* 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
130 lines
5.1 KiB
Go
130 lines
5.1 KiB
Go
package claude
|
|
|
|
import (
|
|
"testing"
|
|
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/setting/model_setting"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
"github.com/tidwall/gjson"
|
|
)
|
|
|
|
func TestPatchClaudeMessageDeltaUsageDataPreserveUnknownFields(t *testing.T) {
|
|
originalData := `{"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"output_tokens":53},"vendor_meta":{"trace_id":"trace_001"}}`
|
|
usage := &dto.ClaudeUsage{
|
|
InputTokens: 100,
|
|
CacheReadInputTokens: 30,
|
|
CacheCreationInputTokens: 50,
|
|
}
|
|
|
|
patchedData := patchClaudeMessageDeltaUsageData(originalData, usage)
|
|
|
|
require.Equal(t, "message_delta", gjson.Get(patchedData, "type").String())
|
|
require.Equal(t, "end_turn", gjson.Get(patchedData, "delta.stop_reason").String())
|
|
require.Equal(t, "trace_001", gjson.Get(patchedData, "vendor_meta.trace_id").String())
|
|
require.EqualValues(t, 53, gjson.Get(patchedData, "usage.output_tokens").Int())
|
|
require.EqualValues(t, 100, gjson.Get(patchedData, "usage.input_tokens").Int())
|
|
require.EqualValues(t, 30, gjson.Get(patchedData, "usage.cache_read_input_tokens").Int())
|
|
require.EqualValues(t, 50, gjson.Get(patchedData, "usage.cache_creation_input_tokens").Int())
|
|
}
|
|
|
|
func TestPatchClaudeMessageDeltaUsageDataZeroValueChecks(t *testing.T) {
|
|
originalData := `{"type":"message_delta","usage":{"output_tokens":53,"input_tokens":9,"cache_read_input_tokens":0}}`
|
|
usage := &dto.ClaudeUsage{
|
|
InputTokens: 100,
|
|
CacheReadInputTokens: 30,
|
|
CacheCreationInputTokens: 0,
|
|
}
|
|
|
|
patchedData := patchClaudeMessageDeltaUsageData(originalData, usage)
|
|
|
|
require.EqualValues(t, 9, gjson.Get(patchedData, "usage.input_tokens").Int())
|
|
require.EqualValues(t, 30, gjson.Get(patchedData, "usage.cache_read_input_tokens").Int())
|
|
assert.False(t, gjson.Get(patchedData, "usage.cache_creation_input_tokens").Exists())
|
|
}
|
|
|
|
func TestShouldSkipClaudeMessageDeltaUsagePatch(t *testing.T) {
|
|
originGlobalPassThrough := model_setting.GetGlobalSettings().PassThroughRequestEnabled
|
|
t.Cleanup(func() {
|
|
model_setting.GetGlobalSettings().PassThroughRequestEnabled = originGlobalPassThrough
|
|
})
|
|
|
|
model_setting.GetGlobalSettings().PassThroughRequestEnabled = true
|
|
assert.True(t, shouldSkipClaudeMessageDeltaUsagePatch(&relaycommon.RelayInfo{}))
|
|
|
|
model_setting.GetGlobalSettings().PassThroughRequestEnabled = false
|
|
assert.True(t, shouldSkipClaudeMessageDeltaUsagePatch(&relaycommon.RelayInfo{
|
|
ChannelMeta: &relaycommon.ChannelMeta{ChannelSetting: dto.ChannelSettings{PassThroughBodyEnabled: true}},
|
|
}))
|
|
assert.False(t, shouldSkipClaudeMessageDeltaUsagePatch(&relaycommon.RelayInfo{
|
|
ChannelMeta: &relaycommon.ChannelMeta{ChannelSetting: dto.ChannelSettings{PassThroughBodyEnabled: false}},
|
|
}))
|
|
}
|
|
|
|
func TestBuildMessageDeltaPatchUsage(t *testing.T) {
|
|
t.Run("merge missing fields from claudeInfo", func(t *testing.T) {
|
|
claudeResponse := &dto.ClaudeResponse{Usage: &dto.ClaudeUsage{OutputTokens: 53}}
|
|
claudeInfo := &ClaudeResponseInfo{
|
|
Usage: &dto.Usage{
|
|
PromptTokens: 100,
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedTokens: 30,
|
|
CachedCreationTokens: 50,
|
|
},
|
|
ClaudeCacheCreation5mTokens: 10,
|
|
ClaudeCacheCreation1hTokens: 20,
|
|
},
|
|
}
|
|
|
|
usage := buildMessageDeltaPatchUsage(claudeResponse, claudeInfo)
|
|
require.NotNil(t, usage)
|
|
require.EqualValues(t, 100, usage.InputTokens)
|
|
require.EqualValues(t, 30, usage.CacheReadInputTokens)
|
|
require.EqualValues(t, 50, usage.CacheCreationInputTokens)
|
|
require.EqualValues(t, 53, usage.OutputTokens)
|
|
require.NotNil(t, usage.CacheCreation)
|
|
require.EqualValues(t, 30, usage.CacheCreation.Ephemeral5mInputTokens)
|
|
require.EqualValues(t, 20, usage.CacheCreation.Ephemeral1hInputTokens)
|
|
})
|
|
|
|
t.Run("keep upstream non-zero values", func(t *testing.T) {
|
|
claudeResponse := &dto.ClaudeResponse{Usage: &dto.ClaudeUsage{
|
|
InputTokens: 9,
|
|
CacheReadInputTokens: 7,
|
|
CacheCreationInputTokens: 6,
|
|
}}
|
|
claudeInfo := &ClaudeResponseInfo{Usage: &dto.Usage{
|
|
PromptTokens: 100,
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedTokens: 30,
|
|
CachedCreationTokens: 50,
|
|
},
|
|
}}
|
|
|
|
usage := buildMessageDeltaPatchUsage(claudeResponse, claudeInfo)
|
|
require.EqualValues(t, 9, usage.InputTokens)
|
|
require.EqualValues(t, 7, usage.CacheReadInputTokens)
|
|
require.EqualValues(t, 6, usage.CacheCreationInputTokens)
|
|
})
|
|
|
|
t.Run("default aggregate cache creation to 5m when split missing", func(t *testing.T) {
|
|
claudeResponse := &dto.ClaudeResponse{Usage: &dto.ClaudeUsage{
|
|
OutputTokens: 53,
|
|
CacheCreationInputTokens: 50,
|
|
}}
|
|
claudeInfo := &ClaudeResponseInfo{Usage: &dto.Usage{
|
|
PromptTokensDetails: dto.InputTokenDetails{
|
|
CachedCreationTokens: 50,
|
|
},
|
|
}}
|
|
|
|
usage := buildMessageDeltaPatchUsage(claudeResponse, claudeInfo)
|
|
require.NotNil(t, usage)
|
|
require.NotNil(t, usage.CacheCreation)
|
|
require.EqualValues(t, 50, usage.CacheCreation.Ephemeral5mInputTokens)
|
|
require.EqualValues(t, 0, usage.CacheCreation.Ephemeral1hInputTokens)
|
|
})
|
|
}
|