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

internal/usage/logger_plugin_test.go

@@ -0,0 +1,96 @@
+package usage
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	coreusage "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/usage"
+)
+
+func TestRequestStatisticsRecordIncludesLatency(t *testing.T) {
+	stats := NewRequestStatistics()
+	stats.Record(context.Background(), coreusage.Record{
+		APIKey:      "test-key",
+		Model:       "gpt-5.4",
+		RequestedAt: time.Date(2026, 3, 20, 12, 0, 0, 0, time.UTC),
+		Latency:     1500 * time.Millisecond,
+		Detail: coreusage.Detail{
+			InputTokens:  10,
+			OutputTokens: 20,
+			TotalTokens:  30,
+		},
+	})
+
+	snapshot := stats.Snapshot()
+	details := snapshot.APIs["test-key"].Models["gpt-5.4"].Details
+	if len(details) != 1 {
+		t.Fatalf("details len = %d, want 1", len(details))
+	}
+	if details[0].LatencyMs != 1500 {
+		t.Fatalf("latency_ms = %d, want 1500", details[0].LatencyMs)
+	}
+}
+
+func TestRequestStatisticsMergeSnapshotDedupIgnoresLatency(t *testing.T) {
+	stats := NewRequestStatistics()
+	timestamp := time.Date(2026, 3, 20, 12, 0, 0, 0, time.UTC)
+	first := StatisticsSnapshot{
+		APIs: map[string]APISnapshot{
+			"test-key": {
+				Models: map[string]ModelSnapshot{
+					"gpt-5.4": {
+						Details: []RequestDetail{{
+							Timestamp: timestamp,
+							LatencyMs: 0,
+							Source:    "user@example.com",
+							AuthIndex: "0",
+							Tokens: TokenStats{
+								InputTokens:  10,
+								OutputTokens: 20,
+								TotalTokens:  30,
+							},
+						}},
+					},
+				},
+			},
+		},
+	}
+	second := StatisticsSnapshot{
+		APIs: map[string]APISnapshot{
+			"test-key": {
+				Models: map[string]ModelSnapshot{
+					"gpt-5.4": {
+						Details: []RequestDetail{{
+							Timestamp: timestamp,
+							LatencyMs: 2500,
+							Source:    "user@example.com",
+							AuthIndex: "0",
+							Tokens: TokenStats{
+								InputTokens:  10,
+								OutputTokens: 20,
+								TotalTokens:  30,
+							},
+						}},
+					},
+				},
+			},
+		},
+	}
+
+	result := stats.MergeSnapshot(first)
+	if result.Added != 1 || result.Skipped != 0 {
+		t.Fatalf("first merge = %+v, want added=1 skipped=0", result)
+	}
+
+	result = stats.MergeSnapshot(second)
+	if result.Added != 0 || result.Skipped != 1 {
+		t.Fatalf("second merge = %+v, want added=0 skipped=1", result)
+	}
+
+	snapshot := stats.Snapshot()
+	details := snapshot.APIs["test-key"].Models["gpt-5.4"].Details
+	if len(details) != 1 {
+		t.Fatalf("details len = %d, want 1", len(details))
+	}
+}