refactor: streamline usage reporting by consolidating record publishing logic

- Introduced a new method `buildRecord` in `usageReporter` to encapsulate record creation, improving code readability and maintainability.
- Added latency tracking to usage records, ensuring accurate reporting of request latencies.
- Updated tests to validate the inclusion of latency in usage records and ensure proper functionality of the new reporting structure.

internal/usage/logger_plugin.go

@@ -87,9 +87,10 @@ type modelStats struct {
 	Details       []RequestDetail
 }
 
-// RequestDetail stores the timestamp and token usage for a single request.
+// RequestDetail stores the timestamp, latency, and token usage for a single request.
 type RequestDetail struct {
 	Timestamp time.Time  `json:"timestamp"`
+	LatencyMs int64      `json:"latency_ms"`
 	Source    string     `json:"source"`
 	AuthIndex string     `json:"auth_index"`
 	Tokens    TokenStats `json:"tokens"`
@@ -198,6 +199,7 @@ func (s *RequestStatistics) Record(ctx context.Context, record coreusage.Record)
 	}
 	s.updateAPIStats(stats, modelName, RequestDetail{
 		Timestamp: timestamp,
+		LatencyMs: normaliseLatency(record.Latency),
 		Source:    record.Source,
 		AuthIndex: record.AuthIndex,
 		Tokens:    detail,
@@ -332,6 +334,9 @@ func (s *RequestStatistics) MergeSnapshot(snapshot StatisticsSnapshot) MergeResu
 			}
 			for _, detail := range modelSnapshot.Details {
 				detail.Tokens = normaliseTokenStats(detail.Tokens)
+				if detail.LatencyMs < 0 {
+					detail.LatencyMs = 0
+				}
 				if detail.Timestamp.IsZero() {
 					detail.Timestamp = time.Now()
 				}
@@ -463,6 +468,13 @@ func normaliseTokenStats(tokens TokenStats) TokenStats {
 	return tokens
 }
 
+func normaliseLatency(latency time.Duration) int64 {
+	if latency <= 0 {
+		return 0
+	}
+	return latency.Milliseconds()
+}
+
 func formatHour(hour int) string {
 	if hour < 0 {
 		hour = 0