Merge origin/main into nightly

Resolve conflicts:
- .gitignore: keep nightly additions (.test, skills-lock.json)
- relay/helper/price.go: keep both billingexpr and model imports
- en.json / zh-CN.json: keep nightly's superset of i18n entries
- service/billing_session.go: add missing 3rd arg to DecreaseUserQuota
- en.json / zh-CN.json: deduplicate 129+320 duplicate i18n keys

dto/channel_settings.go

@@ -30,6 +30,7 @@ type ChannelOtherSettings struct {
 	ClaudeBetaQuery                       bool          `json:"claude_beta_query,omitempty"`         // Claude 渠道是否强制追加 ?beta=true
 	AllowServiceTier                      bool          `json:"allow_service_tier,omitempty"`        // 是否允许 service_tier 透传（默认过滤以避免额外计费）
 	AllowInferenceGeo                     bool          `json:"allow_inference_geo,omitempty"`       // 是否允许 inference_geo 透传（仅 Claude，默认过滤以满足数据驻留合规
+	AllowSpeed                            bool          `json:"allow_speed,omitempty"`               // 是否允许 speed 透传（仅 Claude，默认过滤以避免意外切换推理速度模式）
 	AllowSafetyIdentifier                 bool          `json:"allow_safety_identifier,omitempty"`   // 是否允许 safety_identifier 透传（默认过滤以保护用户隐私）
 	DisableStore                          bool          `json:"disable_store,omitempty"`             // 是否禁用 store 透传（默认允许透传，禁用后可能导致 Codex 无法使用）
 	AllowIncludeObfuscation               bool          `json:"allow_include_obfuscation,omitempty"` // 是否允许 stream_options.include_obfuscation 透传（默认过滤以避免关闭流混淆保护）

dto/claude.go

@@ -204,10 +204,11 @@ type ClaudeToolChoice struct {
 }
 
 type ClaudeRequest struct {
-	Model    string          `json:"model"`
-	Prompt   string          `json:"prompt,omitempty"`
-	System   any             `json:"system,omitempty"`
-	Messages []ClaudeMessage `json:"messages,omitempty"`
+	Model        string          `json:"model"`
+	Prompt       string          `json:"prompt,omitempty"`
+	System       any             `json:"system,omitempty"`
+	Messages     []ClaudeMessage `json:"messages,omitempty"`
+	CacheControl json.RawMessage `json:"cache_control,omitempty"`
 	// InferenceGeo controls Claude data residency region.
 	// This field is filtered by default and can be enabled via channel setting allow_inference_geo.
 	InferenceGeo      string          `json:"inference_geo,omitempty"`
@@ -227,6 +228,9 @@ type ClaudeRequest struct {
 	Thinking          *Thinking       `json:"thinking,omitempty"`
 	McpServers        json.RawMessage `json:"mcp_servers,omitempty"`
 	Metadata          json.RawMessage `json:"metadata,omitempty"`
+	// Speed specifies the Claude inference speed mode.
+	// This field is filtered by default and can be enabled via channel setting allow_speed.
+	Speed json.RawMessage `json:"speed,omitempty"`
 	// ServiceTier specifies upstream service level and may affect billing.
 	// This field is filtered by default and can be enabled via channel setting allow_service_tier.
 	ServiceTier string `json:"service_tier,omitempty"`
@@ -444,6 +448,11 @@ func ProcessTools(tools []any) ([]*Tool, []*ClaudeWebSearchTool) {
 type Thinking struct {
 	Type         string `json:"type,omitempty"`
 	BudgetTokens *int   `json:"budget_tokens,omitempty"`
+	// Display controls whether thinking content is returned in the response.
+	// Used with adaptive thinking on Claude Opus 4.7+: "summarized" restores
+	// the visible summary that was default on Opus 4.6; "omitted" (default on
+	// 4.7) suppresses it. Pass-through field from upstream Anthropic API.
+	Display string `json:"display,omitempty"`
 }
 
 func (c *Thinking) GetBudgetTokens() int {

dto/gemini.go

@@ -46,6 +46,7 @@ func (r *GeminiChatRequest) UnmarshalJSON(data []byte) error {
 type ToolConfig struct {
 	FunctionCallingConfig *FunctionCallingConfig `json:"functionCallingConfig,omitempty"`
 	RetrievalConfig       *RetrievalConfig       `json:"retrievalConfig,omitempty"`
+	IncludeServerSideToolInvocations *bool       `json:"includeServerSideToolInvocations,omitempty"`
 }
 
 type FunctionCallingConfig struct {

dto/openai_response.go

@@ -273,7 +273,7 @@ type OpenAIResponsesResponse struct {
 	Status             json.RawMessage    `json:"status"`
 	Error              any                `json:"error,omitempty"`
 	IncompleteDetails  *IncompleteDetails `json:"incomplete_details,omitempty"`
-	Instructions       string             `json:"instructions"`
+	Instructions       json.RawMessage    `json:"instructions"`
 	MaxOutputTokens    int                `json:"max_output_tokens"`
 	Model              string             `json:"model"`
 	Output             []ResponsesOutput  `json:"output"`

dto/values.go

@@ -5,6 +5,28 @@ import (
 	"strconv"
 )
 
+type StringValue string
+
+func (s *StringValue) UnmarshalJSON(data []byte) error {
+	var str string
+	if err := json.Unmarshal(data, &str); err == nil {
+		*s = StringValue(str)
+		return nil
+	}
+
+	var raw json.Number
+	if err := json.Unmarshal(data, &raw); err == nil {
+		*s = StringValue(raw.String())
+		return nil
+	}
+
+	return json.Unmarshal(data, &str)
+}
+
+func (s StringValue) MarshalJSON() ([]byte, error) {
+	return json.Marshal(string(s))
+}
+
 type IntValue int
 
 func (i *IntValue) UnmarshalJSON(b []byte) error {