set up metrics collecting with open telemetry (#11236)

Done :  
- move metrics and health cache services from health module to metrics
module
- refactor metrics counter from specific method to set up from enum keys
- add OpenTelemetry (Otel) instrumentation for metrics
- set up Otel SDK to send metrics to Otel collector

To do later : 
- implement Otel instrumentation for traces + plug Sentry on top

packages/twenty-front/src/modules/settings/admin-panel/health-status/components/SettingsAdminHealthAccountSyncCountersTable.tsx

@@ -21,10 +21,6 @@ export const SettingsAdminHealthAccountSyncCountersTable = ({
   }
 
   const items = [
-    {
-      label: 'Not Synced',
-      value: details.counters.NOT_SYNCED,
-    },
     {
       label: 'Active Sync',
       value: details.counters.ACTIVE,

packages/twenty-server/.env.example

@@ -40,6 +40,7 @@ FRONTEND_URL=http://localhost:3001
 # LOGGER_DRIVER=console
 # LOGGER_IS_BUFFER_ENABLED=true
 # EXCEPTION_HANDLER_DRIVER=sentry
+# METER_DRIVER=opentelemetry,console
 # SENTRY_ENVIRONMENT=main
 # SENTRY_RELEASE=latest
 # SENTRY_DSN=https://xxx@xxx.ingest.sentry.io/xxx

packages/twenty-server/package.json

@@ -25,6 +25,9 @@
     "@nestjs/devtools-integration": "^0.1.6",
     "@nestjs/graphql": "patch:@nestjs/graphql@12.1.1#./patches/@nestjs+graphql+12.1.1.patch",
     "@node-saml/passport-saml": "^5.0.0",
+    "@opentelemetry/api": "^1.9.0",
+    "@opentelemetry/exporter-metrics-otlp-http": "^0.200.0",
+    "@opentelemetry/sdk-metrics": "^2.0.0",
     "@ptc-org/nestjs-query-graphql": "patch:@ptc-org/nestjs-query-graphql@4.2.0#./patches/@ptc-org+nestjs-query-graphql+4.2.0.patch",
     "@revertdotdev/revert-react": "^0.0.21",
     "@sentry/nestjs": "^8.30.0",

packages/twenty-server/src/engine/core-modules/auth/auth.module.ts

@@ -30,9 +30,9 @@ import { FeatureFlag } from 'src/engine/core-modules/feature-flag/feature-flag.e
 import { FeatureFlagModule } from 'src/engine/core-modules/feature-flag/feature-flag.module';
 import { FileUploadModule } from 'src/engine/core-modules/file/file-upload/file-upload.module';
 import { GuardRedirectModule } from 'src/engine/core-modules/guard-redirect/guard-redirect.module';
-import { HealthModule } from 'src/engine/core-modules/health/health.module';
 import { JwtModule } from 'src/engine/core-modules/jwt/jwt.module';
 import { KeyValuePair } from 'src/engine/core-modules/key-value-pair/key-value-pair.entity';
+import { MetricsModule } from 'src/engine/core-modules/metrics/metrics.module';
 import { OnboardingModule } from 'src/engine/core-modules/onboarding/onboarding.module';
 import { WorkspaceSSOModule } from 'src/engine/core-modules/sso/sso.module';
 import { WorkspaceSSOIdentityProvider } from 'src/engine/core-modules/sso/workspace-sso-identity-provider.entity';
@@ -90,7 +90,7 @@ import { JwtAuthStrategy } from './strategies/jwt.auth.strategy';
     WorkspaceInvitationModule,
     EmailVerificationModule,
     GuardRedirectModule,
-    HealthModule,
+    MetricsModule,
     PermissionsModule,
     UserRoleModule,
   ],

packages/twenty-server/src/engine/core-modules/captcha/captcha.guard.ts

@@ -7,13 +7,14 @@ import {
 import { GqlExecutionContext } from '@nestjs/graphql';
 
 import { CaptchaService } from 'src/engine/core-modules/captcha/captcha.service';
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
+import { MetricsService } from 'src/engine/core-modules/metrics/metrics.service';
+import { MetricsKeys } from 'src/engine/core-modules/metrics/types/metrics-keys.type';
 
 @Injectable()
 export class CaptchaGuard implements CanActivate {
   constructor(
     private captchaService: CaptchaService,
-    private healthCacheService: HealthCacheService,
+    private metricsService: MetricsService,
   ) {}
 
   async canActivate(context: ExecutionContext): Promise<boolean> {
@@ -26,7 +27,10 @@ export class CaptchaGuard implements CanActivate {
     if (result.success) {
       return true;
     } else {
-      await this.healthCacheService.updateInvalidCaptchaCache(token);
+      await this.metricsService.incrementCounter({
+        key: MetricsKeys.InvalidCaptcha,
+        eventId: token,
+      });
 
       throw new BadRequestException(
         'Invalid Captcha, please try another device',

packages/twenty-server/src/engine/core-modules/environment/constants/environment-variables-group-metadata.ts

@@ -54,61 +54,67 @@ export const ENVIRONMENT_VARIABLES_GROUP_METADATA: Record<
       'By default, exceptions are sent to the logs. This should be enough for most self-hosting use-cases. For our cloud app we use Sentry.',
     isHiddenOnLoad: true,
   },
-  [EnvironmentVariablesGroup.Other]: {
+  [EnvironmentVariablesGroup.Metering]: {
     position: 900,
+    description:
+      'By default, metrics are sent to the console. OpenTelemetry collector can be set up for self-hosting use-cases.',
+    isHiddenOnLoad: true,
+  },
+  [EnvironmentVariablesGroup.Other]: {
+    position: 1000,
     description:
       "The variables in this section are mostly used for internal purposes (running our Cloud offering), but shouldn't usually be required for a simple self-hosted instance",
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.BillingConfig]: {
-    position: 1000,
+    position: 1100,
     description:
       'We use Stripe in our Cloud app to charge customers. Not relevant to Self-hosters.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.CaptchaConfig]: {
-    position: 1100,
+    position: 1200,
     description:
       'This protects critical endpoints like login and signup with a captcha to prevent bot attacks. Likely unnecessary for self-hosting scenarios.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.CloudflareConfig]: {
-    position: 1200,
+    position: 1300,
     description: '',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.LLM]: {
-    position: 1300,
+    position: 1400,
     description:
       'Configure the LLM provider and model to use for the app. This is experimental and not linked to any public feature.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.ServerlessConfig]: {
-    position: 1400,
+    position: 1500,
     description:
       'In our multi-tenant cloud app, we offload untrusted custom code from workflows to a serverless system (Lambda) for enhanced security and scalability. Self-hosters with a single tenant can typically ignore this configuration.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.SSL]: {
-    position: 1500,
+    position: 1600,
     description:
       'Configure this if you want to setup SSL on your server or full end-to-end encryption. If you just want basic HTTPS, a simple setup like Cloudflare in flexible mode might be easier.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.SupportChatConfig]: {
-    position: 1600,
+    position: 1700,
     description:
       'We use this to setup a small support chat on the bottom left. Currently powered by Front.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.AnalyticsConfig]: {
-    position: 1700,
+    position: 1800,
     description:
       'We’re running a test to perform analytics within the app. This will evolve.',
     isHiddenOnLoad: true,
   },
   [EnvironmentVariablesGroup.TokensDuration]: {
-    position: 1800,
+    position: 1900,
     description:
       'These have been set to sensible default so you probably don’t need to change them unless you have a specific use-case.',
     isHiddenOnLoad: true,

packages/twenty-server/src/engine/core-modules/environment/decorators/cast-to-meter-driver.decorator.ts

@@ -0,0 +1,21 @@
+import { Transform } from 'class-transformer';
+
+import { MeterDriver } from 'src/engine/core-modules/metrics/types/meter-driver.type';
+
+export const CastToMeterDriverArray = () =>
+  Transform(({ value }: { value: string }) => toMeterDriverArray(value));
+
+const toMeterDriverArray = (value: string | undefined) => {
+  if (typeof value === 'string') {
+    const rawMeterDrivers = value.split(',').map((driver) => driver.trim());
+    const isInvalid = rawMeterDrivers.some(
+      (driver) => !Object.values(MeterDriver).includes(driver as MeterDriver),
+    );
+
+    if (!isInvalid) {
+      return rawMeterDrivers;
+    }
+  }
+
+  return undefined;
+};

packages/twenty-server/src/engine/core-modules/environment/enums/environment-variables-group.enum.ts

@@ -6,6 +6,7 @@ export enum EnvironmentVariablesGroup {
   MicrosoftAuth = 'microsoft-auth',
   EmailSettings = 'email-settings',
   Logging = 'logging',
+  Metering = 'metering',
   ExceptionHandler = 'exception-handler',
   Other = 'other',
   BillingConfig = 'billing-config',

packages/twenty-server/src/engine/core-modules/environment/environment-variables.ts

@@ -25,6 +25,7 @@ import { LLMTracingDriver } from 'src/engine/core-modules/llm-tracing/interfaces
 import { CaptchaDriverType } from 'src/engine/core-modules/captcha/interfaces';
 import { CastToBoolean } from 'src/engine/core-modules/environment/decorators/cast-to-boolean.decorator';
 import { CastToLogLevelArray } from 'src/engine/core-modules/environment/decorators/cast-to-log-level-array.decorator';
+import { CastToMeterDriverArray } from 'src/engine/core-modules/environment/decorators/cast-to-meter-driver.decorator';
 import { CastToPositiveNumber } from 'src/engine/core-modules/environment/decorators/cast-to-positive-number.decorator';
 import { EnvironmentVariablesMetadata } from 'src/engine/core-modules/environment/decorators/environment-variables-metadata.decorator';
 import { IsAWSRegion } from 'src/engine/core-modules/environment/decorators/is-aws-region.decorator';
@@ -36,6 +37,7 @@ import { EnvironmentVariablesGroup } from 'src/engine/core-modules/environment/e
 import { ExceptionHandlerDriver } from 'src/engine/core-modules/exception-handler/interfaces';
 import { StorageDriverType } from 'src/engine/core-modules/file-storage/interfaces';
 import { LoggerDriverType } from 'src/engine/core-modules/logger/interfaces';
+import { MeterDriver } from 'src/engine/core-modules/metrics/types/meter-driver.type';
 import { ServerlessDriverType } from 'src/engine/core-modules/serverless/serverless.interface';
 
 export class EnvironmentVariables {
@@ -585,6 +587,22 @@ export class EnvironmentVariables {
   @IsOptional()
   LOG_LEVELS: LogLevel[] = ['log', 'error', 'warn'];
 
+  @EnvironmentVariablesMetadata({
+    group: EnvironmentVariablesGroup.Metering,
+    description: 'Driver used for collect metrics (OpenTelemetry or Console)',
+  })
+  @CastToMeterDriverArray()
+  @IsOptional()
+  METER_DRIVER: MeterDriver[] = [MeterDriver.Console];
+
+  @EnvironmentVariablesMetadata({
+    group: EnvironmentVariablesGroup.Metering,
+    description: 'Endpoint URL for the OpenTelemetry collector',
+  })
+  @ValidateIf((env) => env.METER_DRIVER.includes(MeterDriver.OpenTelemetry))
+  @IsOptional()
+  OTLP_COLLECTOR_ENDPOINT_URL: string;
+
   @EnvironmentVariablesMetadata({
     group: EnvironmentVariablesGroup.ExceptionHandler,
     description: 'Driver used for logging (only console for now)',

packages/twenty-server/src/engine/core-modules/health/controllers/__tests__/metrics.controller.spec.ts

@@ -1,30 +0,0 @@
-import { Test, TestingModule } from '@nestjs/testing';
-
-import { MetricsController } from 'src/engine/core-modules/health/controllers/metrics.controller';
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
-
-describe('MetricsController', () => {
-  let metricsController: MetricsController;
-
-  beforeEach(async () => {
-    const testingModule: TestingModule = await Test.createTestingModule({
-      controllers: [MetricsController],
-      providers: [
-        {
-          provide: HealthCacheService,
-          useValue: {
-            getMessageChannelSyncJobByStatusCounter: jest.fn(),
-            getCalendarChannelSyncJobByStatusCounter: jest.fn(),
-            getInvalidCaptchaCounter: jest.fn(),
-          },
-        },
-      ],
-    }).compile();
-
-    metricsController = testingModule.get<MetricsController>(MetricsController);
-  });
-
-  it('should be defined', () => {
-    expect(metricsController).toBeDefined();
-  });
-});

packages/twenty-server/src/engine/core-modules/health/controllers/metrics.controller.ts

@@ -1,28 +0,0 @@
-import { Controller, Get } from '@nestjs/common';
-
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
-import { HealthCounterCacheKeys } from 'src/engine/core-modules/health/types/health-counter-cache-keys.type';
-
-@Controller('metrics')
-export class MetricsController {
-  constructor(private readonly healthCacheService: HealthCacheService) {}
-
-  @Get('/message-channel-sync-job-by-status-counter')
-  getMessageChannelSyncJobByStatusCounter() {
-    return this.healthCacheService.countChannelSyncJobByStatus(
-      HealthCounterCacheKeys.MessageChannelSyncJobByStatus,
-    );
-  }
-
-  @Get('/invalid-captcha-counter')
-  getInvalidCaptchaCounter() {
-    return this.healthCacheService.getInvalidCaptchaCounter();
-  }
-
-  @Get('/calendar-channel-sync-job-by-status-counter')
-  getCalendarChannelSyncJobByStatusCounter() {
-    return this.healthCacheService.countChannelSyncJobByStatus(
-      HealthCounterCacheKeys.CalendarEventSyncJobByStatus,
-    );
-  }
-}

packages/twenty-server/src/engine/core-modules/health/health-cache.service.ts

@@ -1,139 +0,0 @@
-import { Injectable } from '@nestjs/common';
-
-import { InjectCacheStorage } from 'src/engine/core-modules/cache-storage/decorators/cache-storage.decorator';
-import { CacheStorageService } from 'src/engine/core-modules/cache-storage/services/cache-storage.service';
-import { CacheStorageNamespace } from 'src/engine/core-modules/cache-storage/types/cache-storage-namespace.enum';
-import { EnvironmentService } from 'src/engine/core-modules/environment/environment.service';
-import { AccountSyncJobByStatusCounter } from 'src/engine/core-modules/health/types/account-sync-metrics.types';
-import { HealthCounterCacheKeys } from 'src/engine/core-modules/health/types/health-counter-cache-keys.type';
-import { CalendarChannelSyncStatus } from 'src/modules/calendar/common/standard-objects/calendar-channel.workspace-entity';
-import { MessageChannelSyncStatus } from 'src/modules/messaging/common/standard-objects/message-channel.workspace-entity';
-
-const CACHE_BUCKET_DURATION_MS = 15000; // 15 seconds window for each cache bucket
-
-@Injectable()
-export class HealthCacheService {
-  private readonly healthMetricsTimeWindowInMinutes: number;
-  private readonly healthCacheTtl: number;
-
-  constructor(
-    @InjectCacheStorage(CacheStorageNamespace.EngineHealth)
-    private readonly cacheStorage: CacheStorageService,
-    private readonly environmentService: EnvironmentService,
-  ) {
-    this.healthMetricsTimeWindowInMinutes = this.environmentService.get(
-      'HEALTH_METRICS_TIME_WINDOW_IN_MINUTES',
-    );
-    this.healthCacheTtl = this.healthMetricsTimeWindowInMinutes * 60000 * 2;
-  }
-
-  private getCacheBucketStartTimestamp(timestamp: number): number {
-    return (
-      Math.floor(timestamp / CACHE_BUCKET_DURATION_MS) *
-      CACHE_BUCKET_DURATION_MS
-    );
-  }
-
-  private getCacheKeyWithTimestamp(key: string, timestamp?: number): string {
-    const currentIntervalTimestamp =
-      timestamp ?? this.getCacheBucketStartTimestamp(Date.now());
-
-    return `${key}:${currentIntervalTimestamp}`;
-  }
-
-  private getLastCacheBucketStartTimestampsFromDate(
-    cacheBucketsCount: number,
-    date: number = Date.now(),
-  ): number[] {
-    const currentIntervalTimestamp = this.getCacheBucketStartTimestamp(date);
-
-    return Array.from(
-      { length: cacheBucketsCount },
-      (_, i) => currentIntervalTimestamp - i * CACHE_BUCKET_DURATION_MS,
-    );
-  }
-
-  async updateMessageOrCalendarChannelSyncJobByStatusCache(
-    key: HealthCounterCacheKeys,
-    status: MessageChannelSyncStatus | CalendarChannelSyncStatus,
-    messageChannelIds: string[],
-  ) {
-    return await this.cacheStorage.setAdd(
-      this.getCacheKeyWithTimestamp(`${key}:${status}`),
-      messageChannelIds,
-      this.healthCacheTtl,
-    );
-  }
-
-  async countChannelSyncJobByStatus(
-    key:
-      | HealthCounterCacheKeys.MessageChannelSyncJobByStatus
-      | HealthCounterCacheKeys.CalendarEventSyncJobByStatus,
-    timeWindowInSeconds: number = this.healthMetricsTimeWindowInMinutes * 60,
-  ): Promise<AccountSyncJobByStatusCounter> {
-    if ((timeWindowInSeconds * 1000) % CACHE_BUCKET_DURATION_MS !== 0) {
-      throw new Error(
-        `Time window must be divisible by ${CACHE_BUCKET_DURATION_MS}`,
-      );
-    }
-
-    const now = Date.now();
-    const countByStatus = {} as AccountSyncJobByStatusCounter;
-    const statuses =
-      key === HealthCounterCacheKeys.MessageChannelSyncJobByStatus
-        ? Object.values(MessageChannelSyncStatus).filter(
-            (status) => status !== MessageChannelSyncStatus.ONGOING,
-          )
-        : Object.values(CalendarChannelSyncStatus).filter(
-            (status) => status !== CalendarChannelSyncStatus.ONGOING,
-          );
-
-    const cacheBuckets =
-      timeWindowInSeconds / (CACHE_BUCKET_DURATION_MS / 1000);
-
-    for (const status of statuses) {
-      const cacheKeys = this.computeTimeStampedCacheKeys(
-        `${key}:${status}`,
-        cacheBuckets,
-        now,
-      );
-
-      const channelIdsCount =
-        await this.cacheStorage.countAllSetMembers(cacheKeys);
-
-      countByStatus[status] = channelIdsCount;
-    }
-
-    return countByStatus;
-  }
-
-  computeTimeStampedCacheKeys(
-    key: string,
-    cacheBucketsCount: number,
-    date: number = Date.now(),
-  ) {
-    return this.getLastCacheBucketStartTimestampsFromDate(
-      cacheBucketsCount,
-      date,
-    ).map((timestamp) => this.getCacheKeyWithTimestamp(key, timestamp));
-  }
-
-  async updateInvalidCaptchaCache(captchaToken: string) {
-    return await this.cacheStorage.setAdd(
-      this.getCacheKeyWithTimestamp(HealthCounterCacheKeys.InvalidCaptcha),
-      [captchaToken],
-      this.healthCacheTtl,
-    );
-  }
-
-  async getInvalidCaptchaCounter(
-    timeWindowInSeconds: number = this.healthMetricsTimeWindowInMinutes * 60,
-  ) {
-    return await this.cacheStorage.countAllSetMembers(
-      this.computeTimeStampedCacheKeys(
-        HealthCounterCacheKeys.InvalidCaptcha,
-        timeWindowInSeconds / (CACHE_BUCKET_DURATION_MS / 1000),
-      ),
-    );
-  }
-}

packages/twenty-server/src/engine/core-modules/health/health.module.ts

@@ -3,14 +3,12 @@ import { TerminusModule } from '@nestjs/terminus';
 import { TypeOrmModule } from '@nestjs/typeorm';
 
 import { HealthController } from 'src/engine/core-modules/health/controllers/health.controller';
-import { MetricsController } from 'src/engine/core-modules/health/controllers/metrics.controller';
 import { AppHealthIndicator } from 'src/engine/core-modules/health/indicators/app.health';
+import { MetricsModule } from 'src/engine/core-modules/metrics/metrics.module';
 import { RedisClientModule } from 'src/engine/core-modules/redis-client/redis-client.module';
 import { Workspace } from 'src/engine/core-modules/workspace/workspace.entity';
 import { WorkspaceMigrationModule } from 'src/engine/metadata-modules/workspace-migration/workspace-migration.module';
 
-import { HealthCacheService } from './health-cache.service';
-
 import { ConnectedAccountHealth } from './indicators/connected-account.health';
 import { DatabaseHealthIndicator } from './indicators/database.health';
 import { RedisHealthIndicator } from './indicators/redis.health';
@@ -21,10 +19,10 @@ import { WorkerHealthIndicator } from './indicators/worker.health';
     RedisClientModule,
     WorkspaceMigrationModule,
     TypeOrmModule.forFeature([Workspace], 'core'),
+    MetricsModule,
   ],
-  controllers: [HealthController, MetricsController],
+  controllers: [HealthController],
   providers: [
-    HealthCacheService,
     DatabaseHealthIndicator,
     RedisHealthIndicator,
     WorkerHealthIndicator,
@@ -32,7 +30,6 @@ import { WorkerHealthIndicator } from './indicators/worker.health';
     AppHealthIndicator,
   ],
   exports: [
-    HealthCacheService,
     DatabaseHealthIndicator,
     RedisHealthIndicator,
     WorkerHealthIndicator,

packages/twenty-server/src/engine/core-modules/health/indicators/__tests__/connected-account.health.spec.ts

@@ -4,19 +4,19 @@ import { Test, TestingModule } from '@nestjs/testing';
 import { HEALTH_ERROR_MESSAGES } from 'src/engine/core-modules/health/constants/health-error-messages.constants';
 import { HEALTH_INDICATORS_TIMEOUT } from 'src/engine/core-modules/health/constants/health-indicators-timeout.conts';
 import { METRICS_FAILURE_RATE_THRESHOLD } from 'src/engine/core-modules/health/constants/metrics-failure-rate-threshold.const';
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
 import { ConnectedAccountHealth } from 'src/engine/core-modules/health/indicators/connected-account.health';
+import { MetricsService } from 'src/engine/core-modules/metrics/metrics.service';
 import { CalendarChannelSyncStatus } from 'src/modules/calendar/common/standard-objects/calendar-channel.workspace-entity';
 import { MessageChannelSyncStatus } from 'src/modules/messaging/common/standard-objects/message-channel.workspace-entity';
 
 describe('ConnectedAccountHealth', () => {
   let service: ConnectedAccountHealth;
-  let healthCacheService: jest.Mocked<HealthCacheService>;
+  let metricsService: jest.Mocked<MetricsService>;
   let healthIndicatorService: jest.Mocked<HealthIndicatorService>;
 
   beforeEach(async () => {
-    healthCacheService = {
+    metricsService = {
-      countChannelSyncJobByStatus: jest.fn(),
+      groupMetrics: jest.fn(),
     } as any;
 
     healthIndicatorService = {
@@ -41,8 +41,8 @@ describe('ConnectedAccountHealth', () => {
       providers: [
         ConnectedAccountHealth,
         {
-          provide: HealthCacheService,
+          provide: MetricsService,
-          useValue: healthCacheService,
+          useValue: metricsService,
         },
         {
           provide: HealthIndicatorService,
@@ -64,7 +64,7 @@ describe('ConnectedAccountHealth', () => {
 
   describe('message sync health', () => {
     it('should return up status when no message sync jobs are present', async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 0,
@@ -92,7 +92,7 @@ describe('ConnectedAccountHealth', () => {
     });
 
     it(`should return down status when message sync failure rate is above ${METRICS_FAILURE_RATE_THRESHOLD}%`, async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 1,
@@ -122,7 +122,7 @@ describe('ConnectedAccountHealth', () => {
 
   describe('calendar sync health', () => {
     it('should return up status when no calendar sync jobs are present', async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 0,
@@ -150,7 +150,7 @@ describe('ConnectedAccountHealth', () => {
     });
 
     it(`should return down status when calendar sync failure rate is above ${METRICS_FAILURE_RATE_THRESHOLD}%`, async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 1,
@@ -180,7 +180,7 @@ describe('ConnectedAccountHealth', () => {
 
   describe('timeout handling', () => {
     it('should handle message sync timeout', async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce(
           new Promise((resolve) =>
             setTimeout(resolve, HEALTH_INDICATORS_TIMEOUT + 100),
@@ -207,7 +207,7 @@ describe('ConnectedAccountHealth', () => {
     });
 
     it('should handle calendar sync timeout', async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 1,
@@ -236,7 +236,7 @@ describe('ConnectedAccountHealth', () => {
 
   describe('combined health check', () => {
     it('should return combined status with both checks healthy', async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 8,
@@ -256,7 +256,7 @@ describe('ConnectedAccountHealth', () => {
     });
 
     it('should return down status when both syncs fail', async () => {
-      healthCacheService.countChannelSyncJobByStatus
+      metricsService.groupMetrics
         .mockResolvedValueOnce({
           [MessageChannelSyncStatus.NOT_SYNCED]: 0,
           [MessageChannelSyncStatus.ACTIVE]: 1,

packages/twenty-server/src/engine/core-modules/health/indicators/connected-account.health.ts

@@ -6,15 +6,17 @@ import {
 
 import { HEALTH_ERROR_MESSAGES } from 'src/engine/core-modules/health/constants/health-error-messages.constants';
 import { METRICS_FAILURE_RATE_THRESHOLD } from 'src/engine/core-modules/health/constants/metrics-failure-rate-threshold.const';
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
-import { HealthCounterCacheKeys } from 'src/engine/core-modules/health/types/health-counter-cache-keys.type';
 import { withHealthCheckTimeout } from 'src/engine/core-modules/health/utils/health-check-timeout.util';
-
+import {
+  CALENDAR_SYNC_METRICS_BY_STATUS,
+  MESSAGE_SYNC_METRICS_BY_STATUS,
+} from 'src/engine/core-modules/metrics/constants/account-sync-metrics-by-status.constant';
+import { MetricsService } from 'src/engine/core-modules/metrics/metrics.service';
 @Injectable()
 export class ConnectedAccountHealth {
   constructor(
     private readonly healthIndicatorService: HealthIndicatorService,
-    private readonly healthCacheService: HealthCacheService,
+    private readonly metricsService: MetricsService,
   ) {}
 
   private async checkMessageSyncHealth(): Promise<HealthIndicatorResult> {
@@ -22,9 +24,7 @@ export class ConnectedAccountHealth {
 
     try {
       const counters = await withHealthCheckTimeout(
-        this.healthCacheService.countChannelSyncJobByStatus(
+        this.metricsService.groupMetrics(MESSAGE_SYNC_METRICS_BY_STATUS),
-          HealthCounterCacheKeys.MessageChannelSyncJobByStatus,
-        ),
         HEALTH_ERROR_MESSAGES.MESSAGE_SYNC_TIMEOUT,
       );
 
@@ -73,9 +73,7 @@ export class ConnectedAccountHealth {
 
     try {
       const counters = await withHealthCheckTimeout(
-        this.healthCacheService.countChannelSyncJobByStatus(
+        this.metricsService.groupMetrics(CALENDAR_SYNC_METRICS_BY_STATUS),
-          HealthCounterCacheKeys.CalendarEventSyncJobByStatus,
-        ),
         HEALTH_ERROR_MESSAGES.CALENDAR_SYNC_TIMEOUT,
       );
 

packages/twenty-server/src/engine/core-modules/health/types/health-counter-cache-keys.type.ts

@@ -1,5 +0,0 @@
-export enum HealthCounterCacheKeys {
-  MessageChannelSyncJobByStatus = 'message-channel-sync-job-by-status',
-  InvalidCaptcha = 'invalid-captcha',
-  CalendarEventSyncJobByStatus = 'calendar-event-sync-job-by-status',
-}

packages/twenty-server/src/engine/core-modules/metrics/constants/account-sync-metrics-by-status.constant.ts

@@ -0,0 +1,31 @@
+import { MetricsKeys } from 'src/engine/core-modules/metrics/types/metrics-keys.type';
+
+export const MESSAGE_SYNC_METRICS_BY_STATUS = [
+  {
+    name: 'ACTIVE',
+    cacheKey: MetricsKeys.MessageChannelSyncJobActive,
+  },
+  {
+    name: 'FAILED_UNKNOWN',
+    cacheKey: MetricsKeys.MessageChannelSyncJobFailedUnknown,
+  },
+  {
+    name: 'FAILED_INSUFFICIENT_PERMISSIONS',
+    cacheKey: MetricsKeys.MessageChannelSyncJobFailedInsufficientPermissions,
+  },
+];
+
+export const CALENDAR_SYNC_METRICS_BY_STATUS = [
+  {
+    name: 'ACTIVE',
+    cacheKey: MetricsKeys.CalendarEventSyncJobActive,
+  },
+  {
+    name: 'FAILED_UNKNOWN',
+    cacheKey: MetricsKeys.CalendarEventSyncJobFailedUnknown,
+  },
+  {
+    name: 'FAILED_INSUFFICIENT_PERMISSIONS',
+    cacheKey: MetricsKeys.CalendarEventSyncJobFailedInsufficientPermissions,
+  },
+];

packages/twenty-server/src/engine/core-modules/metrics/metrics-cache.service.ts

@@ -0,0 +1,94 @@
+import { Injectable } from '@nestjs/common';
+
+import { InjectCacheStorage } from 'src/engine/core-modules/cache-storage/decorators/cache-storage.decorator';
+import { CacheStorageService } from 'src/engine/core-modules/cache-storage/services/cache-storage.service';
+import { CacheStorageNamespace } from 'src/engine/core-modules/cache-storage/types/cache-storage-namespace.enum';
+import { EnvironmentService } from 'src/engine/core-modules/environment/environment.service';
+import { MetricsKeys } from 'src/engine/core-modules/metrics/types/metrics-keys.type';
+
+const CACHE_BUCKET_DURATION_MS = 15000; // 15 seconds window for each cache bucket
+
+@Injectable()
+export class MetricsCacheService {
+  private readonly healthMetricsTimeWindowInMinutes: number;
+  private readonly healthCacheTtl: number;
+
+  constructor(
+    @InjectCacheStorage(CacheStorageNamespace.EngineHealth)
+    private readonly cacheStorage: CacheStorageService,
+    private readonly environmentService: EnvironmentService,
+  ) {
+    this.healthMetricsTimeWindowInMinutes = this.environmentService.get(
+      'HEALTH_METRICS_TIME_WINDOW_IN_MINUTES',
+    );
+    this.healthCacheTtl = this.healthMetricsTimeWindowInMinutes * 60000 * 2;
+  }
+
+  private getCacheBucketStartTimestamp(timestamp: number): number {
+    return (
+      Math.floor(timestamp / CACHE_BUCKET_DURATION_MS) *
+      CACHE_BUCKET_DURATION_MS
+    );
+  }
+
+  private getCacheKeyWithTimestamp(key: string, timestamp?: number): string {
+    const currentIntervalTimestamp =
+      timestamp ?? this.getCacheBucketStartTimestamp(Date.now());
+
+    return `${key}:${currentIntervalTimestamp}`;
+  }
+
+  private getLastCacheBucketStartTimestampsFromDate(
+    cacheBucketsCount: number,
+    date: number,
+  ): number[] {
+    const currentIntervalTimestamp = this.getCacheBucketStartTimestamp(date);
+
+    return Array.from(
+      { length: cacheBucketsCount },
+      (_, i) => currentIntervalTimestamp - i * CACHE_BUCKET_DURATION_MS,
+    );
+  }
+
+  async updateCounter(key: MetricsKeys, items: string[]) {
+    return await this.cacheStorage.setAdd(
+      this.getCacheKeyWithTimestamp(key),
+      items,
+      this.healthCacheTtl,
+    );
+  }
+
+  async computeCount({
+    key,
+    timeWindowInSeconds = this.healthMetricsTimeWindowInMinutes * 60,
+    date = Date.now(),
+  }: {
+    key: MetricsKeys;
+    timeWindowInSeconds?: number;
+    date?: number;
+  }): Promise<number> {
+    if ((timeWindowInSeconds * 1000) % CACHE_BUCKET_DURATION_MS !== 0) {
+      throw new Error(
+        `Time window must be divisible by ${CACHE_BUCKET_DURATION_MS}`,
+      );
+    }
+
+    const cacheBuckets =
+      timeWindowInSeconds / (CACHE_BUCKET_DURATION_MS / 1000);
+
+    const cacheKeys = this.computeTimeStampedCacheKeys(key, cacheBuckets, date);
+
+    return await this.cacheStorage.countAllSetMembers(cacheKeys);
+  }
+
+  computeTimeStampedCacheKeys(
+    key: string,
+    cacheBucketsCount: number,
+    date: number,
+  ) {
+    return this.getLastCacheBucketStartTimestampsFromDate(
+      cacheBucketsCount,
+      date,
+    ).map((timestamp) => this.getCacheKeyWithTimestamp(key, timestamp));
+  }
+}

packages/twenty-server/src/engine/core-modules/metrics/metrics.module.ts

@@ -0,0 +1,10 @@
+import { Module } from '@nestjs/common';
+
+import { MetricsCacheService } from 'src/engine/core-modules/metrics/metrics-cache.service';
+import { MetricsService } from 'src/engine/core-modules/metrics/metrics.service';
+
+@Module({
+  providers: [MetricsService, MetricsCacheService],
+  exports: [MetricsService, MetricsCacheService],
+})
+export class MetricsModule {}

packages/twenty-server/src/engine/core-modules/metrics/metrics.service.ts

@@ -0,0 +1,70 @@
+import { Injectable } from '@nestjs/common';
+
+import { metrics } from '@opentelemetry/api';
+
+import { MetricsCacheService } from 'src/engine/core-modules/metrics/metrics-cache.service';
+import { MetricsKeys } from 'src/engine/core-modules/metrics/types/metrics-keys.type';
+
+@Injectable()
+export class MetricsService {
+  constructor(private readonly metricsCacheService: MetricsCacheService) {}
+
+  async incrementCounter({
+    key,
+    eventId,
+    shouldStoreInCache = true,
+  }: {
+    key: MetricsKeys;
+    eventId: string;
+    shouldStoreInCache?: boolean;
+  }) {
+    //TODO : Define meter name usage in monitoring
+    const meter = metrics.getMeter('twenty-server');
+    const counter = meter.createCounter(key);
+
+    counter.add(1);
+
+    if (shouldStoreInCache) {
+      this.metricsCacheService.updateCounter(key, [eventId]);
+    }
+  }
+
+  async batchIncrementCounter({
+    key,
+    eventIds,
+    shouldStoreInCache = true,
+  }: {
+    key: MetricsKeys;
+    eventIds: string[];
+    shouldStoreInCache?: boolean;
+  }) {
+    //TODO : Define meter name usage in monitoring
+    const meter = metrics.getMeter('twenty-server');
+    const counter = meter.createCounter(key);
+
+    counter.add(eventIds.length);
+
+    if (shouldStoreInCache) {
+      this.metricsCacheService.updateCounter(key, eventIds);
+    }
+  }
+
+  async groupMetrics(
+    metrics: { name: string; cacheKey: MetricsKeys }[],
+  ): Promise<Record<string, number>> {
+    const groupedMetrics: Record<string, number> = {};
+
+    const date = Date.now();
+
+    for (const metric of metrics) {
+      const metricValue = await this.metricsCacheService.computeCount({
+        key: metric.cacheKey,
+        date,
+      });
+
+      groupedMetrics[metric.name] = metricValue;
+    }
+
+    return groupedMetrics;
+  }
+}

packages/twenty-server/src/engine/core-modules/metrics/types/meter-driver.type.ts

@@ -0,0 +1,4 @@
+export enum MeterDriver {
+  OpenTelemetry = 'opentelemetry',
+  Console = 'console',
+}

packages/twenty-server/src/engine/core-modules/metrics/types/metrics-keys.type.ts

@@ -0,0 +1,9 @@
+export enum MetricsKeys {
+  MessageChannelSyncJobActive = 'message-channel-sync-job/active',
+  MessageChannelSyncJobFailedInsufficientPermissions = 'message-channel-sync-job/failed-insufficient-permissions',
+  MessageChannelSyncJobFailedUnknown = 'message-channel-sync-job/failed-unknown',
+  CalendarEventSyncJobActive = 'calendar-event-sync-job/active',
+  CalendarEventSyncJobFailedInsufficientPermissions = 'calendar-event-sync-job/failed-insufficient-permissions',
+  CalendarEventSyncJobFailedUnknown = 'calendar-event-sync-job/failed-unknown',
+  InvalidCaptcha = 'invalid-captcha',
+}

packages/twenty-server/src/instrument.ts

@@ -1,10 +1,27 @@
-import * as Sentry from '@sentry/nestjs';
+import process from 'process';
+
+import opentelemetry from '@opentelemetry/api';
+import { OTLPMetricExporter } from '@opentelemetry/exporter-metrics-otlp-http';
+import {
+  ConsoleMetricExporter,
+  MeterProvider,
+  PeriodicExportingMetricReader,
+} from '@opentelemetry/sdk-metrics';
+import * as Sentry from '@sentry/node';
 import { nodeProfilingIntegration } from '@sentry/profiling-node';
 
 import { NodeEnvironment } from 'src/engine/core-modules/environment/interfaces/node-environment.interface';
 
 import { ExceptionHandlerDriver } from 'src/engine/core-modules/exception-handler/interfaces';
+import { MeterDriver } from 'src/engine/core-modules/metrics/types/meter-driver.type';
 import { WorkspaceCacheKeys } from 'src/engine/workspace-cache-storage/workspace-cache-storage.service';
+import { parseArrayEnvVar } from 'src/utils/parse-array-env-var';
+
+const meterDrivers = parseArrayEnvVar(
+  process.env.METER_DRIVER,
+  Object.values(MeterDriver),
+  [MeterDriver.Console],
+);
 
 if (process.env.EXCEPTION_HANDLER_DRIVER === ExceptionHandlerDriver.Sentry) {
   Sentry.init({
@@ -29,3 +46,34 @@ if (process.env.EXCEPTION_HANDLER_DRIVER === ExceptionHandlerDriver.Sentry) {
     debug: process.env.NODE_ENV === NodeEnvironment.development,
   });
 }
+
+// Meter setup
+
+const meterProvider = new MeterProvider({
+  readers: [
+    ...(meterDrivers.includes(MeterDriver.Console)
+      ? [
+          new PeriodicExportingMetricReader({
+            exporter: new ConsoleMetricExporter(),
+            exportIntervalMillis: 10000,
+          }),
+        ]
+      : []),
+    ...(meterDrivers.includes(MeterDriver.OpenTelemetry)
+      ? [
+          new PeriodicExportingMetricReader({
+            exporter: new OTLPMetricExporter({
+              url: process.env.OTLP_COLLECTOR_METRICS_ENDPOINT_URL,
+            }),
+            exportIntervalMillis: 10000,
+          }),
+        ]
+      : []),
+  ],
+});
+
+opentelemetry.metrics.setGlobalMeterProvider(meterProvider);
+
+process.on('SIGTERM', async () => {
+  await meterProvider.shutdown();
+});

packages/twenty-server/src/modules/calendar/calendar-event-import-manager/calendar-event-import-manager.module.ts

@@ -3,7 +3,7 @@ import { TypeOrmModule } from '@nestjs/typeorm';
 
 import { BillingModule } from 'src/engine/core-modules/billing/billing.module';
 import { FeatureFlag } from 'src/engine/core-modules/feature-flag/feature-flag.entity';
-import { HealthModule } from 'src/engine/core-modules/health/health.module';
+import { MetricsModule } from 'src/engine/core-modules/metrics/metrics.module';
 import { Workspace } from 'src/engine/core-modules/workspace/workspace.entity';
 import { DataSourceEntity } from 'src/engine/metadata-modules/data-source/data-source.entity';
 import { ObjectMetadataRepositoryModule } from 'src/engine/object-metadata-repository/object-metadata-repository.module';
@@ -50,7 +50,7 @@ import { WorkspaceMemberWorkspaceEntity } from 'src/modules/workspace-member/sta
     RefreshTokensManagerModule,
     ConnectedAccountModule,
     CalendarCommonModule,
-    HealthModule,
+    MetricsModule,
   ],
   providers: [
     CalendarChannelSyncStatusService,

packages/twenty-server/src/modules/calendar/common/calendar-common.module.ts

@@ -2,7 +2,7 @@ import { Module } from '@nestjs/common';
 import { TypeOrmModule } from '@nestjs/typeorm';
 
 import { FeatureFlag } from 'src/engine/core-modules/feature-flag/feature-flag.entity';
-import { HealthModule } from 'src/engine/core-modules/health/health.module';
+import { MetricsModule } from 'src/engine/core-modules/metrics/metrics.module';
 import { WorkspaceDataSourceModule } from 'src/engine/workspace-datasource/workspace-datasource.module';
 import { CalendarChannelSyncStatusService } from 'src/modules/calendar/common/services/calendar-channel-sync-status.service';
 import { ConnectedAccountModule } from 'src/modules/connected-account/connected-account.module';
@@ -12,7 +12,7 @@ import { ConnectedAccountModule } from 'src/modules/connected-account/connected-
     WorkspaceDataSourceModule,
     TypeOrmModule.forFeature([FeatureFlag], 'core'),
     ConnectedAccountModule,
-    HealthModule,
+    MetricsModule,
   ],
   providers: [CalendarChannelSyncStatusService],
   exports: [CalendarChannelSyncStatusService],

packages/twenty-server/src/modules/calendar/common/services/calendar-channel-sync-status.service.ts

@@ -5,8 +5,8 @@ import { Any } from 'typeorm';
 import { InjectCacheStorage } from 'src/engine/core-modules/cache-storage/decorators/cache-storage.decorator';
 import { CacheStorageService } from 'src/engine/core-modules/cache-storage/services/cache-storage.service';
 import { CacheStorageNamespace } from 'src/engine/core-modules/cache-storage/types/cache-storage-namespace.enum';
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
+import { MetricsService } from 'src/engine/core-modules/metrics/metrics.service';
-import { HealthCounterCacheKeys } from 'src/engine/core-modules/health/types/health-counter-cache-keys.type';
+import { MetricsKeys } from 'src/engine/core-modules/metrics/types/metrics-keys.type';
 import { TwentyORMManager } from 'src/engine/twenty-orm/twenty-orm.manager';
 import {
   CalendarChannelSyncStage,
@@ -24,7 +24,7 @@ export class CalendarChannelSyncStatusService {
     @InjectCacheStorage(CacheStorageNamespace.ModuleCalendar)
     private readonly cacheStorage: CacheStorageService,
     private readonly accountsToReconnectService: AccountsToReconnectService,
-    private readonly healthCacheService: HealthCacheService,
+    private readonly metricsService: MetricsService,
   ) {}
 
   public async scheduleFullCalendarEventListFetch(
@@ -179,11 +179,10 @@ export class CalendarChannelSyncStatusService {
 
     await this.schedulePartialCalendarEventListFetch(calendarChannelIds);
 
-    await this.healthCacheService.updateMessageOrCalendarChannelSyncJobByStatusCache(
+    await this.metricsService.batchIncrementCounter({
-      HealthCounterCacheKeys.CalendarEventSyncJobByStatus,
+      key: MetricsKeys.CalendarEventSyncJobActive,
-      CalendarChannelSyncStatus.ACTIVE,
+      eventIds: calendarChannelIds,
-      calendarChannelIds,
+    });
-    );
   }
 
   public async markAsFailedUnknownAndFlushCalendarEventsToImport(
@@ -210,11 +209,10 @@ export class CalendarChannelSyncStatusService {
       syncStage: CalendarChannelSyncStage.FAILED,
     });
 
-    await this.healthCacheService.updateMessageOrCalendarChannelSyncJobByStatusCache(
+    await this.metricsService.batchIncrementCounter({
-      HealthCounterCacheKeys.CalendarEventSyncJobByStatus,
+      key: MetricsKeys.CalendarEventSyncJobFailedUnknown,
-      CalendarChannelSyncStatus.FAILED_UNKNOWN,
+      eventIds: calendarChannelIds,
-      calendarChannelIds,
+    });
-    );
   }
 
   public async markAsFailedInsufficientPermissionsAndFlushCalendarEventsToImport(
@@ -266,11 +264,10 @@ export class CalendarChannelSyncStatusService {
       workspaceId,
     );
 
-    await this.healthCacheService.updateMessageOrCalendarChannelSyncJobByStatusCache(
+    await this.metricsService.batchIncrementCounter({
-      HealthCounterCacheKeys.CalendarEventSyncJobByStatus,
+      key: MetricsKeys.CalendarEventSyncJobFailedInsufficientPermissions,
-      CalendarChannelSyncStatus.FAILED_INSUFFICIENT_PERMISSIONS,
+      eventIds: calendarChannelIds,
-      calendarChannelIds,
+    });
-    );
   }
 
   private async addToAccountsToReconnect(

packages/twenty-server/src/modules/messaging/common/messaging-common.module.ts

@@ -2,7 +2,7 @@ import { Module } from '@nestjs/common';
 import { TypeOrmModule } from '@nestjs/typeorm';
 
 import { FeatureFlag } from 'src/engine/core-modules/feature-flag/feature-flag.entity';
-import { HealthModule } from 'src/engine/core-modules/health/health.module';
+import { MetricsModule } from 'src/engine/core-modules/metrics/metrics.module';
 import { WorkspaceDataSourceModule } from 'src/engine/workspace-datasource/workspace-datasource.module';
 import { ConnectedAccountModule } from 'src/modules/connected-account/connected-account.module';
 import { MessageChannelSyncStatusService } from 'src/modules/messaging/common/services/message-channel-sync-status.service';
@@ -12,7 +12,7 @@ import { MessageChannelSyncStatusService } from 'src/modules/messaging/common/se
     WorkspaceDataSourceModule,
     TypeOrmModule.forFeature([FeatureFlag], 'core'),
     ConnectedAccountModule,
-    HealthModule,
+    MetricsModule,
   ],
   providers: [MessageChannelSyncStatusService],
   exports: [MessageChannelSyncStatusService],

packages/twenty-server/src/modules/messaging/common/services/message-channel-sync-status.service.ts

@@ -5,8 +5,8 @@ import { Any } from 'typeorm';
 import { InjectCacheStorage } from 'src/engine/core-modules/cache-storage/decorators/cache-storage.decorator';
 import { CacheStorageService } from 'src/engine/core-modules/cache-storage/services/cache-storage.service';
 import { CacheStorageNamespace } from 'src/engine/core-modules/cache-storage/types/cache-storage-namespace.enum';
-import { HealthCacheService } from 'src/engine/core-modules/health/health-cache.service';
+import { MetricsService } from 'src/engine/core-modules/metrics/metrics.service';
-import { HealthCounterCacheKeys } from 'src/engine/core-modules/health/types/health-counter-cache-keys.type';
+import { MetricsKeys } from 'src/engine/core-modules/metrics/types/metrics-keys.type';
 import { TwentyORMManager } from 'src/engine/twenty-orm/twenty-orm.manager';
 import { AccountsToReconnectService } from 'src/modules/connected-account/services/accounts-to-reconnect.service';
 import { ConnectedAccountWorkspaceEntity } from 'src/modules/connected-account/standard-objects/connected-account.workspace-entity';
@@ -24,7 +24,7 @@ export class MessageChannelSyncStatusService {
     private readonly cacheStorage: CacheStorageService,
     private readonly twentyORMManager: TwentyORMManager,
     private readonly accountsToReconnectService: AccountsToReconnectService,
-    private readonly healthCacheService: HealthCacheService,
+    private readonly metricsService: MetricsService,
   ) {}
 
   public async scheduleFullMessageListFetch(messageChannelIds: string[]) {
@@ -152,11 +152,10 @@ export class MessageChannelSyncStatusService {
       syncedAt: new Date().toISOString(),
     });
 
-    await this.healthCacheService.updateMessageOrCalendarChannelSyncJobByStatusCache(
+    await this.metricsService.batchIncrementCounter({
-      HealthCounterCacheKeys.MessageChannelSyncJobByStatus,
+      key: MetricsKeys.MessageChannelSyncJobActive,
-      MessageChannelSyncStatus.ACTIVE,
+      eventIds: messageChannelIds,
-      messageChannelIds,
+    });
-    );
   }
 
   public async markAsMessagesImportOngoing(messageChannelIds: string[]) {
@@ -199,11 +198,10 @@ export class MessageChannelSyncStatusService {
       syncStatus: MessageChannelSyncStatus.FAILED_UNKNOWN,
     });
 
-    await this.healthCacheService.updateMessageOrCalendarChannelSyncJobByStatusCache(
+    await this.metricsService.batchIncrementCounter({
-      HealthCounterCacheKeys.MessageChannelSyncJobByStatus,
+      key: MetricsKeys.MessageChannelSyncJobFailedUnknown,
-      MessageChannelSyncStatus.FAILED_UNKNOWN,
+      eventIds: messageChannelIds,
-      messageChannelIds,
+    });
-    );
   }
 
   public async markAsFailedInsufficientPermissionsAndFlushMessagesToImport(
@@ -230,11 +228,10 @@ export class MessageChannelSyncStatusService {
       syncStatus: MessageChannelSyncStatus.FAILED_INSUFFICIENT_PERMISSIONS,
     });
 
-    await this.healthCacheService.updateMessageOrCalendarChannelSyncJobByStatusCache(
+    await this.metricsService.batchIncrementCounter({
-      HealthCounterCacheKeys.MessageChannelSyncJobByStatus,
+      key: MetricsKeys.MessageChannelSyncJobFailedInsufficientPermissions,
-      MessageChannelSyncStatus.FAILED_INSUFFICIENT_PERMISSIONS,
+      eventIds: messageChannelIds,
-      messageChannelIds,
+    });
-    );
 
     const connectedAccountRepository =
       await this.twentyORMManager.getRepository<ConnectedAccountWorkspaceEntity>(

packages/twenty-server/src/queue-worker/queue-worker.ts

@@ -3,8 +3,8 @@ import { NestFactory } from '@nestjs/core';
 import { ExceptionHandlerService } from 'src/engine/core-modules/exception-handler/exception-handler.service';
 import { LoggerService } from 'src/engine/core-modules/logger/logger.service';
 import { shouldFilterException } from 'src/engine/utils/global-exception-handler.util';
-import { QueueWorkerModule } from 'src/queue-worker/queue-worker.module';
 import 'src/instrument';
+import { QueueWorkerModule } from 'src/queue-worker/queue-worker.module';
 
 async function bootstrap() {
   let exceptionHandlerService: ExceptionHandlerService | undefined;

packages/twenty-server/src/utils/parse-array-env-var.ts

@@ -0,0 +1,13 @@
+export const parseArrayEnvVar = <T>(
+  envVar: string | undefined,
+  expectedValues: T[],
+  defaultValues: T[],
+): T[] => {
+  if (!envVar) return defaultValues;
+
+  const values = envVar
+    .split(',')
+    .filter((item) => expectedValues.includes(item as T)) as T[];
+
+  return values.length > 0 ? values : defaultValues;
+};

packages/twenty-website/src/content/developers/self-hosting/setup.mdx

@@ -279,7 +279,7 @@ yarn command:prod cron:calendar:ongoing-stale
   ['SERVERLESS_LAMBDA_SECRET_ACCESS_KEY', '', 'Optional depending on the authentication method'],
 ]}></ArticleTable>
 
-### Logging
+### Logging and Observability
 
 <ArticleTable options={[
     ['LOGGER_DRIVER', 'console', "Currently, only supports 'console'"],
@@ -290,6 +290,8 @@ yarn command:prod cron:calendar:ongoing-stale
     ['SENTRY_RELEASE', 'latest', 'The sentry release used if sentry logging driver is selected'],
     ['SENTRY_DSN', 'https://xxx@xxx.ingest.sentry.io/xxx', 'The sentry logging endpoint used if sentry logging driver is selected'],
     ['SENTRY_FRONT_DSN', 'https://xxx@xxx.ingest.sentry.io/xxx', 'The sentry logging endpoint used by the frontend if sentry logging driver is selected'],
+    ['METER_DRIVER', 'console', "The meter driver can be: 'console' and/or 'opentelemetry' "],
+    ['OTLP_COLLECTOR_ENDPOINT_URL', '', 'The OpenTelemetry collector endpoint collects metrics if opentelemetry meter driver is selected. The collector has to be set separately.'],
     ]}></ArticleTable>
 
 

yarn.lock

@@ -11885,6 +11885,15 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/api-logs@npm:0.200.0":
+  version: 0.200.0
+  resolution: "@opentelemetry/api-logs@npm:0.200.0"
+  dependencies:
+    "@opentelemetry/api": "npm:^1.3.0"
+  checksum: 10c0/c6bc3cfba35c69411f294519d93d0ff9f603517030d1162839ee42ac22ed1b0235edaf71d00cabc40125f813d8b4dc830d14315afcebcef138c1df560eaa5c91
+  languageName: node
+  linkType: hard
+
 "@opentelemetry/api-logs@npm:0.52.1":
   version: 0.52.1
   resolution: "@opentelemetry/api-logs@npm:0.52.1"
@@ -11903,7 +11912,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"@opentelemetry/api@npm:^1.0.0, @opentelemetry/api@npm:^1.8, @opentelemetry/api@npm:^1.9.0":
+"@opentelemetry/api@npm:^1.0.0, @opentelemetry/api@npm:^1.3.0, @opentelemetry/api@npm:^1.8, @opentelemetry/api@npm:^1.9.0":
   version: 1.9.0
   resolution: "@opentelemetry/api@npm:1.9.0"
   checksum: 10c0/9aae2fe6e8a3a3eeb6c1fdef78e1939cf05a0f37f8a4fae4d6bf2e09eb1e06f966ece85805626e01ba5fab48072b94f19b835449e58b6d26720ee19a58298add
@@ -11930,6 +11939,32 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/core@npm:2.0.0":
+  version: 2.0.0
+  resolution: "@opentelemetry/core@npm:2.0.0"
+  dependencies:
+    "@opentelemetry/semantic-conventions": "npm:^1.29.0"
+  peerDependencies:
+    "@opentelemetry/api": ">=1.0.0 <1.10.0"
+  checksum: 10c0/d2cc6d8a955305b9de15cc36135e5d5b0f0405fead8bbd4de51433f2d05369af0a3bcb2c6fe7fe6d9e61b0db782511bcadc5d93ed906027d4c00d5c2e3575a24
+  languageName: node
+  linkType: hard
+
+"@opentelemetry/exporter-metrics-otlp-http@npm:^0.200.0":
+  version: 0.200.0
+  resolution: "@opentelemetry/exporter-metrics-otlp-http@npm:0.200.0"
+  dependencies:
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/otlp-exporter-base": "npm:0.200.0"
+    "@opentelemetry/otlp-transformer": "npm:0.200.0"
+    "@opentelemetry/resources": "npm:2.0.0"
+    "@opentelemetry/sdk-metrics": "npm:2.0.0"
+  peerDependencies:
+    "@opentelemetry/api": ^1.3.0
+  checksum: 10c0/b94e99a481d3a156ed28f23ea9a72b594613081892ef889fd31be686d32daaa299e961bf173cdc3dcc5235a59f70f6437dd4d21c0256d638c669999c7912c20f
+  languageName: node
+  linkType: hard
+
 "@opentelemetry/instrumentation-connect@npm:0.39.0":
   version: 0.39.0
   resolution: "@opentelemetry/instrumentation-connect@npm:0.39.0"
@@ -12205,6 +12240,35 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/otlp-exporter-base@npm:0.200.0":
+  version: 0.200.0
+  resolution: "@opentelemetry/otlp-exporter-base@npm:0.200.0"
+  dependencies:
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/otlp-transformer": "npm:0.200.0"
+  peerDependencies:
+    "@opentelemetry/api": ^1.3.0
+  checksum: 10c0/3283c12bffc3156a41d9c16c097966e8418781a1d779250334f3d5b4f864be1aeac69fecfdf489abc95578dc36098dc0e026e5a48eb19ee170d72ef89b94f0e9
+  languageName: node
+  linkType: hard
+
+"@opentelemetry/otlp-transformer@npm:0.200.0":
+  version: 0.200.0
+  resolution: "@opentelemetry/otlp-transformer@npm:0.200.0"
+  dependencies:
+    "@opentelemetry/api-logs": "npm:0.200.0"
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/resources": "npm:2.0.0"
+    "@opentelemetry/sdk-logs": "npm:0.200.0"
+    "@opentelemetry/sdk-metrics": "npm:2.0.0"
+    "@opentelemetry/sdk-trace-base": "npm:2.0.0"
+    protobufjs: "npm:^7.3.0"
+  peerDependencies:
+    "@opentelemetry/api": ^1.3.0
+  checksum: 10c0/4f5383fad48c62e17824df91f6944b0376cb17f7b132b11d62fa5cf46747f224c980960209c85669b6e341a131f94586c6ad52bc1a6d2fb8d5295e23b460600c
+  languageName: node
+  linkType: hard
+
 "@opentelemetry/redis-common@npm:^0.36.2":
   version: 0.36.2
   resolution: "@opentelemetry/redis-common@npm:0.36.2"
@@ -12224,6 +12288,43 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/resources@npm:2.0.0":
+  version: 2.0.0
+  resolution: "@opentelemetry/resources@npm:2.0.0"
+  dependencies:
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/semantic-conventions": "npm:^1.29.0"
+  peerDependencies:
+    "@opentelemetry/api": ">=1.3.0 <1.10.0"
+  checksum: 10c0/2f331ff8268ef7168e8f24312fd7505900693c0ea302f6025937e94c157b8173ee54f5d5a737c06b956da721aa63443ac520f530cade880ef3cd40a2a25c702c
+  languageName: node
+  linkType: hard
+
+"@opentelemetry/sdk-logs@npm:0.200.0":
+  version: 0.200.0
+  resolution: "@opentelemetry/sdk-logs@npm:0.200.0"
+  dependencies:
+    "@opentelemetry/api-logs": "npm:0.200.0"
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/resources": "npm:2.0.0"
+  peerDependencies:
+    "@opentelemetry/api": ">=1.4.0 <1.10.0"
+  checksum: 10c0/031dc40dd012fad102e5c8c0c9bdbbce051dbc7fcc2e05e003f959aeb34d252dc3595b353ea2a9f900ff40f45d19cb4c8f7ab95a9faa01391f6b415c7780c786
+  languageName: node
+  linkType: hard
+
+"@opentelemetry/sdk-metrics@npm:2.0.0, @opentelemetry/sdk-metrics@npm:^2.0.0":
+  version: 2.0.0
+  resolution: "@opentelemetry/sdk-metrics@npm:2.0.0"
+  dependencies:
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/resources": "npm:2.0.0"
+  peerDependencies:
+    "@opentelemetry/api": ">=1.9.0 <1.10.0"
+  checksum: 10c0/9a3c87738671f29a496a39d65b3ab0829b52d0f31c0be662ea575a8f77bc5444044fd01513c891abdff6bf6344a08730e18f79253a85e68962669f3e1fa12e72
+  languageName: node
+  linkType: hard
+
 "@opentelemetry/sdk-metrics@npm:^1.9.1":
   version: 1.26.0
   resolution: "@opentelemetry/sdk-metrics@npm:1.26.0"
@@ -12236,6 +12337,19 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/sdk-trace-base@npm:2.0.0":
+  version: 2.0.0
+  resolution: "@opentelemetry/sdk-trace-base@npm:2.0.0"
+  dependencies:
+    "@opentelemetry/core": "npm:2.0.0"
+    "@opentelemetry/resources": "npm:2.0.0"
+    "@opentelemetry/semantic-conventions": "npm:^1.29.0"
+  peerDependencies:
+    "@opentelemetry/api": ">=1.3.0 <1.10.0"
+  checksum: 10c0/c63cc052741e4cc01d084c883e24a1c0792f081a242e14e5cf526d5a3d96bac5974006fa0d8f902bd04f34ed9ce95a0d0f01b7fdb37fcc813cea9f818f2b8f43
+  languageName: node
+  linkType: hard
+
 "@opentelemetry/sdk-trace-base@npm:^1.22, @opentelemetry/sdk-trace-base@npm:^1.26.0":
   version: 1.26.0
   resolution: "@opentelemetry/sdk-trace-base@npm:1.26.0"
@@ -12256,6 +12370,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/semantic-conventions@npm:^1.29.0":
+  version: 1.30.0
+  resolution: "@opentelemetry/semantic-conventions@npm:1.30.0"
+  checksum: 10c0/0bf99552e3b4b7e8b7eb504b678d52f59c6f259df88e740a2011a0d858e523d36fee86047ae1b7f45849c77f00f970c3059ba58e0a06a7d47d6f01dbe8c455bd
+  languageName: node
+  linkType: hard
+
 "@opentelemetry/sql-common@npm:^0.40.1":
   version: 0.40.1
   resolution: "@opentelemetry/sql-common@npm:0.40.1"
@@ -22204,6 +22325,15 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@types/node@npm:>=13.7.0":
+  version: 22.13.14
+  resolution: "@types/node@npm:22.13.14"
+  dependencies:
+    undici-types: "npm:~6.20.0"
+  checksum: 10c0/fa2ab5b8277bfbcc86c42e46a3ea9871b0d559894cc9d955685d17178c9499f0b1bf03d1d1ea8d92ef2dda818988f4035acb8abf9dc15423a998fa56173ab804
+  languageName: node
+  linkType: hard
+
 "@types/node@npm:^10.1.0":
   version: 10.17.60
   resolution: "@types/node@npm:10.17.60"
@@ -40434,6 +40564,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"long@npm:^5.0.0":
+  version: 5.3.1
+  resolution: "long@npm:5.3.1"
+  checksum: 10c0/8726994c6359bb7162fb94563e14c3f9c0f0eeafd90ec654738f4f144a5705756d36a873c442f172ee2a4b51e08d14ab99765b49aa1fb994c5ba7fe12057bca2
+  languageName: node
+  linkType: hard
+
 "longest-streak@npm:^2.0.0":
   version: 2.0.4
   resolution: "longest-streak@npm:2.0.4"
@@ -47139,6 +47276,26 @@ __metadata:
   languageName: node
   linkType: hard
 
+"protobufjs@npm:^7.3.0":
+  version: 7.4.0
+  resolution: "protobufjs@npm:7.4.0"
+  dependencies:
+    "@protobufjs/aspromise": "npm:^1.1.2"
+    "@protobufjs/base64": "npm:^1.1.2"
+    "@protobufjs/codegen": "npm:^2.0.4"
+    "@protobufjs/eventemitter": "npm:^1.1.0"
+    "@protobufjs/fetch": "npm:^1.1.0"
+    "@protobufjs/float": "npm:^1.0.2"
+    "@protobufjs/inquire": "npm:^1.1.0"
+    "@protobufjs/path": "npm:^1.1.2"
+    "@protobufjs/pool": "npm:^1.1.0"
+    "@protobufjs/utf8": "npm:^1.1.0"
+    "@types/node": "npm:>=13.7.0"
+    long: "npm:^5.0.0"
+  checksum: 10c0/a5460a63fe596523b9a067cbce39a6b310d1a71750fda261f076535662aada97c24450e18c5bc98a27784f70500615904ff1227e1742183509f0db4fdede669b
+  languageName: node
+  linkType: hard
+
 "proxy-addr@npm:~2.0.7":
   version: 2.0.7
   resolution: "proxy-addr@npm:2.0.7"
@@ -53021,6 +53178,9 @@ __metadata:
     "@nestjs/graphql": "patch:@nestjs/graphql@12.1.1#./patches/@nestjs+graphql+12.1.1.patch"
     "@node-saml/passport-saml": "npm:^5.0.0"
     "@nx/js": "npm:18.3.3"
+    "@opentelemetry/api": "npm:^1.9.0"
+    "@opentelemetry/exporter-metrics-otlp-http": "npm:^0.200.0"
+    "@opentelemetry/sdk-metrics": "npm:^2.0.0"
     "@ptc-org/nestjs-query-graphql": "patch:@ptc-org/nestjs-query-graphql@4.2.0#./patches/@ptc-org+nestjs-query-graphql+4.2.0.patch"
     "@revertdotdev/revert-react": "npm:^0.0.21"
     "@sentry/nestjs": "npm:^8.30.0"