* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
275 lines
8.9 KiB
Go
275 lines
8.9 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/relaykit/types"
|
|
"github.com/QuantumNous/new-api/setting/billing_setting"
|
|
"github.com/QuantumNous/new-api/setting/config"
|
|
"github.com/QuantumNous/new-api/setting/ratio_setting"
|
|
"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{
|
|
BillingRatios: map[string]float64{"n": 3},
|
|
})
|
|
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)
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestModelPriceHelperTieredRejectsPreConsumeOverflow(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-overflow-model":"tiered_expr"}`,
|
|
"billing_setting.billing_expr": `{"tiered-overflow-model":"tier(\"overflow\", p * 1000000000000000)"}`,
|
|
"group_ratio_setting.group_ratio": `{"default":1}`,
|
|
}))
|
|
|
|
recorder := httptest.NewRecorder()
|
|
ctx, _ := gin.CreateTestContext(recorder)
|
|
ctx.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
ctx.Set("group", "default")
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "tiered-overflow-model",
|
|
UserGroup: "default",
|
|
UsingGroup: "default",
|
|
BillingRequestInput: &billingexpr.RequestInput{
|
|
Body: []byte(`{}`),
|
|
},
|
|
}
|
|
|
|
_, err := ModelPriceHelper(ctx, info, 1000, &types.TokenCountMeta{})
|
|
|
|
var clamp *common.QuotaClamp
|
|
require.ErrorAs(t, err, &clamp)
|
|
require.Equal(t, "QuotaRound", clamp.Op)
|
|
require.Equal(t, common.QuotaClampOverflow, clamp.Kind)
|
|
}
|
|
|
|
func TestModelPriceHelperRequestBillingRatiosOnlyApplyToFixedPrice(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
savedModelPrices := ratio_setting.ModelPrice2JSONString()
|
|
savedModelRatios := ratio_setting.ModelRatio2JSONString()
|
|
t.Cleanup(func() {
|
|
require.NoError(t, ratio_setting.UpdateModelPriceByJSONString(savedModelPrices))
|
|
require.NoError(t, ratio_setting.UpdateModelRatioByJSONString(savedModelRatios))
|
|
})
|
|
|
|
modelPrices, err := common.Marshal(map[string]float64{
|
|
"fixed-image-price": 0.04,
|
|
"fractional-image-price": 0.0000012,
|
|
"overflow-image-price": float64(common.MaxQuota) / common.QuotaPerUnit / 2,
|
|
})
|
|
require.NoError(t, err)
|
|
require.NoError(t, ratio_setting.UpdateModelPriceByJSONString(string(modelPrices)))
|
|
modelRatios, err := common.Marshal(map[string]float64{"ratio-image-price": 15})
|
|
require.NoError(t, err)
|
|
require.NoError(t, ratio_setting.UpdateModelRatioByJSONString(string(modelRatios)))
|
|
|
|
tests := []struct {
|
|
name string
|
|
model string
|
|
wantQuota int
|
|
wantUsePrice bool
|
|
wantImageCount bool
|
|
}{
|
|
{
|
|
name: "fixed price applies image count",
|
|
model: "fixed-image-price",
|
|
wantQuota: 180000,
|
|
wantUsePrice: true,
|
|
wantImageCount: true,
|
|
},
|
|
{
|
|
name: "ratio price ignores request billing ratios",
|
|
model: "ratio-image-price",
|
|
wantQuota: 15000,
|
|
wantUsePrice: false,
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
ctx, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
ctx.Set("group", "default")
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: tt.model,
|
|
UserGroup: "default",
|
|
UsingGroup: "default",
|
|
}
|
|
meta := &types.TokenCountMeta{
|
|
ImagePriceRatio: 3,
|
|
BillingRatios: map[string]float64{"n": 3},
|
|
}
|
|
|
|
priceData, err := ModelPriceHelper(ctx, info, 1000, meta)
|
|
|
|
require.NoError(t, err)
|
|
require.Equal(t, tt.wantQuota, priceData.QuotaToPreConsume)
|
|
require.Equal(t, tt.wantUsePrice, priceData.UsePrice)
|
|
require.Equal(t, tt.wantImageCount, priceData.HasOtherRatio("n"))
|
|
require.Equal(t, priceData.OtherRatios(), info.PriceData.OtherRatios())
|
|
})
|
|
}
|
|
|
|
newInfo := func(model string) (*gin.Context, *relaycommon.RelayInfo) {
|
|
ctx, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
ctx.Set("group", "default")
|
|
return ctx, &relaycommon.RelayInfo{
|
|
OriginModelName: model,
|
|
UserGroup: "default",
|
|
UsingGroup: "default",
|
|
}
|
|
}
|
|
meta := &types.TokenCountMeta{BillingRatios: map[string]float64{"n": 3}}
|
|
|
|
ctx, info := newInfo("fractional-image-price")
|
|
priceData, err := ModelPriceHelper(ctx, info, 0, meta)
|
|
require.NoError(t, err)
|
|
// 0.0000012 * 500000 * 3 = 1.8, then truncate once to 1.
|
|
require.Equal(t, 1, priceData.QuotaToPreConsume)
|
|
|
|
ctx, info = newInfo("overflow-image-price")
|
|
_, err = ModelPriceHelper(ctx, info, 0, meta)
|
|
var clamp *common.QuotaClamp
|
|
require.ErrorAs(t, err, &clamp)
|
|
require.Equal(t, "QuotaFromFloat", clamp.Op)
|
|
require.Equal(t, common.QuotaClampOverflow, clamp.Kind)
|
|
require.Nil(t, info.Billing)
|
|
}
|