fix: ensure time_since_last_block accuracy with polling fallback (#28)

Author: auricom

pkg/exporters/drift/drift.go

@@ -61,6 +61,9 @@ func (e exporter) ExportMetrics(ctx context.Context, m *metrics.Metrics) error {
 
 			m.RecordEndpointAvailability(e.chainID, e.referenceNode, true)
 			m.RecordReferenceBlockHeight(e.chainID, e.referenceNode, refHeight)
+			// Also update time since last block metric when we see new blocks via polling
+			// This ensures the metric stays accurate even if WebSocket subscription fails
+			m.UpdateLastBlockTime(e.chainID, time.Now())
 			e.logger.Info().Uint64("height", refHeight).Str("endpoint", e.referenceNode).Msg("recorded reference node height")
 
 			// get each full node height and calculate drift
@@ -77,6 +80,10 @@ func (e exporter) ExportMetrics(ctx context.Context, m *metrics.Metrics) error {
 				m.RecordCurrentBlockHeight(e.chainID, fullNode, currentHeight)
 				m.RecordBlockHeightDrift(e.chainID, fullNode, refHeight, currentHeight)
 
+				// Also update time since last block metric when we see new blocks via polling
+				// This ensures the metric stays accurate even if WebSocket subscription fails
+				m.UpdateLastBlockTime(e.chainID, time.Now())
+
 				drift := int64(refHeight) - int64(currentHeight)
 				e.logger.Info().
 					Uint64("ref_height", refHeight).

pkg/metrics/metrics.go

@@ -562,6 +562,21 @@ func (m *Metrics) RecordBlockTime(chainID string, arrivalTime time.Time) {
 		}
 	}
 
+	m.updateLastBlockTimeUnsafe(chainID, arrivalTime)
+}
+
+// UpdateLastBlockTime updates the last block arrival time and resets time since last block metric
+// without recording block time histogram. This is used by pollers that can't measure inter-block time.
+func (m *Metrics) UpdateLastBlockTime(chainID string, arrivalTime time.Time) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.updateLastBlockTimeUnsafe(chainID, arrivalTime)
+}
+
+// updateLastBlockTimeUnsafe is an unexported helper that updates the last block arrival time
+// and resets the time since last block gauge.
+// This function is not thread-safe and should be called with a lock held.
+func (m *Metrics) updateLastBlockTimeUnsafe(chainID string, arrivalTime time.Time) {
 	// update last seen arrival time
 	m.lastBlockArrivalTime[chainID] = arrivalTime
 	// reset time since last block to 0