured 5xx requests from the per-request error_events table -
  // this is the deepest source: full stack head + body excerpt + path.
  // The dedicated /admin/errors page paginates this; here we surface
  // the most recent for the dashboard.
  const requestErrorRows = await db
    .select({
      requestId: errorEvents.requestId,
      statusCode: errorEvents.statusCode,
      method: errorEvents.method,
      path: errorEvents.path,
      errorName: errorEvents.errorName,
      errorMessage: errorEvents.errorMessage,
      metadata: errorEvents.metadata,
      createdAt: errorEvents.createdAt,
    })
    .from(errorEvents)
    .orderBy(desc(errorEvents.createdAt))
    .limit(limit);

  const requestErrors: RecentError[] = requestErrorRows.map((row) => {
    const meta = (row.metadata as Record<string, unknown>) ?? {};
    return {
      id: row.requestId,
      source: 'request' as const,
      message:
        `${row.method} ${row.path} → ${row.statusCode} ${row.errorMessage ?? row.errorName ?? ''}`.trim(),
      timestamp: row.createdAt,
      metadata: meta,
      requestId: row.requestId,
      statusCode: row.statusCode,
      errorCode: typeof meta.code === 'string' ? meta.code : null,
    };
  });

  // Merge and sort combined list by timestamp descending
  const combined = [...auditResults, ...queueErrors, ...requestErrors].sort(
    (a, b) => b.timestamp.getTime() - a.timestamp.getTime(),
  );

  return combined.slice(0, limit);
}