Merge branch 'main' into issue-2977

docs/api/openapi.yml

@@ -1763,12 +1763,15 @@ components:
           additionalProperties: {}
           nullable: true
           type: object
+        syncState:
+          $ref: '#/components/schemas/CloudintegrationtypesSyncState'
         timestampMillis:
           format: int64
           type: integer
       required:
       - timestampMillis
       - data
+      - syncState
       type: object
     CloudintegrationtypesAzureAccountConfig:
       properties:
@@ -2013,6 +2016,8 @@ components:
           format: date-time
           nullable: true
           type: string
+        syncState:
+          $ref: '#/components/schemas/CloudintegrationtypesSyncState'
       required:
       - account_id
       - cloud_account_id
@@ -2022,6 +2027,7 @@ components:
       - providerAccountId
       - integrationConfig
       - removedAt
+      - syncState
       type: object
     CloudintegrationtypesGettableServicesMetadata:
       properties:
@@ -2121,6 +2127,9 @@ components:
           type: object
         providerAccountId:
           type: string
+        syncedVersion:
+          nullable: true
+          type: integer
       required:
       - data
       type: object
@@ -2133,6 +2142,18 @@ components:
         gcp:
           $ref: '#/components/schemas/CloudintegrationtypesGCPIntegrationConfig'
       type: object
+    CloudintegrationtypesRegionState:
+      enum:
+      - present
+      - removed
+      type: string
+    CloudintegrationtypesRegionSyncState:
+      properties:
+        state:
+          $ref: '#/components/schemas/CloudintegrationtypesRegionState'
+      required:
+      - state
+      type: object
     CloudintegrationtypesService:
       properties:
         assets:
@@ -2274,6 +2295,23 @@ components:
         metrics:
           type: boolean
       type: object
+    CloudintegrationtypesSyncState:
+      nullable: true
+      properties:
+        inSync:
+          type: boolean
+        regions:
+          additionalProperties:
+            $ref: '#/components/schemas/CloudintegrationtypesRegionSyncState'
+          type: object
+        version:
+          format: int64
+          type: integer
+      required:
+      - version
+      - inSync
+      - regions
+      type: object
     CloudintegrationtypesUpdatableAccount:
       properties:
         config:

ee/modules/cloudintegration/implcloudintegration/module.go

@@ -188,27 +188,41 @@ func (module *module) AgentCheckIn(ctx context.Context, orgID valuer.UUID, provi
 		return nil, err
 	}
 
+	// Get account as domain object for config access (enabled regions, etc.)
+	domainAccount, err := cloudintegrationtypes.NewAccountFromStorable(account)
+	if err != nil {
+		return nil, err
+	}
+
+	syncState := domainAccount.NextSyncState(req.SyncedVersion)
+
 	// If account has been removed (disconnected), return a minimal response with empty integration config.
 	// The agent uses this response to clean up resources
 	if account.RemovedAt != nil {
+		// Heartbeat stays frozen after removal, only the sync state is updated.
+		if domainAccount.AgentReport != nil && syncState != nil {
+			domainAccount.AgentReport.SyncState = syncState
+			account.Update(account.AccountID, domainAccount.AgentReport)
+
+			err = module.store.UpdateAgentReport(ctx, account)
+			if err != nil {
+				return nil, err
+			}
+		}
+
 		return cloudintegrationtypes.NewAgentCheckInResponse(
 			req.ProviderAccountID,
 			account.ID.StringValue(),
 			new(cloudintegrationtypes.ProviderIntegrationConfig),
 			account.RemovedAt,
+			syncState,
 		), nil
 	}
 
 	// update account with cloud provider account id and agent report (heartbeat)
-	account.Update(&req.ProviderAccountID, cloudintegrationtypes.NewAgentReport(req.Data))
+	account.Update(&req.ProviderAccountID, cloudintegrationtypes.NewAgentReport(req.Data, syncState))
 
-	err = module.store.UpdateAccount(ctx, account)
-	if err != nil {
-		return nil, err
-	}
-
-	// Get account as domain object for config access (enabled regions, etc.)
-	domainAccount, err := cloudintegrationtypes.NewAccountFromStorable(account)
+	err = module.store.UpdateAgentReport(ctx, account)
 	if err != nil {
 		return nil, err
 	}
@@ -234,6 +248,7 @@ func (module *module) AgentCheckIn(ctx context.Context, orgID valuer.UUID, provi
 		account.ID.StringValue(),
 		integrationConfig,
 		account.RemovedAt,
+		syncState,
 	), nil
 }
 

frontend/src/api/generated/services/sigNoz.schemas.ts

@@ -3366,6 +3366,37 @@ export interface CloudintegrationtypesAWSServiceConfigDTO {
 	metrics?: CloudintegrationtypesAWSServiceMetricsConfigDTO;
 }
 
+export enum CloudintegrationtypesRegionStateDTO {
+	present = 'present',
+	removed = 'removed',
+}
+export interface CloudintegrationtypesRegionSyncStateDTO {
+	state: CloudintegrationtypesRegionStateDTO;
+}
+
+export type CloudintegrationtypesSyncStateDTORegions = {
+	[key: string]: CloudintegrationtypesRegionSyncStateDTO;
+};
+
+/**
+ * @nullable
+ */
+export type CloudintegrationtypesSyncStateDTO = {
+	/**
+	 * @type boolean
+	 */
+	inSync: boolean;
+	/**
+	 * @type object
+	 */
+	regions: CloudintegrationtypesSyncStateDTORegions;
+	/**
+	 * @type integer
+	 * @format int64
+	 */
+	version: number;
+} | null;
+
 export type CloudintegrationtypesAgentReportDTODataAnyOf = {
 	[key: string]: unknown;
 };
@@ -3384,6 +3415,7 @@ export type CloudintegrationtypesAgentReportDTO = {
 	 * @type object,null
 	 */
 	data: CloudintegrationtypesAgentReportDTOData;
+	syncState: CloudintegrationtypesSyncStateDTO | null;
 	/**
 	 * @type integer
 	 * @format int64
@@ -3812,6 +3844,7 @@ export interface CloudintegrationtypesGettableAgentCheckInDTO {
 	 * @format date-time
 	 */
 	removedAt: string | null;
+	syncState: CloudintegrationtypesSyncStateDTO | null;
 }
 
 export interface CloudintegrationtypesServiceMetadataDTO {
@@ -3882,6 +3915,10 @@ export interface CloudintegrationtypesPostableAgentCheckInDTO {
 	 * @type string
 	 */
 	providerAccountId?: string;
+	/**
+	 * @type integer,null
+	 */
+	syncedVersion?: number | null;
 }
 
 export interface CloudintegrationtypesStorableIntegrationDashboardDTO {

frontend/src/container/Integrations/CloudIntegration/AmazonWebServices/__tests__/mockData.ts

@@ -24,6 +24,7 @@ const accountsResponse: ListAccounts200 = {
 				agentReport: {
 					timestampMillis: 1747114366214,
 					data: null,
+					syncState: null,
 				},
 				providerAccountId: PROVIDER_ACCOUNT_ID,
 				removedAt: null,

frontend/src/pages/IntegrationsDetailsPage/CloudIntegration/stories/__story_mockdata__/cloudIntegration.ts

@@ -295,7 +295,11 @@ const account = (
 	provider,
 	providerAccountId: ACCOUNTS[provider][index],
 	config: accountConfig(provider),
-	agentReport: { timestampMillis: Date.now() - 45 * 1000, data: null },
+	agentReport: {
+		timestampMillis: Date.now() - 45 * 1000,
+		data: null,
+		syncState: null,
+	},
 	createdAt: new Date(Date.now() - 21 * 24 * 60 * 60 * 1000).toISOString(),
 	updatedAt: new Date(Date.now() - 60 * 60 * 1000).toISOString(),
 	removedAt: null,

pkg/modules/cloudintegration/implcloudintegration/store.go

@@ -134,6 +134,24 @@ func (store *store) UpdateAccount(ctx context.Context, account *cloudintegration
 		BunDBCtx(ctx).
 		NewUpdate().
 		Model(account).
+		Column("config").
+		Column("updated_at").
+		WherePK().
+		Where("org_id = ?", account.OrgID).
+		Where("provider = ?", account.Provider).
+		Exec(ctx)
+
+	return err
+}
+
+func (store *store) UpdateAgentReport(ctx context.Context, account *cloudintegrationtypes.StorableCloudIntegration) error {
+	_, err := store.
+		store.
+		BunDBCtx(ctx).
+		NewUpdate().
+		Model(account).
+		Column("account_id").
+		Column("last_agent_report").
 		WherePK().
 		Where("org_id = ?", account.OrgID).
 		Where("provider = ?", account.Provider).

pkg/types/cloudintegrationtypes/account.go

@@ -26,6 +26,17 @@ type Account struct {
 type AgentReport struct {
 	TimestampMillis int64          `json:"timestampMillis" required:"true"`
 	Data            map[string]any `json:"data" required:"true" nullable:"true"`
+	SyncState       *SyncState     `json:"syncState" required:"true" nullable:"true"`
+}
+
+type SyncState struct {
+	Version int64                       `json:"version" required:"true"`
+	InSync  bool                        `json:"inSync" required:"true"`
+	Regions map[string]*RegionSyncState `json:"regions" required:"true" nullable:"false"`
+}
+
+type RegionSyncState struct {
+	State RegionState `json:"state" required:"true"`
 }
 
 type AccountConfig struct {
@@ -150,6 +161,7 @@ func NewAccountFromStorable(storableAccount *StorableCloudIntegration) (*Account
 		account.AgentReport = &AgentReport{
 			TimestampMillis: storableAccount.LastAgentReport.TimestampMillis,
 			Data:            storableAccount.LastAgentReport.Data,
+			SyncState:       NewSyncStateFromStorable(storableAccount.LastAgentReport.SyncState),
 		}
 	}
 
@@ -308,10 +320,101 @@ func NewAccountConfigFromUpdatable(provider CloudProviderType, config *Updatable
 	}
 }
 
-func NewAgentReport(data map[string]any) *AgentReport {
+func NewAgentReport(data map[string]any, syncState *SyncState) *AgentReport {
 	return &AgentReport{
 		TimestampMillis: time.Now().UnixMilli(),
 		Data:            data,
+		SyncState:       syncState,
+	}
+}
+
+// NewSyncState returns the sync state after a check-in without mutating previous.
+// The ack is applied before the config diff, so it is checked against the version the agent was last sent.
+func NewSyncState(previous *SyncState, regions []string, removed bool, syncedVersion *int64) *SyncState {
+	next := &SyncState{Version: 1, InSync: true, Regions: make(map[string]*RegionSyncState)}
+
+	// First check-in: seed from the config as in sync. Otherwise start from a copy of previous.
+	if previous == nil {
+		for _, region := range regions {
+			next.Regions[region] = &RegionSyncState{State: RegionStatePresent}
+		}
+	} else {
+		next.Version = previous.Version
+		next.InSync = previous.InSync
+		for region, regionSyncState := range previous.Regions {
+			next.Regions[region] = &RegionSyncState{State: regionSyncState.State}
+		}
+	}
+
+	// The agent synced this version, so its removed regions are cleaned up and can be dropped.
+	if syncedVersion != nil && *syncedVersion == next.Version {
+		next.InSync = true
+		for region, regionSyncState := range next.Regions {
+			if regionSyncState.State == RegionStateRemoved {
+				delete(next.Regions, region)
+			}
+		}
+	}
+
+	changed := false
+
+	if removed {
+		// Integration removed: every present region must be cleaned up.
+		for _, regionSyncState := range next.Regions {
+			if regionSyncState.State != RegionStateRemoved {
+				regionSyncState.State = RegionStateRemoved
+				changed = true
+			}
+		}
+	} else {
+		desiredRegions := make(map[string]struct{}, len(regions))
+		for _, region := range regions {
+			desiredRegions[region] = struct{}{}
+
+			regionSyncState, ok := next.Regions[region]
+			switch {
+			case !ok:
+				// Region added to the config.
+				next.Regions[region] = &RegionSyncState{State: RegionStatePresent}
+				changed = true
+			case regionSyncState.State == RegionStateRemoved:
+				// Region added back before its removal was acked.
+				regionSyncState.State = RegionStatePresent
+				changed = true
+			}
+		}
+
+		for region, regionSyncState := range next.Regions {
+			if _, desired := desiredRegions[region]; !desired && regionSyncState.State == RegionStatePresent {
+				// Region removed from the config.
+				regionSyncState.State = RegionStateRemoved
+				changed = true
+			}
+		}
+	}
+
+	if changed {
+		next.Version++
+		next.InSync = false
+	}
+
+	return next
+}
+
+func NewSyncStateFromStorable(storableSyncState *StorableSyncState) *SyncState {
+	if storableSyncState == nil {
+		return nil
+	}
+
+	regions := make(map[string]*RegionSyncState, len(storableSyncState.Regions))
+	for region, regionSyncState := range storableSyncState.Regions {
+		regions[region] = &RegionSyncState{State: regionSyncState.State}
+	}
+
+	return &SyncState{
+		Version: storableSyncState.Version,
+		InSync:  storableSyncState.InSync,
+		Regions: regions,
 	}
 }
 
@@ -335,6 +438,26 @@ func (account *Account) Update(provider CloudProviderType, config *AccountConfig
 	return nil
 }
 
+// NextSyncState returns the sync state for this check-in, or nil for providers without one.
+func (account *Account) NextSyncState(syncedVersion *int64) *SyncState {
+	if account.Provider != CloudProviderTypeAWS {
+		return nil
+	}
+
+	var previous *SyncState
+	if account.AgentReport != nil {
+		previous = account.AgentReport.SyncState
+	}
+
+	regions := account.Config.AWS.Regions
+	// Removed before the agent ever checked in: no region was sent to it, so there is nothing to clean up.
+	if account.AgentReport == nil && account.RemovedAt != nil {
+		regions = nil
+	}
+
+	return NewSyncState(previous, regions, account.RemovedAt != nil, syncedVersion)
+}
+
 func (postableAccount *PostableAccount) UnmarshalJSON(data []byte) error {
 	type Alias PostableAccount
 

pkg/types/cloudintegrationtypes/checkin.go

@@ -12,7 +12,8 @@ type AgentCheckInRequest struct {
 	ProviderAccountID  string      `json:"providerAccountId" required:"false"`
 	CloudIntegrationID valuer.UUID `json:"cloudIntegrationId" required:"false"`
 
-	Data map[string]any `json:"data" required:"true" nullable:"true"`
+	Data          map[string]any `json:"data" required:"true" nullable:"true"`
+	SyncedVersion *int64         `json:"syncedVersion" required:"false" nullable:"true"`
 }
 
 type PostableAgentCheckIn struct {
@@ -28,6 +29,7 @@ type AgentCheckInResponse struct {
 	ProviderAccountID  string                     `json:"providerAccountId" required:"true"`
 	IntegrationConfig  *ProviderIntegrationConfig `json:"integrationConfig" required:"true"`
 	RemovedAt          *time.Time                 `json:"removedAt" required:"true" nullable:"true"`
+	SyncState          *SyncState                 `json:"syncState" required:"true" nullable:"true"`
 }
 
 type GettableAgentCheckIn struct {
@@ -73,12 +75,13 @@ func NewGettableAgentCheckIn(provider CloudProviderType, resp *AgentCheckInRespo
 	return gettable
 }
 
-func NewAgentCheckInResponse(providerAccountID, cloudIntegrationID string, integrationConfig *ProviderIntegrationConfig, removedAt *time.Time) *AgentCheckInResponse {
+func NewAgentCheckInResponse(providerAccountID, cloudIntegrationID string, integrationConfig *ProviderIntegrationConfig, removedAt *time.Time, syncState *SyncState) *AgentCheckInResponse {
 	return &AgentCheckInResponse{
 		CloudIntegrationID: cloudIntegrationID,
 		ProviderAccountID:  providerAccountID,
 		IntegrationConfig:  integrationConfig,
 		RemovedAt:          removedAt,
+		SyncState:          syncState,
 	}
 }
 

pkg/types/cloudintegrationtypes/cloudintegration.go

@@ -25,6 +25,17 @@ var (
 	ErrCodeServiceDefinitionNotFound            = errors.MustNewCode("service_definition_not_found")
 )
 
+var (
+	RegionStatePresent = RegionState{valuer.NewString("present")}
+	RegionStateRemoved = RegionState{valuer.NewString("removed")}
+)
+
+type RegionState struct{ valuer.String }
+
+func (RegionState) Enum() []any {
+	return []any{RegionStatePresent, RegionStateRemoved}
+}
+
 // StorableCloudIntegration represents a cloud integration stored in the database.
 // This is also referred as "Account" in the context of cloud integrations.
 type StorableCloudIntegration struct {
@@ -43,8 +54,16 @@ type StorableCloudIntegration struct {
 // StorableAgentReport represents the last heartbeat and arbitrary data sent by the agent
 // as of now there is no use case for Data field, but keeping it for backwards compatibility with older structure.
 type StorableAgentReport struct {
-	TimestampMillis int64          `json:"timestamp_millis"` // backward compatibility
-	Data            map[string]any `json:"data"`
+	TimestampMillis int64              `json:"timestamp_millis"` // backward compatibility
+	Data            map[string]any     `json:"data"`
+	SyncState       *StorableSyncState `json:"sync_state,omitempty"`
+}
+
+// StorableSyncState holds every region sent to the agent. A removed region is dropped only after the agent acks Version.
+type StorableSyncState struct {
+	Version int64                       `json:"version"`
+	InSync  bool                        `json:"in_sync"`
+	Regions map[string]*RegionSyncState `json:"regions"`
 }
 
 // StorableCloudIntegrationService is to store service config for a cloud integration, which is a cloud provider specific configuration.
@@ -148,12 +167,30 @@ func NewStorableCloudIntegration(account *Account) (*StorableCloudIntegration, e
 		storableAccount.LastAgentReport = &StorableAgentReport{
 			TimestampMillis: account.AgentReport.TimestampMillis,
 			Data:            account.AgentReport.Data,
+			SyncState:       NewStorableSyncState(account.AgentReport.SyncState),
 		}
 	}
 
 	return storableAccount, nil
 }
 
+func NewStorableSyncState(syncState *SyncState) *StorableSyncState {
+	if syncState == nil {
+		return nil
+	}
+
+	regions := make(map[string]*RegionSyncState, len(syncState.Regions))
+	for region, regionSyncState := range syncState.Regions {
+		regions[region] = &RegionSyncState{State: regionSyncState.State}
+	}
+
+	return &StorableSyncState{
+		Version: syncState.Version,
+		InSync:  syncState.InSync,
+		Regions: regions,
+	}
+}
+
 // NewStorableCloudIntegrationService creates a new StorableCloudIntegrationService with
 // generated ID and timestamps from a CloudIntegrationService and its serialized config JSON.
 func NewStorableCloudIntegrationService(svc *CloudIntegrationService, configJSON string) *StorableCloudIntegrationService {
@@ -172,6 +209,7 @@ func (account *StorableCloudIntegration) Update(providerAccountID *string, agent
 		account.LastAgentReport = &StorableAgentReport{
 			TimestampMillis: agentReport.TimestampMillis,
 			Data:            agentReport.Data,
+			SyncState:       NewStorableSyncState(agentReport.SyncState),
 		}
 	}
 }

pkg/types/cloudintegrationtypes/store.go

@@ -25,9 +25,12 @@ type Store interface {
 	// CreateAccount creates a new cloud integration account
 	CreateAccount(ctx context.Context, account *StorableCloudIntegration) error
 
-	// UpdateAccount updates an existing cloud integration account
+	// UpdateAccount updates the user updatable fields (config) of an existing cloud integration account
 	UpdateAccount(ctx context.Context, account *StorableCloudIntegration) error
 
+	// UpdateAgentReport updates the provider account id and last agent report of an existing cloud integration account
+	UpdateAgentReport(ctx context.Context, account *StorableCloudIntegration) error
+
 	// RemoveAccount marks a cloud integration account as removed by setting the RemovedAt field
 	RemoveAccount(ctx context.Context, orgID, id valuer.UUID, provider CloudProviderType) error