fix: settle Responses cached token usage (#6892)

service/billing_usage.go

@@ -113,6 +113,29 @@ func usageFromOpenAIBillingUsage(billingUsage *dto.BillingUsage) *dto.Usage {
 	if usage.TotalTokens == 0 {
 	if usage.TotalTokens == 0 {
 		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	}
 	}
+	if inputDetails := usage.InputTokensDetails; inputDetails != nil {
+		if usage.PromptTokensDetails.CachedTokens == 0 && inputDetails.CachedTokens > 0 {
+			usage.PromptTokensDetails.CachedTokens = inputDetails.CachedTokens
+		}
+		if usage.PromptTokensDetails.CachedCreationTokens == 0 && inputDetails.CachedCreationTokens > 0 {
+			usage.PromptTokensDetails.CachedCreationTokens = inputDetails.CachedCreationTokens
+		}
+		if usage.PromptTokensDetails.CacheWriteTokens == 0 && inputDetails.CacheWriteTokens > 0 {
+			usage.PromptTokensDetails.CacheWriteTokens = inputDetails.CacheWriteTokens
+		}
+		if usage.PromptTokensDetails.TextTokens == 0 && inputDetails.TextTokens > 0 {
+			usage.PromptTokensDetails.TextTokens = inputDetails.TextTokens
+		}
+		if usage.PromptTokensDetails.ImageTokens == 0 && inputDetails.ImageTokens > 0 {
+			usage.PromptTokensDetails.ImageTokens = inputDetails.ImageTokens
+		}
+		if usage.PromptTokensDetails.AudioTokens == 0 && inputDetails.AudioTokens > 0 {
+			usage.PromptTokensDetails.AudioTokens = inputDetails.AudioTokens
+		}
+	}
+	if usage.PromptTokensDetails.CachedTokens == 0 && usage.PromptCacheHitTokens > 0 {
+		usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
+	}
 	usage.UsageSemantic = dto.BillingUsageSemanticOpenAI
 	usage.UsageSemantic = dto.BillingUsageSemanticOpenAI
 	usage.UsageSource = billingUsage.Source
 	usage.UsageSource = billingUsage.Source
 	usage.BillingUsage = dto.CloneBillingUsage(billingUsage)
 	usage.BillingUsage = dto.CloneBillingUsage(billingUsage)

service/text_quota_test.go

@@ -283,6 +283,92 @@ func TestCalculateTextQuotaSummaryUsesOpenAIBillingUsageBeforeTopLevelUsage(t *t
 	require.Equal(t, 98, summary.Quota)
 	require.Equal(t, 98, summary.Quota)
 }
 }
 
 
+func TestCalculateTextQuotaSummaryUsesOpenAIResponsesInputTokenDetails(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	ctx, _ := gin.CreateTestContext(httptest.NewRecorder())
+	relayInfo := &relaycommon.RelayInfo{
+		RelayFormat:     types.RelayFormatOpenAI,
+		OriginModelName: "gpt-4o",
+		PriceData: hosttypes.PriceData{
+			ModelRatio:      1,
+			CompletionRatio: 2,
+			CacheRatio:      0.25,
+			GroupRatioInfo:  hosttypes.GroupRatioInfo{GroupRatio: 1},
+		},
+		StartTime: time.Now(),
+	}
+
+	responsesUsage := &dto.Usage{
+		InputTokens:  100,
+		OutputTokens: 10,
+		TotalTokens:  110,
+		InputTokensDetails: &dto.InputTokenDetails{
+			CachedTokens: 40,
+		},
+	}
+	convertedUsage := &dto.Usage{
+		PromptTokens:     100,
+		CompletionTokens: 10,
+		TotalTokens:      110,
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedTokens: 40,
+		},
+		BillingUsage: dto.NewOpenAIResponsesBillingUsage(responsesUsage),
+	}
+
+	effectiveUsage := effectiveBillingUsage(convertedUsage)
+	require.Equal(t, 40, effectiveUsage.PromptTokensDetails.CachedTokens)
+	require.Zero(t, convertedUsage.BillingUsage.OpenAIUsage.PromptTokensDetails.CachedTokens)
+
+	summary := calculateTextQuotaSummary(ctx, relayInfo, effectiveUsage)
+	require.Equal(t, 40, summary.CacheTokens)
+	// 60 uncached input + 40*0.25 cached input + 10*2 output = 90.
+	require.Equal(t, 90, summary.Quota)
+}
+
+func TestUsageFromOpenAIBillingUsageNormalizesCacheDetailsWithoutOverwritingCanonicalValues(t *testing.T) {
+	responsesUsage := &dto.Usage{
+		InputTokens:          100,
+		OutputTokens:         10,
+		PromptCacheHitTokens: 55,
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedTokens: 8,
+			TextTokens:   12,
+		},
+		InputTokensDetails: &dto.InputTokenDetails{
+			CachedTokens:         40,
+			CachedCreationTokens: 5,
+			CacheWriteTokens:     6,
+			TextTokens:           60,
+			ImageTokens:          7,
+			AudioTokens:          9,
+		},
+	}
+
+	billingUsage := dto.NewOpenAIResponsesBillingUsage(responsesUsage)
+	usage := effectiveBillingUsage(&dto.Usage{BillingUsage: billingUsage})
+
+	require.Equal(t, 8, usage.PromptTokensDetails.CachedTokens)
+	require.Equal(t, 5, usage.PromptTokensDetails.CachedCreationTokens)
+	require.Equal(t, 6, usage.PromptTokensDetails.CacheWriteTokens)
+	require.Equal(t, 12, usage.PromptTokensDetails.TextTokens)
+	require.Equal(t, 7, usage.PromptTokensDetails.ImageTokens)
+	require.Equal(t, 9, usage.PromptTokensDetails.AudioTokens)
+	require.Zero(t, billingUsage.OpenAIUsage.PromptTokensDetails.CachedCreationTokens)
+}
+
+func TestUsageFromOpenAIBillingUsageFallsBackToPromptCacheHitTokens(t *testing.T) {
+	usage := effectiveBillingUsage(&dto.Usage{
+		BillingUsage: dto.NewOpenAIChatBillingUsage(&dto.Usage{
+			PromptTokens:         100,
+			CompletionTokens:     10,
+			PromptCacheHitTokens: 35,
+		}),
+	})
+
+	require.Equal(t, 35, usage.PromptTokensDetails.CachedTokens)
+}
+
 func TestUsageBillingPathForLog(t *testing.T) {
 func TestUsageBillingPathForLog(t *testing.T) {
 	require.Equal(t, usageBillingPathAnthropic, usageBillingPathForLog(true, &dto.Usage{
 	require.Equal(t, usageBillingPathAnthropic, usageBillingPathForLog(true, &dto.Usage{
 		BillingUsage: dto.NewClaudeMessagesBillingUsage(&dto.ClaudeUsage{InputTokens: 1}),
 		BillingUsage: dto.NewClaudeMessagesBillingUsage(&dto.ClaudeUsage{InputTokens: 1}),