Files
sub2api/backend/internal/handler/openai_alpha_search.go
T
William DrakeandClaude Opus 5.5 52c123e6f4 fix(billing): hold inflight reservation until billing lands; price estimate like billing; wire remaining endpoints
Address gaps found in adversarial verification of the in-flight balance
reservation:

- Early release: the reservation is now a ref-counted handle carried on the
  request context. Billing tasks submitted via submit*UsageRecordTask take a
  ref and return it only after RecordUsage has run; with reservation enabled
  the balance cache is deducted synchronously inside the billing task, so the
  reservation is released only after admission can see the deduction. Dropped
  tasks return their ref immediately. The reservation is renewed every ttl/3
  while the handler runs; after the handler returns it is no longer renewed,
  so the post-handler hold is bounded by one TTL.
- Estimate: use the same billing model (channel mapping + BillingModelSource,
  max over requested/mapped when ambiguous) and ModelPricingResolver (group
  ModelPricing incl. wildcards, channel per_request/image/video/token
  overrides), default/group/user rate + peak multiplier, plus image, video,
  audio and search surcharge kinds. Unpriced requests fail open with a
  throttled log; new billing.inflight_reservation.fail_closed_on_unpriced
  (default false) rejects them instead.
- Wire images, embeddings, web/x search, alpha search, grok media generation,
  grok realtime/voice, OpenAI-platform /v1/messages and ResponsesWebSocket
  (session-level reservation with renewal).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 16:14:43 -04:00

326 lines
13 KiB
Go

package handler
import (
"context"
"errors"
"net/http"
"strconv"
"strings"
"time"
pkghttputil "github.com/Wei-Shaw/sub2api/internal/pkg/httputil"
"github.com/Wei-Shaw/sub2api/internal/pkg/ip"
"github.com/Wei-Shaw/sub2api/internal/pkg/logger"
middleware2 "github.com/Wei-Shaw/sub2api/internal/server/middleware"
"github.com/Wei-Shaw/sub2api/internal/service"
"github.com/gin-gonic/gin"
"github.com/tidwall/gjson"
"go.uber.org/zap"
)
// AlphaSearch proxies the standalone search endpoint used by Codex Responses Lite.
func (h *OpenAIGatewayHandler) AlphaSearch(c *gin.Context) {
streamStarted := false
defer h.recoverResponsesPanic(c, &streamStarted)
setOpenAIClientTransportHTTP(c)
requestStart := time.Now()
apiKey, ok := middleware2.GetAPIKeyFromContext(c)
if !ok || apiKey.Group == nil {
h.errorResponse(c, http.StatusUnauthorized, "authentication_error", "Invalid API key")
return
}
if apiKey.Group.Platform != service.PlatformOpenAI && apiKey.Group.Platform != service.PlatformComposite {
h.errorResponse(c, http.StatusNotFound, "not_found_error", "Codex alpha search is only available for OpenAI and Composite groups")
return
}
subject, ok := middleware2.GetAuthSubjectFromContext(c)
if !ok {
h.errorResponse(c, http.StatusInternalServerError, "api_error", "User context not found")
return
}
reqLog := requestLogger(
c,
"handler.openai_gateway.alpha_search",
zap.Int64("user_id", subject.UserID),
zap.Int64("api_key_id", apiKey.ID),
zap.Any("group_id", apiKey.GroupID),
)
if !h.ensureResponsesDependencies(c, reqLog) {
return
}
body, err := pkghttputil.ReadRequestBodyWithPrealloc(c.Request)
if err != nil {
if maxErr, ok := extractMaxBytesError(err); ok {
h.errorResponse(c, http.StatusRequestEntityTooLarge, "invalid_request_error", buildBodyTooLargeMessage(maxErr.Limit))
return
}
h.errorResponse(c, http.StatusBadRequest, "invalid_request_error", "Failed to read request body")
return
}
if len(body) == 0 {
h.errorResponse(c, http.StatusBadRequest, "invalid_request_error", "Request body is empty")
return
}
if !gjson.ValidBytes(body) {
logRequestBodyParseFailure(reqLog, body, nil)
h.errorResponse(c, http.StatusBadRequest, "invalid_request_error", "Failed to parse request body")
return
}
modelResult := gjson.GetBytes(body, "model")
if !modelResult.Exists() || modelResult.Type != gjson.String || strings.TrimSpace(modelResult.String()) == "" {
h.errorResponse(c, http.StatusBadRequest, "invalid_request_error", "model is required")
return
}
requestedModel := strings.TrimSpace(modelResult.String())
if !compositeTargetPlatformAllowed(c, apiKey, requestedModel, service.PlatformOpenAI) {
h.errorResponse(c, http.StatusNotFound, "not_found_error", "Codex alpha search only supports OpenAI models for Composite groups")
return
}
reqLog = reqLog.With(zap.String("model", requestedModel))
setOpsRequestContext(c, requestedModel, false)
setOpsEndpointContext(c, "", int16(service.RequestTypeSync))
if decision := h.checkSecurityAudit(c, reqLog, apiKey, subject, "openai_alpha_search", requestedModel, body); decision != nil && !decision.AllowNextStage {
h.openAISecurityAuditError(c, decision)
return
}
channelMapping, _ := h.gatewayService.ResolveChannelMappingAndRestrict(c.Request.Context(), apiKey.GroupID, requestedModel)
forwardBody := openAIModelMappedBody(body, channelMapping.Mapped, channelMapping.MappedModel, h.gatewayService.ReplaceModelInBody)
subscription, _ := middleware2.GetSubscriptionFromContext(c)
service.SetOpsLatencyMs(c, service.OpsAuthLatencyMsKey, time.Since(requestStart).Milliseconds())
userRelease, acquired := h.acquireResponsesUserSlot(c, subject.UserID, subject.Concurrency, false, &streamStarted, reqLog)
if !acquired {
return
}
if userRelease != nil {
defer userRelease()
}
if err := h.billingCacheService.CheckBillingEligibility(c.Request.Context(), apiKey.User, apiKey, apiKey.Group, subscription, service.QuotaPlatform(c.Request.Context(), apiKey)); err != nil {
status, code, message, retryAfter := billingErrorDetails(err)
if retryAfter > 0 {
c.Header("Retry-After", strconv.Itoa(retryAfter))
}
h.errorResponse(c, status, code, message)
return
}
// 余额模式在途预留(与计费同口径估算;计费任务扣减余额缓存后才释放)。
inflightDone, inflightErr := reserveInflightBalance(c, h.billingCacheService, h.gatewayService, apiKey, subscription, service.InflightEstimateRequest{Model: requestedModel, BodyBytes: len(body), MaxTokens: requestMaxOutputTokens(body), Kind: service.InflightEstimateToken, SearchCalls: 1})
if inflightErr != nil {
status, code, message, retryAfter := billingErrorDetails(inflightErr)
if retryAfter > 0 {
c.Header("Retry-After", strconv.Itoa(retryAfter))
}
h.errorResponse(c, status, code, message)
return
}
defer inflightDone()
searchID := strings.TrimSpace(gjson.GetBytes(body, "id").String())
sessionHash := h.gatewayService.GenerateSessionHashWithFallback(c, nil, searchID)
profitVetoCount := 0
failedAccountIDs := make(map[int64]struct{})
sameAccountRetryCount := make(map[int64]int)
var lastFailoverErr *service.UpstreamFailoverError
switchCount := 0
var oauth429FailoverState service.OpenAIOAuth429FailoverState
routingStart := time.Now()
// 分组利润控制:alpha search 文本入口请求级装门并固定 pricingAt
//(记录路径经 service.OpenAIPricingAtFromContext 从请求 ctx 回读)。
asPricingCtx, _ := h.gatewayService.WithOpenAIRequestPricingContext(c.Request.Context(), apiKey.GroupID)
c.Request = c.Request.WithContext(asPricingCtx)
for {
selection, _, err := h.gatewayService.SelectAccountWithSchedulerForCapability(
c.Request.Context(),
apiKey.GroupID,
"",
sessionHash,
requestedModel,
failedAccountIDs,
service.OpenAIUpstreamTransportHTTPSSE,
service.OpenAIEndpointCapabilityAlphaSearch,
false,
false,
false,
service.PlatformOpenAI,
)
if err != nil || selection == nil || selection.Account == nil {
if failoverClientGone(c) {
reqLog.Info("openai_alpha_search.account_select_aborted_client_disconnected", zap.Error(err))
return
}
if len(failedAccountIDs) == 0 {
cls := classifyNoAccountErrorFromGin(c, h.gatewayService, apiKey, requestedModel, requestedModel, service.PlatformOpenAI)
if !cls.ModelNotFound {
markOpsRoutingCapacityLimitedIfNoAvailable(c, err)
}
h.errorResponse(c, cls.Status, cls.ErrType, cls.Message)
return
}
if lastFailoverErr != nil {
h.handleFailoverExhausted(c, lastFailoverErr, false)
} else {
h.errorResponse(c, http.StatusBadGateway, "upstream_error", "Upstream request failed")
}
return
}
account := selection.Account
setOpsSelectedAccount(c, account.ID, account.Platform)
accountRelease, slotResult := h.acquireResponsesAccountSlot(c, apiKey.GroupID, sessionHash, selection, false, &streamStarted, reqLog)
if slotResult == openAISlotAcquireProfitVetoed {
// 利润终检否决:排除该账号重新选号;否决次数达上限则按无可用账号终止。
if !recordOpenAIProfitVeto(failedAccountIDs, account.ID, &profitVetoCount) {
h.handleOpenAIProfitVetoExhausted(c, streamStarted, reqLog, profitVetoCount)
return
}
continue
}
if slotResult != openAISlotAcquireOK {
return
}
service.SetOpsLatencyMs(c, service.OpsRoutingLatencyMsKey, time.Since(routingStart).Milliseconds())
writerSizeBeforeForward := c.Writer.Size()
forwardStart := time.Now()
var result *service.OpenAIForwardResult
result, err = func() (*service.OpenAIForwardResult, error) {
if accountRelease != nil {
defer accountRelease()
}
return h.gatewayService.ForwardAlphaSearch(c.Request.Context(), c, account, forwardBody)
}()
service.SetOpsLatencyMs(c, service.OpsResponseLatencyMsKey, time.Since(forwardStart).Milliseconds())
if err == nil {
h.gatewayService.ReportOpenAIAccountScheduleResult(account, openAIAccountScheduleModel(c, account, requestedModel, false, result), true, nil)
if result != nil {
h.recordAlphaSearchUsage(c, apiKey, account, subscription, channelMapping, requestedModel, body, result, subject.UserID)
}
return
}
var failoverErr *service.UpstreamFailoverError
if !errors.As(err, &failoverErr) {
h.gatewayService.ReportOpenAIAccountScheduleResult(account, openAIAccountScheduleModel(c, account, requestedModel, false, result), false, nil, err)
if failoverClientGone(c) {
reqLog.Info("openai_alpha_search.forward_aborted_client_disconnected", zap.Int64("account_id", account.ID), zap.Error(err))
return
}
if c.Writer.Size() == writerSizeBeforeForward {
h.errorResponse(c, http.StatusBadGateway, "upstream_error", "Upstream request failed")
}
reqLog.Warn("openai_alpha_search.forward_failed", zap.Int64("account_id", account.ID), zap.Error(err))
return
}
h.gatewayService.ReportOpenAIAccountScheduleResult(account, openAIAccountScheduleModel(c, account, requestedModel, false, result), false, nil, err)
if c.Writer.Size() != writerSizeBeforeForward {
h.handleFailoverExhausted(c, failoverErr, true)
return
}
if failoverClientGone(c) {
reqLog.Info("openai_alpha_search.failover_aborted_client_disconnected",
zap.Int64("account_id", account.ID),
zap.Int("upstream_status", failoverErr.StatusCode),
)
return
}
if failoverErr.RetryableOnSameAccount {
retryLimit := account.GetPoolModeRetryCount()
if sameAccountRetryAllowed(failoverErr, sameAccountRetryCount[account.ID], retryLimit) {
sameAccountRetryCount[account.ID]++
retryDelay := sameAccountRetryDelayFor(failoverErr, sameAccountRetryCount[account.ID])
reqLog.Warn("openai_alpha_search.same_account_retry",
zap.Int64("account_id", account.ID),
zap.Int("upstream_status", failoverErr.StatusCode),
zap.Int("retry_limit", retryLimit),
zap.Int("retry_count", sameAccountRetryCount[account.ID]),
zap.Duration("retry_delay", retryDelay),
)
select {
case <-c.Request.Context().Done():
return
case <-time.After(retryDelay):
}
continue
}
}
h.gatewayService.RecordOpenAIAccountSwitch()
failedAccountIDs[account.ID] = struct{}{}
lastFailoverErr = failoverErr
if switchCount >= h.maxAccountSwitches {
h.handleFailoverExhausted(c, failoverErr, false)
return
}
switchCount++
if h.gatewayService.ShouldStopOpenAIOAuth429Failover(account, failoverErr.StatusCode, switchCount, &oauth429FailoverState) {
h.handleFailoverExhausted(c, failoverErr, false)
return
}
reqLog.Warn("openai_alpha_search.upstream_failover_switching",
zap.Int64("account_id", account.ID),
zap.Int("upstream_status", failoverErr.StatusCode),
zap.Int("switch_count", switchCount),
)
}
}
// recordAlphaSearchUsage 为一次成功的 alpha/search 网页搜索落按次计费用量行
// (上游不返回 usage 字段,按 WebSearchCalls 走分组单价 × 倍率的按次口径)。
// 与 images 一致使用 mandatory 池提交,池满时同步兜底执行,保证扣费不丢。
func (h *OpenAIGatewayHandler) recordAlphaSearchUsage(
c *gin.Context,
apiKey *service.APIKey,
account *service.Account,
subscription *service.UserSubscription,
channelMapping service.ChannelMappingResult,
requestedModel string,
body []byte,
result *service.OpenAIForwardResult,
userID int64,
) {
userAgent := c.GetHeader("User-Agent")
clientIP := ip.GetClientIP(c)
sessionID := service.ExtractClientSessionID(c)
requestPayloadHash := service.HashUsageRequestPayload(body)
inboundEndpoint := GetInboundEndpoint(c)
upstreamEndpoint := GetUpstreamEndpoint(c, account.Platform)
quotaPlatform := service.QuotaPlatform(c.Request.Context(), apiKey)
h.submitMandatoryUsageRecordTask(c.Request.Context(), func(ctx context.Context) {
if err := h.gatewayService.RecordUsage(ctx, &service.OpenAIRecordUsageInput{
Result: result,
APIKey: apiKey,
User: apiKey.User,
Account: account,
Subscription: subscription,
InboundEndpoint: inboundEndpoint,
UpstreamEndpoint: upstreamEndpoint,
UserAgent: userAgent,
IPAddress: clientIP,
RequestPayloadHash: requestPayloadHash,
APIKeyService: h.apiKeyService,
QuotaPlatform: quotaPlatform,
SessionID: sessionID,
ChannelUsageFields: channelMapping.ToUsageFields(requestedModel, result.UpstreamModel),
PricingAt: service.OpenAIPricingAtFromContext(c.Request.Context()),
}); err != nil {
logger.L().With(
zap.String("component", "handler.openai_gateway.alpha_search"),
zap.Int64("user_id", userID),
zap.Int64("api_key_id", apiKey.ID),
zap.Any("group_id", apiKey.GroupID),
zap.String("model", requestedModel),
zap.Int64("account_id", account.ID),
).Error("openai_alpha_search.record_usage_failed", zap.Error(err))
}
})
}