feat: implement tiered billing expression evaluation and related functionality

- Added support for tiered billing expressions in the billing system.
- Introduced new types and functions for handling billing expressions, including caching and execution.
- Updated existing billing logic to accommodate tiered billing scenarios.
- Enhanced request handling to support incoming billing expression requests.
- Added tests for tiered billing functionality to ensure correctness.

relay/helper/billing_expr_request_test.go

@@ -0,0 +1,35 @@
+package helper
+
+import (
+	"bytes"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/QuantumNous/new-api/common"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/gin-gonic/gin"
+	"github.com/stretchr/testify/require"
+)
+
+func TestResolveIncomingBillingExprRequestInput(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	recorder := httptest.NewRecorder()
+	ctx, _ := gin.CreateTestContext(recorder)
+	ctx.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
+	ctx.Request.Header.Set("Content-Type", "application/json")
+
+	body := []byte(`{"service_tier":"fast"}`)
+	ctx.Request.Body = io.NopCloser(bytes.NewReader(body))
+	ctx.Set(common.KeyRequestBody, body)
+
+	info := &relaycommon.RelayInfo{
+		RequestHeaders: map[string]string{"Content-Type": "application/json"},
+	}
+
+	input, err := ResolveIncomingBillingExprRequestInput(ctx, info)
+	require.NoError(t, err)
+	require.Equal(t, body, input.Body)
+	require.Equal(t, "application/json", input.Headers["Content-Type"])
+}