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
517 lines
15 KiB
Go
517 lines
15 KiB
Go
package gemini
|
|
|
|
import (
|
|
"bytes"
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"testing"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"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 TestGeminiChatHandlerCompletionTokensExcludeToolUsePromptTokens(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
RelayFormat: types.RelayFormatGemini,
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
|
|
payload := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "ok"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 151,
|
|
ToolUsePromptTokenCount: 18329,
|
|
CandidatesTokenCount: 1089,
|
|
ThoughtsTokenCount: 1120,
|
|
TotalTokenCount: 20689,
|
|
},
|
|
}
|
|
|
|
body, err := common.Marshal(payload)
|
|
require.NoError(t, err)
|
|
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
}
|
|
|
|
usage, newAPIError := GeminiChatHandler(c, info, resp)
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 18480, usage.PromptTokens)
|
|
require.Equal(t, 2209, usage.CompletionTokens)
|
|
require.Equal(t, 20689, usage.TotalTokens)
|
|
require.Equal(t, 1120, usage.CompletionTokenDetails.ReasoningTokens)
|
|
}
|
|
|
|
func TestGeminiStreamHandlerCompletionTokensExcludeToolUsePromptTokens(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
oldStreamingTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 300
|
|
t.Cleanup(func() {
|
|
constant.StreamingTimeout = oldStreamingTimeout
|
|
})
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
|
|
chunk := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "partial"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 151,
|
|
ToolUsePromptTokenCount: 18329,
|
|
CandidatesTokenCount: 1089,
|
|
ThoughtsTokenCount: 1120,
|
|
TotalTokenCount: 20689,
|
|
},
|
|
}
|
|
|
|
chunkData, err := common.Marshal(chunk)
|
|
require.NoError(t, err)
|
|
|
|
streamBody := []byte("data: " + string(chunkData) + "\n" + "data: [DONE]\n")
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(streamBody)),
|
|
}
|
|
|
|
usage, newAPIError := geminiStreamHandler(c, info, resp, func(_ string, _ *dto.GeminiChatResponse) bool {
|
|
return true
|
|
})
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 18480, usage.PromptTokens)
|
|
require.Equal(t, 2209, usage.CompletionTokens)
|
|
require.Equal(t, 20689, usage.TotalTokens)
|
|
require.Equal(t, 1120, usage.CompletionTokenDetails.ReasoningTokens)
|
|
}
|
|
|
|
func TestGeminiTextGenerationHandlerPromptTokensIncludeToolUsePromptTokens(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1beta/models/gemini-3-flash-preview:generateContent", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
|
|
payload := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "ok"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 151,
|
|
ToolUsePromptTokenCount: 18329,
|
|
CandidatesTokenCount: 1089,
|
|
ThoughtsTokenCount: 1120,
|
|
TotalTokenCount: 20689,
|
|
},
|
|
}
|
|
|
|
body, err := common.Marshal(payload)
|
|
require.NoError(t, err)
|
|
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
}
|
|
|
|
usage, newAPIError := GeminiTextGenerationHandler(c, info, resp)
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 18480, usage.PromptTokens)
|
|
require.Equal(t, 2209, usage.CompletionTokens)
|
|
require.Equal(t, 20689, usage.TotalTokens)
|
|
require.Equal(t, 1120, usage.CompletionTokenDetails.ReasoningTokens)
|
|
}
|
|
|
|
func TestGeminiChatHandlerUsesEstimatedPromptTokensWhenUsagePromptMissing(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
RelayFormat: types.RelayFormatGemini,
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
info.SetEstimatePromptTokens(20)
|
|
|
|
payload := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "ok"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 0,
|
|
ToolUsePromptTokenCount: 0,
|
|
CandidatesTokenCount: 90,
|
|
ThoughtsTokenCount: 10,
|
|
TotalTokenCount: 110,
|
|
},
|
|
}
|
|
|
|
body, err := common.Marshal(payload)
|
|
require.NoError(t, err)
|
|
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
}
|
|
|
|
usage, newAPIError := GeminiChatHandler(c, info, resp)
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 20, usage.PromptTokens)
|
|
require.Equal(t, 100, usage.CompletionTokens)
|
|
require.Equal(t, 110, usage.TotalTokens)
|
|
}
|
|
|
|
func TestGeminiStreamHandlerUsesEstimatedPromptTokensWhenUsagePromptMissing(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
oldStreamingTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 300
|
|
t.Cleanup(func() {
|
|
constant.StreamingTimeout = oldStreamingTimeout
|
|
})
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
info.SetEstimatePromptTokens(20)
|
|
|
|
chunk := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "partial"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 0,
|
|
ToolUsePromptTokenCount: 0,
|
|
CandidatesTokenCount: 90,
|
|
ThoughtsTokenCount: 10,
|
|
TotalTokenCount: 110,
|
|
},
|
|
}
|
|
|
|
chunkData, err := common.Marshal(chunk)
|
|
require.NoError(t, err)
|
|
|
|
streamBody := []byte("data: " + string(chunkData) + "\n" + "data: [DONE]\n")
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(streamBody)),
|
|
}
|
|
|
|
usage, newAPIError := geminiStreamHandler(c, info, resp, func(_ string, _ *dto.GeminiChatResponse) bool {
|
|
return true
|
|
})
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 20, usage.PromptTokens)
|
|
require.Equal(t, 100, usage.CompletionTokens)
|
|
require.Equal(t, 110, usage.TotalTokens)
|
|
}
|
|
|
|
func TestGeminiTextGenerationHandlerUsesEstimatedPromptTokensWhenUsagePromptMissing(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1beta/models/gemini-3-flash-preview:generateContent", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
info.SetEstimatePromptTokens(20)
|
|
|
|
payload := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "ok"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 0,
|
|
ToolUsePromptTokenCount: 0,
|
|
CandidatesTokenCount: 90,
|
|
ThoughtsTokenCount: 10,
|
|
TotalTokenCount: 110,
|
|
},
|
|
}
|
|
|
|
body, err := common.Marshal(payload)
|
|
require.NoError(t, err)
|
|
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
}
|
|
|
|
usage, newAPIError := GeminiTextGenerationHandler(c, info, resp)
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 20, usage.PromptTokens)
|
|
require.Equal(t, 100, usage.CompletionTokens)
|
|
require.Equal(t, 110, usage.TotalTokens)
|
|
}
|
|
|
|
func TestGeminiChatHandlerMissingUsageMetadataBuildsEstimatedBillingUsage(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
RelayFormat: types.RelayFormatGemini,
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
info.SetEstimatePromptTokens(20)
|
|
|
|
body := []byte(`{"candidates":[{"content":{"role":"model","parts":[{"text":"ok"}]}}]}`)
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
}
|
|
|
|
usage, newAPIError := GeminiChatHandler(c, info, resp)
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 20, usage.PromptTokens)
|
|
require.NotNil(t, usage.BillingUsage)
|
|
require.True(t, usage.BillingUsage.Estimated)
|
|
require.Equal(t, dto.BillingUsageSourceGeminiChat, usage.BillingUsage.Source)
|
|
require.Equal(t, dto.BillingUsageSemanticGemini, usage.BillingUsage.Semantic)
|
|
require.NotNil(t, usage.BillingUsage.GeminiUsageMetadata)
|
|
require.Equal(t, usage.PromptTokens, usage.BillingUsage.GeminiUsageMetadata.PromptTokenCount)
|
|
require.Equal(t, usage.CompletionTokens, usage.BillingUsage.GeminiUsageMetadata.CandidatesTokenCount)
|
|
require.True(t, common.GetContextKeyBool(c, constant.ContextKeyLocalCountTokens))
|
|
}
|
|
|
|
func TestGeminiStreamHandlerPromptOnlyUsageMetadataEstimatesCompletionTokens(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
oldStreamingTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 300
|
|
t.Cleanup(func() {
|
|
constant.StreamingTimeout = oldStreamingTimeout
|
|
})
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
info.SetEstimatePromptTokens(20)
|
|
|
|
// Simulates a client aborting the stream before the final chunk: text was
|
|
// streamed but the last observed usageMetadata only carries prompt tokens.
|
|
chunk := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "partial streamed answer before disconnect"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 151,
|
|
TotalTokenCount: 151,
|
|
},
|
|
}
|
|
|
|
chunkData, err := common.Marshal(chunk)
|
|
require.NoError(t, err)
|
|
|
|
streamBody := []byte("data: " + string(chunkData) + "\n" + "data: [DONE]\n")
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(streamBody)),
|
|
}
|
|
|
|
usage, newAPIError := geminiStreamHandler(c, info, resp, func(_ string, _ *dto.GeminiChatResponse) bool {
|
|
return true
|
|
})
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 151, usage.PromptTokens)
|
|
require.Greater(t, usage.CompletionTokens, 0)
|
|
require.Equal(t, usage.PromptTokens+usage.CompletionTokens, usage.TotalTokens)
|
|
require.NotNil(t, usage.BillingUsage)
|
|
require.True(t, usage.BillingUsage.Estimated)
|
|
require.NotNil(t, usage.BillingUsage.GeminiUsageMetadata)
|
|
require.Equal(t, usage.CompletionTokens, usage.BillingUsage.GeminiUsageMetadata.CandidatesTokenCount)
|
|
}
|
|
|
|
func TestGeminiChatHandlerPromptOnlyUsageMetadataEstimatesCompletionTokens(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
RelayFormat: types.RelayFormatGemini,
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
|
|
payload := dto.GeminiChatResponse{
|
|
Candidates: []dto.GeminiChatCandidate{
|
|
{
|
|
Content: dto.GeminiChatContent{
|
|
Role: "model",
|
|
Parts: []dto.GeminiPart{
|
|
{Text: "answer text without candidate token count"},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
UsageMetadata: dto.GeminiUsageMetadata{
|
|
PromptTokenCount: 151,
|
|
TotalTokenCount: 151,
|
|
},
|
|
}
|
|
|
|
body, err := common.Marshal(payload)
|
|
require.NoError(t, err)
|
|
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(body)),
|
|
}
|
|
|
|
usage, newAPIError := GeminiChatHandler(c, info, resp)
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 151, usage.PromptTokens)
|
|
require.Greater(t, usage.CompletionTokens, 0)
|
|
require.Equal(t, usage.PromptTokens+usage.CompletionTokens, usage.TotalTokens)
|
|
require.NotNil(t, usage.BillingUsage)
|
|
require.True(t, usage.BillingUsage.Estimated)
|
|
}
|
|
|
|
func TestGeminiStreamHandlerEmptyUsageMetadataBuildsEstimatedBillingUsage(t *testing.T) {
|
|
gin.SetMode(gin.TestMode)
|
|
c, _ := gin.CreateTestContext(httptest.NewRecorder())
|
|
c.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
|
|
|
|
oldStreamingTimeout := constant.StreamingTimeout
|
|
constant.StreamingTimeout = 300
|
|
t.Cleanup(func() {
|
|
constant.StreamingTimeout = oldStreamingTimeout
|
|
})
|
|
|
|
info := &relaycommon.RelayInfo{
|
|
OriginModelName: "gemini-3-flash-preview",
|
|
ChannelMeta: &relaycommon.ChannelMeta{
|
|
UpstreamModelName: "gemini-3-flash-preview",
|
|
},
|
|
}
|
|
info.SetEstimatePromptTokens(20)
|
|
|
|
streamBody := []byte("data: {\"candidates\":[{\"content\":{\"role\":\"model\",\"parts\":[{\"text\":\"partial\"}]}}],\"usageMetadata\":{}}\n" + "data: [DONE]\n")
|
|
resp := &http.Response{
|
|
Body: io.NopCloser(bytes.NewReader(streamBody)),
|
|
}
|
|
|
|
usage, newAPIError := geminiStreamHandler(c, info, resp, func(_ string, _ *dto.GeminiChatResponse) bool {
|
|
return true
|
|
})
|
|
require.Nil(t, newAPIError)
|
|
require.NotNil(t, usage)
|
|
require.Equal(t, 20, usage.PromptTokens)
|
|
require.NotNil(t, usage.BillingUsage)
|
|
require.True(t, usage.BillingUsage.Estimated)
|
|
require.Equal(t, dto.BillingUsageSourceGeminiChat, usage.BillingUsage.Source)
|
|
require.NotNil(t, usage.BillingUsage.GeminiUsageMetadata)
|
|
require.Equal(t, usage.PromptTokens, usage.BillingUsage.GeminiUsageMetadata.PromptTokenCount)
|
|
require.Equal(t, usage.CompletionTokens, usage.BillingUsage.GeminiUsageMetadata.CandidatesTokenCount)
|
|
require.True(t, common.GetContextKeyBool(c, constant.ContextKeyLocalCountTokens))
|
|
}
|