Merge branch 'QuantumNous:main' into fix-claude-haiku

setting/model_setting/gemini.go

@@ -4,7 +4,7 @@ import (
 	"github.com/QuantumNous/new-api/setting/config"
 )
 
-// GeminiSettings 定义Gemini模型的配置
+// GeminiSettings defines Gemini model configuration. 注意bool要以enabled结尾才可以生效编辑
 type GeminiSettings struct {
 	SafetySettings                        map[string]string `json:"safety_settings"`
 	VersionSettings                       map[string]string `json:"version_settings"`
@@ -12,6 +12,7 @@ type GeminiSettings struct {
 	ThinkingAdapterEnabled                bool              `json:"thinking_adapter_enabled"`
 	ThinkingAdapterBudgetTokensPercentage float64           `json:"thinking_adapter_budget_tokens_percentage"`
 	FunctionCallThoughtSignatureEnabled   bool              `json:"function_call_thought_signature_enabled"`
+	RemoveFunctionResponseIdEnabled       bool              `json:"remove_function_response_id_enabled"`
 }
 
 // 默认配置
@@ -30,6 +31,7 @@ var defaultGeminiSettings = GeminiSettings{
 	ThinkingAdapterEnabled:                false,
 	ThinkingAdapterBudgetTokensPercentage: 0.6,
 	FunctionCallThoughtSignatureEnabled:   true,
+	RemoveFunctionResponseIdEnabled:       true,
 }
 
 // 全局实例

setting/ratio_setting/cache_ratio.go

@@ -43,6 +43,7 @@ var defaultCacheRatio = map[string]float64{
 	"claude-3-opus-20240229":              0.1,
 	"claude-3-haiku-20240307":             0.1,
 	"claude-3-5-haiku-20241022":           0.1,
+	"claude-haiku-4-5-20251001":           0.1,
 	"claude-3-5-sonnet-20240620":          0.1,
 	"claude-3-5-sonnet-20241022":          0.1,
 	"claude-3-7-sonnet-20250219":          0.1,
@@ -64,6 +65,7 @@ var defaultCreateCacheRatio = map[string]float64{
 	"claude-3-opus-20240229":              1.25,
 	"claude-3-haiku-20240307":             1.25,
 	"claude-3-5-haiku-20241022":           1.25,
+	"claude-haiku-4-5-20251001":           1.25,
 	"claude-3-5-sonnet-20240620":          1.25,
 	"claude-3-5-sonnet-20241022":          1.25,
 	"claude-3-7-sonnet-20250219":          1.25,

setting/ratio_setting/model_ratio.go

@@ -7,7 +7,6 @@ import (
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/setting/operation_setting"
-	"github.com/QuantumNous/new-api/setting/reasoning"
 )
 
 // from songquanpeng/one-api
@@ -137,6 +136,7 @@ var defaultModelRatio = map[string]float64{
 	"claude-2.1":                                4,     // $8 / 1M tokens
 	"claude-3-haiku-20240307":                   0.125, // $0.25 / 1M tokens
 	"claude-3-5-haiku-20241022":                 0.5,   // $1 / 1M tokens
+	"claude-haiku-4-5-20251001":                 0.5,   // $1 / 1M tokens
 	"claude-3-sonnet-20240229":                  1.5,   // $3 / 1M tokens
 	"claude-3-5-sonnet-20240620":                1.5,
 	"claude-3-5-sonnet-20241022":                1.5,
@@ -297,6 +297,7 @@ var defaultModelPrice = map[string]float64{
 	"mj_upload":                      0.05,
 	"sora-2":                         0.3,
 	"sora-2-pro":                     0.5,
+	"gpt-4o-mini-tts":                0.3,
 }
 
 var defaultAudioRatio = map[string]float64{
@@ -304,11 +305,13 @@ var defaultAudioRatio = map[string]float64{
 	"gpt-4o-mini-audio-preview":    66.67,
 	"gpt-4o-realtime-preview":      8,
 	"gpt-4o-mini-realtime-preview": 16.67,
+	"gpt-4o-mini-tts":              25,
 }
 
 var defaultAudioCompletionRatio = map[string]float64{
 	"gpt-4o-realtime":      2,
 	"gpt-4o-mini-realtime": 2,
+	"gpt-4o-mini-tts":      1,
 }
 
 var (
@@ -536,7 +539,10 @@ func getHardcodedCompletionModelRatio(name string) (float64, bool) {
 			if name == "gpt-4o-2024-05-13" {
 				return 3, true
 			}
-			return 4, true
+			if strings.HasPrefix(name, "gpt-4o-mini-tts") {
+				return 20, false
+			}
+			return 4, false
 		}
 		// gpt-5 匹配
 		if strings.HasPrefix(name, "gpt-5") {
@@ -823,10 +829,6 @@ func FormatMatchingModelName(name string) string {
 		name = handleThinkingBudgetModel(name, "gemini-2.5-pro", "gemini-2.5-pro-thinking-*")
 	}
 
-	if base, _, ok := reasoning.TrimEffortSuffix(name); ok {
-		name = base
-	}
-
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}

setting/reasoning/suffix.go

@@ -6,7 +6,7 @@ import (
 	"github.com/samber/lo"
 )
 
-var EffortSuffixes = []string{"-high", "-medium", "-low"}
+var EffortSuffixes = []string{"-high", "-medium", "-low", "-minimal"}
 
 // TrimEffortSuffix -> modelName level(low) exists
 func TrimEffortSuffix(modelName string) (string, string, bool) {

setting/system_setting/discord.go

@@ -3,9 +3,9 @@ package system_setting
 import "github.com/QuantumNous/new-api/setting/config"
 
 type DiscordSettings struct {
-	Enabled               bool   `json:"enabled"`
-	ClientId              string `json:"client_id"`
-	ClientSecret          string `json:"client_secret"`
+	Enabled      bool   `json:"enabled"`
+	ClientId     string `json:"client_id"`
+	ClientSecret string `json:"client_secret"`
 }
 
 // 默认配置