hobokenchicken/GopherGate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: correct deepseek pricing, gemini streaming tokens, and group-name logging
CI / Lint (push) Has been cancelled
Details
CI / Test (push) Has been cancelled
Details
CI / Build (push) Has been cancelled
Details

Browse Source 
- Add promo discount system for deepseek-v4-pro (75% off until 2026-05-31)
- Rewrite StreamGemini to handle both SSE and JSON array response formats,
  fixing 0-token logging for gemini-3-flash and gemini-3-flash-preview
- Fall back to model group name for cost lookup when concrete model
  isnt in the registry (fixes $0 cost on deepseek-auto entries)
- Move registry lock before FindModel call to fix data race
This commit is contained in:
newkirk
2026-05-17 19:48:47 -04:00
parent 970e778703
commit 40f055cb57
4 changed files with 253 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/server/server.go
+39 -21
View File
@@ -309,9 +309,32 @@ func (s *Server) handleResponses(c *gin.Context) {
return
}
// Select provider based on model name
// Strip common prefixes and resolve model groups to concrete models
// (same pattern as handleChatCompletions).
modelGroup := ""
modelID := req.Model
prefixes := []string{"gemini/", "google/", "openai/", "deepseek/", "moonshot/", "grok/", "ollama/"}
for _, p := range prefixes {
if strings.HasPrefix(modelID, p) {
modelID = strings.TrimPrefix(modelID, p)
break
}
}
if s.modelRouter != nil {
decision, err := s.modelRouter.RouteToConcrete(c.Request.Context(), modelID, "")
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("model routing failed: %v", err)})
return
}
if decision.SelectedModel != modelID {
modelGroup = modelID
}
modelID = decision.SelectedModel
}
// Select provider based on resolved model name
providerName := "openai" // default for Responses API
modelLower := strings.ToLower(req.Model)
modelLower := strings.ToLower(modelID)
if strings.HasPrefix(modelLower, "gemini/") || strings.Contains(modelLower, "gemini") || strings.HasPrefix(modelLower, "google/") {
providerName = "gemini"
} else if strings.HasPrefix(modelLower, "deepseek/") || (strings.Contains(modelLower, "deepseek") && !strings.Contains(modelLower, "ollama")) {
@@ -339,17 +362,7 @@ func (s *Server) handleResponses(c *gin.Context) {
return
}
// Strip common prefixes from model name
modelID := req.Model
prefixes := []string{"gemini/", "google/", "openai/", "deepseek/", "moonshot/", "grok/", "ollama/"}
for _, p := range prefixes {
if strings.HasPrefix(modelID, p) {
modelID = strings.TrimPrefix(modelID, p)
break
}
}
// Use the stripped model name for the actual API call
// Use resolved model for the actual API call
req.Model = modelID
clientID := "default"
@@ -364,7 +377,7 @@ func (s *Server) handleResponses(c *gin.Context) {
if stream {
ch, err := provider.ResponsesStream(c.Request.Context(), &req)
if err != nil {
s.logRequest(startTime, clientID, providerName, req.Model, "", nil, err, false)
s.logRequest(startTime, clientID, providerName, modelID, modelGroup, nil, err, false)
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
@@ -379,9 +392,9 @@ func (s *Server) handleResponses(c *gin.Context) {
if !ok {
fmt.Fprintf(w, "data: [DONE]\n\n")
if lastUsage != nil {
s.logRequest(startTime, clientID, providerName, req.Model, "", lastUsage.ToUsage(), nil, false)
s.logRequest(startTime, clientID, providerName, modelID, modelGroup, lastUsage.ToUsage(), nil, false)
} else {
s.logRequest(startTime, clientID, providerName, req.Model, "", nil, nil, false)
s.logRequest(startTime, clientID, providerName, modelID, modelGroup, nil, nil, false)
}
return false
}
@@ -401,15 +414,15 @@ func (s *Server) handleResponses(c *gin.Context) {
resp, err := provider.Responses(c.Request.Context(), &req)
if err != nil {
s.logRequest(startTime, clientID, providerName, req.Model, "", nil, err, false)
s.logRequest(startTime, clientID, providerName, modelID, modelGroup, nil, err, false)
c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
return
}
if resp.Usage != nil {
s.logRequest(startTime, clientID, providerName, req.Model, "", resp.Usage.ToUsage(), nil, false)
s.logRequest(startTime, clientID, providerName, modelID, modelGroup, resp.Usage.ToUsage(), nil, false)
} else {
s.logRequest(startTime, clientID, providerName, req.Model, "", nil, nil, false)
s.logRequest(startTime, clientID, providerName, modelID, modelGroup, nil, nil, false)
}
c.JSON(http.StatusOK, resp)
}
@@ -881,9 +894,14 @@ func (s *Server) logRequest(start time.Time, clientID, provider, model, modelGro
entry.CacheWriteTokens = *usage.CacheWriteTokens
}
// Calculate cost using registry
// Calculate cost using registry; if the resolved model is unknown,
// fall back to the model group so group requests still get priced.
s.registryMu.RLock()
entry.Cost = utils.CalculateCost(s.registry, model, entry.PromptTokens, entry.CompletionTokens, entry.ReasoningTokens, entry.CacheReadTokens, entry.CacheWriteTokens)
pricingModel := model
if s.registry != nil && s.registry.FindModel(pricingModel) == nil && modelGroup != "" {
pricingModel = modelGroup
}
entry.Cost = utils.CalculateCost(s.registry, pricingModel, entry.PromptTokens, entry.CompletionTokens, entry.ReasoningTokens, entry.CacheReadTokens, entry.CacheWriteTokens)
s.registryMu.RUnlock()
}