feat: 适配 OpenAI 新模型 gpt-5.6-sol/terra/luna

backend/internal/pkg/openai/constants.go

@@ -18,6 +18,9 @@ type Model struct {
 
 // DefaultModels OpenAI models list
 var DefaultModels = []Model{
+	{ID: "gpt-5.6-sol", Object: "model", Created: 1780876800, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.6 Sol"},
+	{ID: "gpt-5.6-terra", Object: "model", Created: 1780876800, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.6 Terra"},
+	{ID: "gpt-5.6-luna", Object: "model", Created: 1780876800, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.6 Luna"},
 	{ID: "gpt-5.5", Object: "model", Created: 1776873600, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.5"},
 	{ID: "gpt-5.4", Object: "model", Created: 1738368000, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.4"},
 	{ID: "gpt-5.4-mini", Object: "model", Created: 1738368000, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.4 Mini"},

backend/internal/service/billing_service.go

@@ -280,6 +280,11 @@ func (s *BillingService) initFallbackPricing() {
 	s.fallbackPrices["gpt-5.5"] = s.fallbackPrices["gpt-5.4"]
 	s.fallbackPrices["gpt-5.5-pro"] = s.fallbackPrices["gpt-5.4"]
 
+	// GPT-5.6（sol / terra / luna）暂无独立定价，回退到 GPT-5.4。
+	s.fallbackPrices["gpt-5.6-sol"] = s.fallbackPrices["gpt-5.4"]
+	s.fallbackPrices["gpt-5.6-terra"] = s.fallbackPrices["gpt-5.4"]
+	s.fallbackPrices["gpt-5.6-luna"] = s.fallbackPrices["gpt-5.4"]
+
 	s.fallbackPrices["gpt-5.4-mini"] = &ModelPricing{
 		InputPricePerToken:     7.5e-7,
 		OutputPricePerToken:    4.5e-6,
@@ -667,6 +672,12 @@ func (s *BillingService) getFallbackPricing(model string) *ModelPricing {
 	// OpenAI（GPT-5 / Codex 族）：仅匹配已知型号，避免未知 OpenAI 型号误计价。
 	if normalized := normalizeKnownOpenAICodexModel(modelLower); normalized != "" {
 		switch normalized {
+		case "gpt-5.6-sol":
+			return s.fallbackPrices["gpt-5.6-sol"]
+		case "gpt-5.6-terra":
+			return s.fallbackPrices["gpt-5.6-terra"]
+		case "gpt-5.6-luna":
+			return s.fallbackPrices["gpt-5.6-luna"]
 		case "gpt-5.5-pro":
 			return s.fallbackPrices["gpt-5.5-pro"]
 		case "gpt-5.5":
@@ -1060,7 +1071,8 @@ func isOpenAIGPT54Model(model string) bool {
 	// normalizeCodexModel 的默认兜底把非 OpenAI 模型（claude-*、gemini-*、gpt-4o）
 	// 误识别为 gpt-5.4。
 	normalized := normalizeKnownOpenAICodexModel(model)
-	return normalized == "gpt-5.4" || normalized == "gpt-5.5" || normalized == "gpt-5.5-pro"
+	return normalized == "gpt-5.4" || normalized == "gpt-5.5" || normalized == "gpt-5.5-pro" ||
+		normalized == "gpt-5.6-sol" || normalized == "gpt-5.6-terra" || normalized == "gpt-5.6-luna"
 }
 
 // CalculateCostWithConfig 使用配置中的默认倍率计算费用

backend/internal/service/openai_codex_transform.go

@@ -9,6 +9,9 @@ import (
 )
 
 var codexModelMap = map[string]string{
+	"gpt-5.6-sol":          "gpt-5.6-sol",
+	"gpt-5.6-terra":        "gpt-5.6-terra",
+	"gpt-5.6-luna":         "gpt-5.6-luna",
 	"gpt-5.5":              "gpt-5.5",
 	"gpt-5.5-pro":          "gpt-5.5-pro",
 	"codex-auto-review":    "codex-auto-review",
@@ -54,6 +57,9 @@ var codexVersionModelPrefixes = []struct {
 	prefix string
 	target string
 }{
+	{prefix: "gpt-5.6-sol", target: "gpt-5.6-sol"},
+	{prefix: "gpt-5.6-terra", target: "gpt-5.6-terra"},
+	{prefix: "gpt-5.6-luna", target: "gpt-5.6-luna"},
 	{prefix: "gpt-5.3-codex-spark", target: "gpt-5.3-codex-spark"},
 	{prefix: "gpt-5.3-codex", target: "gpt-5.3-codex"},
 	{prefix: "gpt-5.4-mini", target: "gpt-5.4-mini"},

backend/internal/service/openai_model_alias.go

@@ -65,6 +65,12 @@ func normalizeKnownOpenAICodexModel(model string) string {
 	}
 
 	switch {
+	case strings.Contains(normalized, "gpt-5.6-sol"):
+		return "gpt-5.6-sol"
+	case strings.Contains(normalized, "gpt-5.6-terra"):
+		return "gpt-5.6-terra"
+	case strings.Contains(normalized, "gpt-5.6-luna"):
+		return "gpt-5.6-luna"
 	case strings.Contains(normalized, "gpt-5.5-pro"):
 		return "gpt-5.5-pro"
 	case strings.Contains(normalized, "gpt-5.5"):

backend/internal/service/pricing_service.go

@@ -798,6 +798,13 @@ func (s *PricingService) matchOpenAIModel(model string) *LiteLLMModelPricing {
 		}
 	}
 
+	// GPT-5.6（sol / terra / luna）回退到 GPT-5.4 定价
+	if strings.HasPrefix(model, "gpt-5.6") {
+		logger.With(zap.String("component", "service.pricing")).
+			Info(fmt.Sprintf("[Pricing] OpenAI fallback matched %s -> %s", model, "gpt-5.4(static)"))
+		return openAIGPT54FallbackPricing
+	}
+
 	// GPT-5.5 回退到 GPT-5.4 定价
 	if strings.HasPrefix(model, "gpt-5.5") {
 		logger.With(zap.String("component", "service.pricing")).

backend/resources/model-pricing/model_prices_and_context_window.json

@@ -4886,6 +4886,150 @@
     "supports_web_search": true,
     "supports_xhigh_reasoning_effort": true
   },
+  "gpt-5.6-sol": {
+    "cache_read_input_token_cost": 5e-07,
+    "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+    "cache_read_input_token_cost_flex": 2.5e-07,
+    "cache_read_input_token_cost_priority": 1e-06,
+    "input_cost_per_token": 5e-06,
+    "input_cost_per_token_above_272k_tokens": 1e-05,
+    "input_cost_per_token_batches": 2.5e-06,
+    "input_cost_per_token_flex": 2.5e-06,
+    "input_cost_per_token_priority": 1e-05,
+    "litellm_provider": "openai",
+    "max_input_tokens": 1050000,
+    "max_output_tokens": 128000,
+    "max_tokens": 128000,
+    "mode": "chat",
+    "output_cost_per_token": 3e-05,
+    "output_cost_per_token_above_272k_tokens": 4.5e-05,
+    "output_cost_per_token_batches": 1.5e-05,
+    "output_cost_per_token_flex": 1.5e-05,
+    "output_cost_per_token_priority": 6e-05,
+    "supported_endpoints": [
+      "/v1/chat/completions",
+      "/v1/batch",
+      "/v1/responses"
+    ],
+    "supported_modalities": [
+      "text",
+      "image"
+    ],
+    "supported_output_modalities": [
+      "text"
+    ],
+    "supports_function_calling": true,
+    "supports_minimal_reasoning_effort": false,
+    "supports_native_streaming": true,
+    "supports_none_reasoning_effort": true,
+    "supports_parallel_function_calling": true,
+    "supports_pdf_input": true,
+    "supports_prompt_caching": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true,
+    "supports_service_tier": true,
+    "supports_system_messages": true,
+    "supports_tool_choice": true,
+    "supports_vision": true,
+    "supports_web_search": true,
+    "supports_xhigh_reasoning_effort": true
+  },
+  "gpt-5.6-terra": {
+    "cache_read_input_token_cost": 5e-07,
+    "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+    "cache_read_input_token_cost_flex": 2.5e-07,
+    "cache_read_input_token_cost_priority": 1e-06,
+    "input_cost_per_token": 5e-06,
+    "input_cost_per_token_above_272k_tokens": 1e-05,
+    "input_cost_per_token_batches": 2.5e-06,
+    "input_cost_per_token_flex": 2.5e-06,
+    "input_cost_per_token_priority": 1e-05,
+    "litellm_provider": "openai",
+    "max_input_tokens": 1050000,
+    "max_output_tokens": 128000,
+    "max_tokens": 128000,
+    "mode": "chat",
+    "output_cost_per_token": 3e-05,
+    "output_cost_per_token_above_272k_tokens": 4.5e-05,
+    "output_cost_per_token_batches": 1.5e-05,
+    "output_cost_per_token_flex": 1.5e-05,
+    "output_cost_per_token_priority": 6e-05,
+    "supported_endpoints": [
+      "/v1/chat/completions",
+      "/v1/batch",
+      "/v1/responses"
+    ],
+    "supported_modalities": [
+      "text",
+      "image"
+    ],
+    "supported_output_modalities": [
+      "text"
+    ],
+    "supports_function_calling": true,
+    "supports_minimal_reasoning_effort": false,
+    "supports_native_streaming": true,
+    "supports_none_reasoning_effort": true,
+    "supports_parallel_function_calling": true,
+    "supports_pdf_input": true,
+    "supports_prompt_caching": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true,
+    "supports_service_tier": true,
+    "supports_system_messages": true,
+    "supports_tool_choice": true,
+    "supports_vision": true,
+    "supports_web_search": true,
+    "supports_xhigh_reasoning_effort": true
+  },
+  "gpt-5.6-luna": {
+    "cache_read_input_token_cost": 5e-07,
+    "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+    "cache_read_input_token_cost_flex": 2.5e-07,
+    "cache_read_input_token_cost_priority": 1e-06,
+    "input_cost_per_token": 5e-06,
+    "input_cost_per_token_above_272k_tokens": 1e-05,
+    "input_cost_per_token_batches": 2.5e-06,
+    "input_cost_per_token_flex": 2.5e-06,
+    "input_cost_per_token_priority": 1e-05,
+    "litellm_provider": "openai",
+    "max_input_tokens": 1050000,
+    "max_output_tokens": 128000,
+    "max_tokens": 128000,
+    "mode": "chat",
+    "output_cost_per_token": 3e-05,
+    "output_cost_per_token_above_272k_tokens": 4.5e-05,
+    "output_cost_per_token_batches": 1.5e-05,
+    "output_cost_per_token_flex": 1.5e-05,
+    "output_cost_per_token_priority": 6e-05,
+    "supported_endpoints": [
+      "/v1/chat/completions",
+      "/v1/batch",
+      "/v1/responses"
+    ],
+    "supported_modalities": [
+      "text",
+      "image"
+    ],
+    "supported_output_modalities": [
+      "text"
+    ],
+    "supports_function_calling": true,
+    "supports_minimal_reasoning_effort": false,
+    "supports_native_streaming": true,
+    "supports_none_reasoning_effort": true,
+    "supports_parallel_function_calling": true,
+    "supports_pdf_input": true,
+    "supports_prompt_caching": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true,
+    "supports_service_tier": true,
+    "supports_system_messages": true,
+    "supports_tool_choice": true,
+    "supports_vision": true,
+    "supports_web_search": true,
+    "supports_xhigh_reasoning_effort": true
+  },
   "gpt-5.5": {
     "cache_read_input_token_cost": 5e-07,
     "cache_read_input_token_cost_above_272k_tokens": 1e-06,