Calcium-Ion
c36418c863
* refactor: consolidate relay protocol converters * refactor relayconvert text converters * feat: refine relay converters and advanced custom routing * refactor: enhance logging and add thought signature handling for Gemini requests * refactor: enhance channel cache and pricing endpoint handling for advanced custom models * feat: preserve billing usage semantics * feat: add protocol-aware billing usage * Delete useless files * chore: update action versions in workflow files * chore: update Docker action versions in workflow files * fix: harden billing usage settlement and hot-path route matching - estimate Gemini completion tokens locally when billable usageMetadata is prompt-only but output content was received (e.g. client aborts the stream before the final chunk), and rebuild the attached billing_usage as estimated so settlement does not bill zero output tokens - guard NewClaudeMessagesBillingUsage against all-zero ClaudeUsage, matching the OpenAI/Gemini constructors, so a zero billing_usage cannot override a non-zero top-level usage during settlement - cache compiled advanced-custom route model regexes; they run on the request hot path and were recompiled per request - move the effectiveBillingUsage remap to PostTextConsumeQuota only, and document that calculateTextQuotaSummary expects remapped usage - document the updatePricingLock -> channelSyncLock lock ordering that InitChannelCache/CacheUpdateChannel rely on, and the aux-struct pitfall in GeminiChatResponse.UnmarshalJSON
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"
|
|
"github.com/QuantumNous/new-api/dto"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/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))
|
|
}
|