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
94 lines
3.2 KiB
Go
94 lines
3.2 KiB
Go
package gemini
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
"github.com/QuantumNous/new-api/dto"
|
|
"github.com/QuantumNous/new-api/logger"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relay/helper"
|
|
"github.com/QuantumNous/new-api/service"
|
|
"github.com/QuantumNous/new-api/types"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
func GeminiTextGenerationHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
defer service.CloseResponseBodyGracefully(resp)
|
|
|
|
// 读取响应体
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
|
|
logger.LogDebug(c, "Gemini native response body: %s", responseBody)
|
|
|
|
// 解析为 Gemini 原生响应格式
|
|
var geminiResponse dto.GeminiChatResponse
|
|
err = common.Unmarshal(responseBody, &geminiResponse)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
|
|
if len(geminiResponse.Candidates) == 0 && geminiResponse.PromptFeedback != nil && geminiResponse.PromptFeedback.BlockReason != nil {
|
|
common.SetContextKey(c, constant.ContextKeyAdminRejectReason, fmt.Sprintf("gemini_block_reason=%s", *geminiResponse.PromptFeedback.BlockReason))
|
|
}
|
|
|
|
// 计算使用量（优先上游 UsageMetadata，缺失时本地估算并保留 Gemini 计费语义）
|
|
usage := buildUsageFromGeminiResponse(c, info, &geminiResponse)
|
|
|
|
service.IOCopyBytesGracefully(c, resp, responseBody)
|
|
|
|
return &usage, nil
|
|
}
|
|
|
|
func NativeGeminiEmbeddingHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.Usage, *types.NewAPIError) {
|
|
defer service.CloseResponseBodyGracefully(resp)
|
|
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
|
|
logger.LogDebug(c, "Gemini native embedding response body: %s", responseBody)
|
|
|
|
usage := service.ResponseText2Usage(c, "", info.UpstreamModelName, info.GetEstimatePromptTokens())
|
|
|
|
if info.IsGeminiBatchEmbedding {
|
|
var geminiResponse dto.GeminiBatchEmbeddingResponse
|
|
err = common.Unmarshal(responseBody, &geminiResponse)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
} else {
|
|
var geminiResponse dto.GeminiEmbeddingResponse
|
|
err = common.Unmarshal(responseBody, &geminiResponse)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
}
|
|
|
|
service.IOCopyBytesGracefully(c, resp, responseBody)
|
|
|
|
return usage, nil
|
|
}
|
|
|
|
func GeminiTextGenerationStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
helper.SetEventStreamHeaders(c)
|
|
|
|
return geminiStreamHandler(c, info, resp, func(data string, geminiResponse *dto.GeminiChatResponse) bool {
|
|
err := helper.StringData(c, data)
|
|
if err != nil {
|
|
logger.LogError(c, "failed to write stream data: "+err.Error())
|
|
return false
|
|
}
|
|
info.SendResponseCount++
|
|
return true
|
|
})
|
|
}
|