Files
new-api/relay/helper/price_test.go
T

141 lines
4.5 KiB
Go

package helper
import (
"net/http"
"net/http/httptest"
"testing"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/pkg/billingexpr"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/setting/billing_setting"
"github.com/QuantumNous/new-api/setting/config"
"github.com/QuantumNous/new-api/types"
"github.com/gin-gonic/gin"
"github.com/stretchr/testify/require"
)
func TestModelPriceHelperTieredUsesPreloadedRequestInput(t *testing.T) {
gin.SetMode(gin.TestMode)
saved := map[string]string{}
require.NoError(t, config.GlobalConfig.SaveToDB(func(key, value string) error {
saved[key] = value
return nil
}))
t.Cleanup(func() {
require.NoError(t, config.GlobalConfig.LoadFromDB(saved))
})
require.NoError(t, config.GlobalConfig.LoadFromDB(map[string]string{
"billing_setting.billing_mode": `{"tiered-test-model":"tiered_expr"}`,
"billing_setting.billing_expr": `{"tiered-test-model":"param(\"stream\") == true ? tier(\"stream\", p * 3) : tier(\"base\", p * 2)"}`,
}))
recorder := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(recorder)
req := httptest.NewRequest(http.MethodPost, "/api/channel/test/1", nil)
req.Body = nil
req.ContentLength = 0
req.Header.Set("Content-Type", "application/json")
ctx.Request = req
ctx.Set("group", "default")
info := &relaycommon.RelayInfo{
OriginModelName: "tiered-test-model",
UserGroup: "default",
UsingGroup: "default",
RequestHeaders: map[string]string{"Content-Type": "application/json"},
BillingRequestInput: &billingexpr.RequestInput{
Headers: map[string]string{"Content-Type": "application/json"},
Body: []byte(`{"stream":true}`),
},
}
priceData, err := ModelPriceHelper(ctx, info, 1000, &types.TokenCountMeta{})
require.NoError(t, err)
require.Equal(t, 1500, priceData.QuotaToPreConsume)
require.NotNil(t, info.TieredBillingSnapshot)
require.Equal(t, "stream", info.TieredBillingSnapshot.EstimatedTier)
require.Equal(t, billing_setting.BillingModeTieredExpr, info.TieredBillingSnapshot.BillingMode)
require.Equal(t, common.QuotaPerUnit, info.TieredBillingSnapshot.QuotaPerUnit)
}
func TestModelPriceHelperTieredPreConsumeMaxTokensFallback(t *testing.T) {
gin.SetMode(gin.TestMode)
saved := map[string]string{}
require.NoError(t, config.GlobalConfig.SaveToDB(func(key, value string) error {
saved[key] = value
return nil
}))
t.Cleanup(func() {
require.NoError(t, config.GlobalConfig.LoadFromDB(saved))
})
require.NoError(t, config.GlobalConfig.LoadFromDB(map[string]string{
"billing_setting.billing_mode": `{"tiered-fallback-model":"tiered_expr"}`,
"billing_setting.billing_expr": `{"tiered-fallback-model":"tier(\"base\", p * 3 + c * 15)"}`,
"group_ratio_setting.group_ratio": `{"default":1,"free":0}`,
}))
const promptTokens = 1000
cases := []struct {
name string
group string
maxTokens int
expected int
}{
{
// max_tokens omitted in a paid group -> fall back to 8192 completion tokens.
// p*3 + c*15 = 1000*3 + 8192*15 = 125880 -> /1e6 * 500000 = 62940
name: "non-free group falls back to 8192 completion tokens",
group: "default",
maxTokens: 0,
expected: 62940,
},
{
// explicit max_tokens is used verbatim, no fallback.
// 1000*3 + 100*15 = 4500 -> /1e6 * 500000 = 2250
name: "explicit max_tokens is used verbatim",
group: "default",
maxTokens: 100,
expected: 2250,
},
{
// free group (ratio 0) stays zero; fallback is gated on non-zero group ratio.
name: "free group stays zero without fallback",
group: "free",
maxTokens: 0,
expected: 0,
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
recorder := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(recorder)
req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
req.Header.Set("Content-Type", "application/json")
ctx.Request = req
ctx.Set("group", tc.group)
info := &relaycommon.RelayInfo{
OriginModelName: "tiered-fallback-model",
UserGroup: tc.group,
UsingGroup: tc.group,
RequestHeaders: map[string]string{"Content-Type": "application/json"},
BillingRequestInput: &billingexpr.RequestInput{
Headers: map[string]string{"Content-Type": "application/json"},
Body: []byte(`{}`),
},
}
priceData, err := ModelPriceHelper(ctx, info, promptTokens, &types.TokenCountMeta{MaxTokens: tc.maxTokens})
require.NoError(t, err)
require.Equal(t, tc.expected, priceData.QuotaToPreConsume)
})
}
}