Calcium-Ion
86ac0f7745
* 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
106 lines
3.4 KiB
Go
106 lines
3.4 KiB
Go
package service
|
|
|
|
import (
|
|
"fmt"
|
|
"net/http/httptest"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func buildChannelAffinityStatsContextForTest(ruleName, usingGroup, keyFP string) *gin.Context {
|
|
rec := httptest.NewRecorder()
|
|
ctx, _ := gin.CreateTestContext(rec)
|
|
setChannelAffinityContext(ctx, channelAffinityMeta{
|
|
CacheKey: fmt.Sprintf("test:%s:%s:%s", ruleName, usingGroup, keyFP),
|
|
TTLSeconds: 600,
|
|
RuleName: ruleName,
|
|
UsingGroup: usingGroup,
|
|
KeyFingerprint: keyFP,
|
|
})
|
|
return ctx
|
|
}
|
|
|
|
func TestObserveChannelAffinityUsageCacheByRelayFormat_ClaudeMode(t *testing.T) {
|
|
ruleName := fmt.Sprintf("rule_%d", time.Now().UnixNano())
|
|
usingGroup := "default"
|
|
keyFP := fmt.Sprintf("fp_%d", time.Now().UnixNano())
|
|
ctx := buildChannelAffinityStatsContextForTest(ruleName, usingGroup, keyFP)
|
|
|
|
usage := &dto.Usage{
|
|
PromptTokens: 100,
|
|
CompletionTokens: 40,
|
|
TotalTokens: 140,
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedTokens: 30,
|
|
},
|
|
}
|
|
|
|
ObserveChannelAffinityUsageCacheByRelayFormat(ctx, usage, types.RelayFormatClaude)
|
|
stats := GetChannelAffinityUsageCacheStats(ruleName, usingGroup, keyFP)
|
|
|
|
require.EqualValues(t, 1, stats.Total)
|
|
require.EqualValues(t, 1, stats.Hit)
|
|
require.EqualValues(t, 100, stats.PromptTokens)
|
|
require.EqualValues(t, 40, stats.CompletionTokens)
|
|
require.EqualValues(t, 140, stats.TotalTokens)
|
|
require.EqualValues(t, 30, stats.CachedTokens)
|
|
require.Equal(t, cacheTokenRateModeCachedOverPromptPlusCached, stats.CachedTokenRateMode)
|
|
}
|
|
|
|
func TestObserveChannelAffinityUsageCacheByRelayFormat_MixedMode(t *testing.T) {
|
|
ruleName := fmt.Sprintf("rule_%d", time.Now().UnixNano())
|
|
usingGroup := "default"
|
|
keyFP := fmt.Sprintf("fp_%d", time.Now().UnixNano())
|
|
ctx := buildChannelAffinityStatsContextForTest(ruleName, usingGroup, keyFP)
|
|
|
|
openAIUsage := &dto.Usage{
|
|
PromptTokens: 100,
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedTokens: 10,
|
|
},
|
|
}
|
|
claudeUsage := &dto.Usage{
|
|
PromptTokens: 80,
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedTokens: 20,
|
|
},
|
|
}
|
|
|
|
ObserveChannelAffinityUsageCacheByRelayFormat(ctx, openAIUsage, types.RelayFormatOpenAI)
|
|
ObserveChannelAffinityUsageCacheByRelayFormat(ctx, claudeUsage, types.RelayFormatClaude)
|
|
stats := GetChannelAffinityUsageCacheStats(ruleName, usingGroup, keyFP)
|
|
|
|
require.EqualValues(t, 2, stats.Total)
|
|
require.EqualValues(t, 2, stats.Hit)
|
|
require.EqualValues(t, 180, stats.PromptTokens)
|
|
require.EqualValues(t, 30, stats.CachedTokens)
|
|
require.Equal(t, cacheTokenRateModeMixed, stats.CachedTokenRateMode)
|
|
}
|
|
|
|
func TestObserveChannelAffinityUsageCacheByRelayFormat_UnsupportedModeKeepsEmpty(t *testing.T) {
|
|
ruleName := fmt.Sprintf("rule_%d", time.Now().UnixNano())
|
|
usingGroup := "default"
|
|
keyFP := fmt.Sprintf("fp_%d", time.Now().UnixNano())
|
|
ctx := buildChannelAffinityStatsContextForTest(ruleName, usingGroup, keyFP)
|
|
|
|
usage := &dto.Usage{
|
|
PromptTokens: 100,
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedTokens: 25,
|
|
},
|
|
}
|
|
|
|
ObserveChannelAffinityUsageCacheByRelayFormat(ctx, usage, types.RelayFormatGemini)
|
|
stats := GetChannelAffinityUsageCacheStats(ruleName, usingGroup, keyFP)
|
|
|
|
require.EqualValues(t, 1, stats.Total)
|
|
require.EqualValues(t, 1, stats.Hit)
|
|
require.EqualValues(t, 25, stats.CachedTokens)
|
|
require.Equal(t, "", stats.CachedTokenRateMode)
|
|
}
|