Files
new-api/model/pricing_endpoint_test.go
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
2026-07-27 15:56:21 +08:00

295 lines
9.9 KiB
Go

package model
import (
"fmt"
"testing"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/relaykit/dto"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func resetPricingEndpointTestTables(t *testing.T) {
t.Helper()
originalMemoryCacheEnabled := common.MemoryCacheEnabled
common.MemoryCacheEnabled = true
require.NoError(t, DB.AutoMigrate(&Channel{}, &Ability{}, &Model{}, &Vendor{}))
for _, table := range []string{"abilities", "channels", "models", "vendors"} {
require.NoError(t, DB.Exec("DELETE FROM "+table).Error)
}
InitChannelCache()
InvalidatePricingCache()
t.Cleanup(func() {
for _, table := range []string{"abilities", "channels", "models", "vendors"} {
require.NoError(t, DB.Exec("DELETE FROM "+table).Error)
}
InitChannelCache()
InvalidatePricingCache()
common.MemoryCacheEnabled = originalMemoryCacheEnabled
})
}
func insertPricingEndpointChannel(t *testing.T, channelID int, channelType int, settings dto.ChannelOtherSettings) {
t.Helper()
channel := &Channel{
Id: channelID,
Type: channelType,
Key: fmt.Sprintf("key-%d", channelID),
Status: common.ChannelStatusEnabled,
Name: fmt.Sprintf("channel-%d", channelID),
}
if settings.AdvancedCustom != nil {
channel.SetOtherSettings(settings)
}
require.NoError(t, DB.Create(channel).Error)
}
func insertPricingEndpointAbility(t *testing.T, channelID int, modelName string) {
t.Helper()
require.NoError(t, DB.Create(&Ability{
Group: "default",
Model: modelName,
ChannelId: channelID,
Enabled: true,
}).Error)
}
func pricingEndpointAdvancedCustomConfig(routes ...dto.AdvancedCustomRoute) dto.ChannelOtherSettings {
return dto.ChannelOtherSettings{
AdvancedCustom: &dto.AdvancedCustomConfig{
Routes: routes,
},
}
}
func pricingEndpointTypesByModel(t *testing.T) map[string][]constant.EndpointType {
t.Helper()
InitChannelCache()
return pricingEndpointTypesFromPricing(GetPricing())
}
func pricingEndpointTypesFromPricing(pricings []Pricing) map[string][]constant.EndpointType {
byModel := make(map[string][]constant.EndpointType)
for _, pricing := range pricings {
byModel[pricing.ModelName] = pricing.SupportedEndpointTypes
}
return byModel
}
func TestPricingAdvancedCustomUsesConfiguredEndpointTypes(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 101, constant.ChannelTypeAdvancedCustom, pricingEndpointAdvancedCustomConfig(
dto.AdvancedCustomRoute{
IncomingPath: "/v1/chat/completions",
UpstreamPath: "/v1/chat/completions",
},
dto.AdvancedCustomRoute{
IncomingPath: "/v1/responses",
UpstreamPath: "/v1beta/models/{model}:generateContent",
Converter: "openai_responses_to_gemini_generate_content",
Models: []string{"re:^gemini-"},
},
))
insertPricingEndpointAbility(t, 101, "gemini-2.5-flash")
insertPricingEndpointAbility(t, 101, "gpt-4o")
byModel := pricingEndpointTypesByModel(t)
assert.Equal(t, []constant.EndpointType{
constant.EndpointTypeOpenAI,
constant.EndpointTypeOpenAIResponse,
}, byModel["gemini-2.5-flash"])
assert.Equal(t, []constant.EndpointType{
constant.EndpointTypeOpenAI,
}, byModel["gpt-4o"])
}
func TestPricingModelMetadataEndpointsMergeWithAdvancedCustomInference(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 103, constant.ChannelTypeAdvancedCustom, pricingEndpointAdvancedCustomConfig(
dto.AdvancedCustomRoute{
IncomingPath: "/v1/responses",
UpstreamPath: "/v1beta/models/{model}:generateContent",
Converter: "openai_responses_to_gemini_generate_content",
Models: []string{"re:^gemini-"},
},
))
insertPricingEndpointAbility(t, 103, "gemini-2.5-flash")
require.NoError(t, DB.Create(&Model{
ModelName: "gemini-2.5-flash",
Endpoints: `{
"openai": "/v1/chat/completions"
}`,
Status: 1,
NameRule: NameRuleExact,
}).Error)
byModel := pricingEndpointTypesByModel(t)
assert.Equal(t, []constant.EndpointType{
constant.EndpointTypeOpenAIResponse,
constant.EndpointTypeOpenAI,
}, byModel["gemini-2.5-flash"])
}
func TestPricingModelMetadataEndpointsCanProvideEndpointWithoutChannelInference(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 104, constant.ChannelTypeAdvancedCustom, pricingEndpointAdvancedCustomConfig(
dto.AdvancedCustomRoute{
IncomingPath: "/v1/responses",
UpstreamPath: "/v1beta/models/{model}:generateContent",
Converter: "openai_responses_to_gemini_generate_content",
Models: []string{"re:^gemini-"},
},
))
insertPricingEndpointAbility(t, 104, "metadata-only-model")
require.NoError(t, DB.Create(&Model{
ModelName: "metadata-only-model",
Endpoints: `{
"openai": "/v1/chat/completions"
}`,
Status: 1,
NameRule: NameRuleExact,
}).Error)
byModel := pricingEndpointTypesByModel(t)
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAI}, byModel["metadata-only-model"])
}
func TestPricingAdvancedCustomMissingConfigFallsBackToChannelType(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 102, constant.ChannelTypeAdvancedCustom, dto.ChannelOtherSettings{})
insertPricingEndpointAbility(t, 102, "gpt-4o")
byModel := pricingEndpointTypesByModel(t)
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAI}, byModel["gpt-4o"])
}
func TestPricingNativeChannelEndpointTypesUnchanged(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 201, constant.ChannelTypeOpenAI, dto.ChannelOtherSettings{})
insertPricingEndpointChannel(t, 202, constant.ChannelTypeGemini, dto.ChannelOtherSettings{})
insertPricingEndpointChannel(t, 203, constant.ChannelTypeAnthropic, dto.ChannelOtherSettings{})
insertPricingEndpointAbility(t, 201, "gpt-4o")
insertPricingEndpointAbility(t, 202, "gemini-2.5-flash")
insertPricingEndpointAbility(t, 203, "claude-3-5-sonnet")
byModel := pricingEndpointTypesByModel(t)
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAI}, byModel["gpt-4o"])
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeGemini, constant.EndpointTypeOpenAI}, byModel["gemini-2.5-flash"])
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeAnthropic, constant.EndpointTypeOpenAI}, byModel["claude-3-5-sonnet"])
}
func TestInitChannelCacheInvalidatesPricingCache(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 301, constant.ChannelTypeAdvancedCustom, pricingEndpointAdvancedCustomConfig(
dto.AdvancedCustomRoute{
IncomingPath: "/v1/chat/completions",
UpstreamPath: "/v1/chat/completions",
},
))
insertPricingEndpointAbility(t, 301, "gemini-3.5-flash")
InitChannelCache()
initial := pricingEndpointTypesByModel(t)
require.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAI}, initial["gemini-3.5-flash"])
var channel Channel
require.NoError(t, DB.First(&channel, "id = ?", 301).Error)
channel.SetOtherSettings(pricingEndpointAdvancedCustomConfig(
dto.AdvancedCustomRoute{
IncomingPath: "/v1/chat/completions",
UpstreamPath: "/v1/chat/completions",
},
dto.AdvancedCustomRoute{
IncomingPath: "/v1/responses",
UpstreamPath: "/v1beta/models/{model}:generateContent",
Converter: "openai_responses_to_gemini_generate_content",
Models: []string{"re:^gemini-"},
},
))
require.NoError(t, DB.Model(&Channel{}).Where("id = ?", 301).Update("settings", channel.OtherSettings).Error)
InitChannelCache()
updated := pricingEndpointTypesByModel(t)
assert.Equal(t, []constant.EndpointType{
constant.EndpointTypeOpenAI,
constant.EndpointTypeOpenAIResponse,
}, updated["gemini-3.5-flash"])
}
func TestInitChannelCacheInvalidatesStartupPricingBuiltBeforeChannelCache(t *testing.T) {
resetPricingEndpointTestTables(t)
insertPricingEndpointChannel(t, 302, constant.ChannelTypeAdvancedCustom, pricingEndpointAdvancedCustomConfig(
dto.AdvancedCustomRoute{
IncomingPath: "/v1/chat/completions",
UpstreamPath: "/v1/chat/completions",
},
dto.AdvancedCustomRoute{
IncomingPath: "/v1/responses",
UpstreamPath: "/v1beta/models/{model}:generateContent",
Converter: "openai_responses_to_gemini_generate_content",
Models: []string{"re:^gemini-"},
},
))
insertPricingEndpointAbility(t, 302, "gemini-3.5-flash")
staleByModel := pricingEndpointTypesFromPricing(GetPricing())
require.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAI}, staleByModel["gemini-3.5-flash"])
InitChannelCache()
rebuiltByModel := pricingEndpointTypesFromPricing(GetPricing())
assert.Equal(t, []constant.EndpointType{
constant.EndpointTypeOpenAI,
constant.EndpointTypeOpenAIResponse,
}, rebuiltByModel["gemini-3.5-flash"])
}
func TestCacheUpdateChannelSyncsAdvancedCustomConfig(t *testing.T) {
resetPricingEndpointTestTables(t)
channel := &Channel{
Id: 401,
Type: constant.ChannelTypeAdvancedCustom,
Key: "key-401",
Status: common.ChannelStatusEnabled,
Name: "channel-401",
}
channel.SetOtherSettings(pricingEndpointAdvancedCustomConfig(dto.AdvancedCustomRoute{
IncomingPath: "/v1/responses",
UpstreamPath: "/v1beta/models/{model}:generateContent",
Converter: "openai_responses_to_gemini_generate_content",
}))
CacheUpdateChannel(channel)
require.NotNil(t, channel2advancedCustomConfig[401])
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAIResponse}, channel2advancedCustomConfig[401].SupportedEndpointTypesForModel("gemini-3.5-flash"))
channel.SetOtherSettings(pricingEndpointAdvancedCustomConfig(dto.AdvancedCustomRoute{
IncomingPath: "/v1/chat/completions",
UpstreamPath: "/v1/chat/completions",
}))
CacheUpdateChannel(channel)
require.NotNil(t, channel2advancedCustomConfig[401])
assert.Equal(t, []constant.EndpointType{constant.EndpointTypeOpenAI}, channel2advancedCustomConfig[401].SupportedEndpointTypesForModel("gemini-3.5-flash"))
channel.Type = constant.ChannelTypeOpenAI
CacheUpdateChannel(channel)
assert.Nil(t, channel2advancedCustomConfig[401])
}