fix(billing): correct tiered billing settlement and edge cases

- quota.go: add missing SettleBilling call in PostWssConsumeQuota
- text_quota.go: gate InjectTieredBillingInfo on tieredBillingApplied bool
  instead of tieredResult != nil, so fallback billing still logs metadata
- price.go: remove quotaBeforeGroup == 0 from freeModel condition to avoid
  bypassing settlement for output-only expressions
- tiered_settle.go: split cc/cc1h subtraction using UsageSemantic to
  distinguish OpenAI vs Claude cache creation token formats
- pricing.go: only set BillingMode when a non-empty expression exists
- useModelPricingEditorState.js: only write billing_mode when
  finalBillingExpr is non-empty

service/quota.go

@@ -226,6 +226,10 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
+	if err := SettleBilling(ctx, relayInfo, quota); err != nil {
+		logger.LogError(ctx, "error settling billing: "+err.Error())
+	}
+
 	logModel := modelName
 	if extraContent != "" {
 		logContent += ", " + extraContent

service/text_quota.go

@@ -330,6 +330,7 @@ func PostTextConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, us
 	summary := calculateTextQuotaSummary(ctx, relayInfo, usage)
 
 	var tieredResult *billingexpr.TieredResult
+	tieredBillingApplied := false
 	if originUsage != nil {
 		var tieredUsedVars map[string]bool
 		if snap := relayInfo.TieredBillingSnapshot; snap != nil {
@@ -337,6 +338,7 @@ func PostTextConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, us
 		}
 		tieredOk, tieredQuota, tieredRes := TryTieredSettle(relayInfo, BuildTieredTokenParams(usage, summary.IsClaudeUsageSemantic, tieredUsedVars))
 		if tieredOk {
+			tieredBillingApplied = true
 			tieredResult = tieredRes
 			summary.Quota = composeTieredTextQuota(relayInfo, summary, tieredQuota, tieredRes)
 		}
@@ -451,7 +453,7 @@ func PostTextConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, us
 		// prompt/cache fields here, otherwise old upstream payloads may be double-counted.
 		other["input_tokens_total"] = usage.InputTokens
 	}
-	if tieredResult != nil {
+	if tieredBillingApplied {
 		InjectTieredBillingInfo(other, relayInfo, tieredResult)
 	}
 

service/tiered_settle.go

@@ -22,8 +22,14 @@ func BuildTieredTokenParams(usage *dto.Usage, isClaudeUsageSemantic bool, usedVa
 	p := float64(usage.PromptTokens)
 	c := float64(usage.CompletionTokens)
 	cr := float64(usage.PromptTokensDetails.CachedTokens)
-	ccTotal := float64(usage.PromptTokensDetails.CachedCreationTokens)
-	cc1h := float64(usage.ClaudeCacheCreation1hTokens)
+	cc5m := float64(usage.PromptTokensDetails.CachedCreationTokens)
+	cc1h := float64(0)
+
+	if usage.UsageSemantic == "anthropic" {
+		cc1h = float64(usage.ClaudeCacheCreation1hTokens)
+		cc5m = float64(usage.ClaudeCacheCreation5mTokens)
+	}
+
 	img := float64(usage.PromptTokensDetails.ImageTokens)
 	ai := float64(usage.PromptTokensDetails.AudioTokens)
 	imgO := float64(usage.CompletionTokenDetails.ImageTokens)
@@ -33,8 +39,11 @@ func BuildTieredTokenParams(usage *dto.Usage, isClaudeUsageSemantic bool, usedVa
 		if usedVars["cr"] {
 			p -= cr
 		}
-		if usedVars["cc"] || usedVars["cc1h"] {
-			p -= ccTotal
+		if usedVars["cc"] {
+			p -= cc5m
+		}
+		if usedVars["cc1h"] {
+			p -= cc1h
 		}
 		if usedVars["img"] {
 			p -= img
@@ -61,7 +70,7 @@ func BuildTieredTokenParams(usage *dto.Usage, isClaudeUsageSemantic bool, usedVa
 		P:    p,
 		C:    c,
 		CR:   cr,
-		CC:   ccTotal - cc1h,
+		CC:   cc5m,
 		CC1h: cc1h,
 		Img:  img,
 		ImgO: imgO,