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/runtime/executor/usage_helpers.go

@@ -73,17 +73,7 @@ func (r *usageReporter) publishWithOutcome(ctx context.Context, detail usage.Det
 		return
 	}
 	r.once.Do(func() {
-		usage.PublishRecord(ctx, usage.Record{
-			Provider:    r.provider,
-			Model:       r.model,
-			Source:      r.source,
-			APIKey:      r.apiKey,
-			AuthID:      r.authID,
-			AuthIndex:   r.authIndex,
-			RequestedAt: r.requestedAt,
-			Failed:      failed,
-			Detail:      detail,
-		})
+		usage.PublishRecord(ctx, r.buildRecord(detail, failed))
 	})
 }
 
@@ -96,20 +86,39 @@ func (r *usageReporter) ensurePublished(ctx context.Context) {
 		return
 	}
 	r.once.Do(func() {
-		usage.PublishRecord(ctx, usage.Record{
-			Provider:    r.provider,
-			Model:       r.model,
-			Source:      r.source,
-			APIKey:      r.apiKey,
-			AuthID:      r.authID,
-			AuthIndex:   r.authIndex,
-			RequestedAt: r.requestedAt,
-			Failed:      false,
-			Detail:      usage.Detail{},
-		})
+		usage.PublishRecord(ctx, r.buildRecord(usage.Detail{}, false))
 	})
 }
 
+func (r *usageReporter) buildRecord(detail usage.Detail, failed bool) usage.Record {
+	if r == nil {
+		return usage.Record{Detail: detail, Failed: failed}
+	}
+	return usage.Record{
+		Provider:    r.provider,
+		Model:       r.model,
+		Source:      r.source,
+		APIKey:      r.apiKey,
+		AuthID:      r.authID,
+		AuthIndex:   r.authIndex,
+		RequestedAt: r.requestedAt,
+		Latency:     r.latency(),
+		Failed:      failed,
+		Detail:      detail,
+	}
+}
+
+func (r *usageReporter) latency() time.Duration {
+	if r == nil || r.requestedAt.IsZero() {
+		return 0
+	}
+	latency := time.Since(r.requestedAt)
+	if latency < 0 {
+		return 0
+	}
+	return latency
+}
+
 func apiKeyFromContext(ctx context.Context) string {
 	if ctx == nil {
 		return ""

internal/runtime/executor/usage_helpers_test.go

@@ -1,6 +1,11 @@
 package executor
 
-import "testing"
+import (
+	"testing"
+	"time"
+
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/usage"
+)
 
 func TestParseOpenAIUsageChatCompletions(t *testing.T) {
 	data := []byte(`{"usage":{"prompt_tokens":1,"completion_tokens":2,"total_tokens":3,"prompt_tokens_details":{"cached_tokens":4},"completion_tokens_details":{"reasoning_tokens":5}}}`)
@@ -41,3 +46,19 @@ func TestParseOpenAIUsageResponses(t *testing.T) {
 		t.Fatalf("reasoning tokens = %d, want %d", detail.ReasoningTokens, 9)
 	}
 }
+
+func TestUsageReporterBuildRecordIncludesLatency(t *testing.T) {
+	reporter := &usageReporter{
+		provider:    "openai",
+		model:       "gpt-5.4",
+		requestedAt: time.Now().Add(-1500 * time.Millisecond),
+	}
+
+	record := reporter.buildRecord(usage.Detail{TotalTokens: 3}, false)
+	if record.Latency < time.Second {
+		t.Fatalf("latency = %v, want >= 1s", record.Latency)
+	}
+	if record.Latency > 3*time.Second {
+		t.Fatalf("latency = %v, want <= 3s", record.Latency)
+	}
+}