Merge pull request #186 from router-for-me/doc

docs: add AI Studio setup

README.md

@@ -23,6 +23,7 @@ Chinese providers have now been added: [Qwen Code](https://github.com/QwenLM/qwe
 - Multiple accounts with round-robin load balancing (Gemini, OpenAI, Claude, Qwen and iFlow)
 - Simple CLI authentication flows (Gemini, OpenAI, Claude, Qwen and iFlow)
 - Generative Language API Key support
+- AI Studio Build multi-account load balancing
 - Gemini CLI multi-account load balancing
 - Claude Code multi-account load balancing
 - Qwen Code multi-account load balancing
@@ -68,6 +69,14 @@ brew install cliproxyapi
 brew services start cliproxyapi
 ```
 
+### Installation via CLIProxyAPI Linux Installer
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/brokechubb/cliproxyapi-installer/refs/heads/master/cliproxyapi-installer | bash
+```
+
+Thanks to [brokechubb](https://github.com/brokechubb) for building the Linux installer!
+
 ## Usage
 
 ### GUI Client & Official WebUI
@@ -260,12 +269,16 @@ console.log(await claudeResponse.json());
 - gemini-2.5-flash-lite
 - gemini-2.5-flash-image
 - gemini-2.5-flash-image-preview
+- gemini-pro-latest
+- gemini-flash-latest
+- gemini-flash-lite-latest
 - gpt-5
 - gpt-5-codex
 - claude-opus-4-1-20250805
 - claude-opus-4-20250514
 - claude-sonnet-4-20250514
 - claude-sonnet-4-5-20250929
+- claude-haiku-4-5-20251001
 - claude-3-7-sonnet-20250219
 - claude-3-5-haiku-20241022
 - qwen3-coder-plus
@@ -277,7 +290,6 @@ console.log(await claudeResponse.json());
 - deepseek-r1
 - deepseek-v3
 - kimi-k2
-- glm-4.5
 - glm-4.6
 - tstars2.0
 - And other iFlow-supported models
@@ -415,7 +427,7 @@ openai-compatibility:
     # api-keys:
     #   - "sk-or-v1-...b780"
     #   - "sk-or-v1-...b781"
-    models: # The models supported by the provider.
+    models: # The models supported by the provider. Or you can use a format such as openrouter://moonshotai/kimi-k2:free to request undefined models
       - name: "moonshotai/kimi-k2:free" # The actual model name.
         alias: "kimi-k2" # The alias used in the API.
 ```
@@ -510,28 +522,37 @@ openai-compatibility:
         alias: "kimi-k2"
 ```
 
-Legacy format (still supported):
-
-```yaml
-openai-compatibility:
-  - name: "openrouter"
-    base-url: "https://openrouter.ai/api/v1"
-    api-keys:
-      - "sk-or-v1-...b780"
-      - "sk-or-v1-...b781"
-    models:
-      - name: "moonshotai/kimi-k2:free"
-        alias: "kimi-k2"
-```
-
 Usage: 
 
 Call OpenAI's endpoint `/v1/chat/completions` with `model` set to the alias (e.g., `kimi-k2`). The proxy routes to the configured provider/model automatically.
 
-Also, you may call Claude's endpoint `/v1/messages`, Gemini's `/v1beta/models/model-name:streamGenerateContent` or `/v1beta/models/model-name:generateContent`.
-
 And you can always use Gemini CLI with `CODE_ASSIST_ENDPOINT` set to `http://127.0.0.1:8317` for these OpenAI-compatible provider's models.
 
+### AI Studio Instructions
+
+You can use this service (CLIProxyAPI) as a backend for [this AI Studio App](https://aistudio.google.com/apps/drive/1CPW7FpWGsDZzkaYgYOyXQ_6FWgxieLmL). Follow the steps below to configure it:
+
+1.  **Start the CLIProxyAPI Service**: Ensure your CLIProxyAPI instance is running, either locally or remotely.
+2.  **Access the AI Studio App**: Log in to your Google account in your browser, then open the following link:
+    - [https://aistudio.google.com/apps/drive/1CPW7FpWGsDZzkaYgYOyXQ_6FWgxieLmL](https://aistudio.google.com/apps/drive/1CPW7FpWGsDZzkaYgYOyXQ_6FWgxieLmL)
+
+#### Connection Configuration
+
+By default, the AI Studio App attempts to connect to a local CLIProxyAPI instance at `ws://127.0.0.1:8317`.
+
+-   **Connecting to a Remote Service**:
+    If you need to connect to a remotely deployed CLIProxyAPI, modify the `config.ts` file in the AI Studio App to update the `WEBSOCKET_PROXY_URL` value.
+    -   Use the `wss://` protocol if your remote service has SSL enabled.
+    -   Use the `ws://` protocol if SSL is not enabled.
+
+#### Authentication Configuration
+
+By default, WebSocket connections to CLIProxyAPI do not require authentication.
+
+-   **Enable Authentication on the CLIProxyAPI Server**:
+    In your `config.yaml` file, set `ws_auth` to `true`.
+-   **Configure Authentication on the AI Studio Client**:
+    In the `config.ts` file of the AI Studio App, set the `JWT_TOKEN` value to your authentication token.
 
 ### Authentication Directory
 

README_CN.md

@@ -43,6 +43,7 @@
 - 多账户支持与轮询负载均衡（Gemini、OpenAI、Claude、Qwen 与 iFlow）
 - 简单的 CLI 身份验证流程（Gemini、OpenAI、Claude、Qwen 与 iFlow）
 - 支持 Gemini AIStudio API 密钥
+- 支持 AI Studio Build 多账户轮询
 - 支持 Gemini CLI 多账户轮询
 - 支持 Claude Code 多账户轮询
 - 支持 Qwen Code 多账户轮询
@@ -82,6 +83,14 @@ brew install cliproxyapi
 brew services start cliproxyapi
 ```
 
+### 通过 CLIProxyAPI Linux Installer 安装
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/brokechubb/cliproxyapi-installer/refs/heads/master/cliproxyapi-installer | bash
+```
+
+感谢 [brokechubb](https://github.com/brokechubb) 构建了 Linux installer！
+
 ## 使用方法
 
 ### 图形客户端与官方 WebUI
@@ -273,12 +282,16 @@ console.log(await claudeResponse.json());
 - gemini-2.5-flash-lite
 - gemini-2.5-flash-image
 - gemini-2.5-flash-image-preview
+- gemini-pro-latest
+- gemini-flash-latest
+- gemini-flash-lite-latest
 - gpt-5
 - gpt-5-codex
 - claude-opus-4-1-20250805
 - claude-opus-4-20250514
 - claude-sonnet-4-20250514
 - claude-sonnet-4-5-20250929
+- claude-haiku-4-5-20251001
 - claude-3-7-sonnet-20250219
 - claude-3-5-haiku-20241022
 - qwen3-coder-plus
@@ -290,7 +303,6 @@ console.log(await claudeResponse.json());
 - deepseek-r1
 - deepseek-v3
 - kimi-k2
-- glm-4.5
 - glm-4.6
 - tstars2.0
 - 以及其他 iFlow 支持的模型
@@ -428,7 +440,7 @@ openai-compatibility:
     # api-keys:
     #   - "sk-or-v1-...b780"
     #   - "sk-or-v1-...b781"
-    models: # 提供商支持的模型。
+    models: # 提供商支持的模型。或者你可以使用类似 openrouter://moonshotai/kimi-k2:free 这样的格式来请求未在这里定义的模型
       - name: "moonshotai/kimi-k2:free" # 实际的模型名称。
         alias: "kimi-k2" # 在API中使用的别名。
 ```
@@ -523,24 +535,36 @@ openai-compatibility:
         alias: "kimi-k2"
 ```
 
-旧格式（仍支持）：
-
-```yaml
-openai-compatibility:
-  - name: "openrouter"
-    base-url: "https://openrouter.ai/api/v1"
-    api-keys:
-      - "sk-or-v1-...b780"
-      - "sk-or-v1-...b781"
-    models:
-      - name: "moonshotai/kimi-k2:free"
-        alias: "kimi-k2"
-```
-
 使用方式：在 `/v1/chat/completions` 中将 `model` 设为别名（如 `kimi-k2`），代理将自动路由到对应提供商与模型。
 
 并且，对于这些与OpenAI兼容的提供商模型，您始终可以通过将CODE_ASSIST_ENDPOINT设置为 http://127.0.0.1:8317 来使用Gemini CLI。
 
+### AI Studio 使用说明
+
+您可以将本服务 (CLIProxyAPI) 作为后端，配合 [这个 AI Studio 应用](https://aistudio.google.com/apps/drive/1CPW7FpWGsDZzkaYgYOyXQ_6FWgxieLmL) 使用。请遵循以下步骤进行配置：
+
+1.  **启动 CLIProxyAPI 服务**：确保您的 CLIProxyAPI 实例正在本地或远程运行。
+2.  **访问 AI Studio 应用**：在浏览器中登录您的 Google 账户，然后打开以下链接：
+    - [https://aistudio.google.com/apps/drive/1CPW7FpWGsDZzkaYgYOyXQ_6FWgxieLmL](https://aistudio.google.com/apps/drive/1CPW7FpWGsDZzkaYgYOyXQ_6FWgxieLmL)
+
+#### 连接配置
+
+默认情况下，AI Studio 应用会尝试连接到本地的 CLIProxyAPI (`ws://127.0.0.1:8317`)。
+
+-   **连接到远程服务**：
+    如果您需要连接到远程部署的 CLIProxyAPI，请修改 AI Studio 应用中的 `config.ts` 文件，更新 `WEBSOCKET_PROXY_URL` 的值。
+    -   如果您的远程服务启用了 SSL，请使用 `wss://` 协议。
+    -   如果未启用 SSL，请使用 `ws://` 协议。
+
+#### 认证配置
+
+默认情况下，CLIProxyAPI 的 WebSocket 连接不要求认证。
+
+-   **在 CLIProxyAPI 服务端启用认证**：
+    在您的 `config.yaml` 文件中，将 `ws_auth` 设置为 `true`。
+-   **在 AI Studio 客户端配置认证**：
+    在 AI Studio 应用的 `config.ts` 文件中，设置 `JWT_TOKEN` 的值为您的认证令牌。
+
 ### 身份验证目录
 
 `auth-dir` 参数指定身份验证令牌的存储位置。当您运行登录命令时，应用程序将在此目录中创建包含 Google 账户身份验证令牌的 JSON 文件。多个账户可用于轮询。

examples/custom-provider/main.go

@@ -146,6 +146,10 @@ func (MyExecutor) ExecuteStream(ctx context.Context, a *coreauth.Auth, req clipe
 	return ch, nil
 }
 
+func (MyExecutor) CountTokens(ctx context.Context, a *coreauth.Auth, req clipexec.Request, opts clipexec.Options) (clipexec.Response, error) {
+	return clipexec.Response{}, errors.New("not implemented")
+}
+
 func (MyExecutor) Refresh(ctx context.Context, a *coreauth.Auth) (*coreauth.Auth, error) {
 	return a, nil
 }

go.mod

@@ -28,6 +28,7 @@ require (
 	cloud.google.com/go/compute/metadata v0.3.0 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/ProtonMail/go-crypto v1.3.0 // indirect
+	github.com/andybalholm/brotli v1.0.6 // indirect
 	github.com/bytedance/sonic v1.11.6 // indirect
 	github.com/bytedance/sonic/loader v0.1.1 // indirect
 	github.com/cloudflare/circl v1.6.1 // indirect

go.sum

@@ -4,6 +4,8 @@ github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERo
 github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
 github.com/ProtonMail/go-crypto v1.3.0 h1:ILq8+Sf5If5DCpHQp4PbZdS1J7HDFRXz/+xKBiRGFrw=
 github.com/ProtonMail/go-crypto v1.3.0/go.mod h1:9whxjD8Rbs29b4XWbB8irEcE8KHMqaR2e7GWU1R+/PE=
+github.com/andybalholm/brotli v1.0.6 h1:Yf9fFpf49Zrxb9NlQaluyE92/+X7UVHlhMNJN2sxfOI=
+github.com/andybalholm/brotli v1.0.6/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig=
 github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
 github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
 github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio=

internal/api/server.go

@@ -225,9 +225,13 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
 	envManagementSecret := envAdminPasswordSet && envAdminPassword != ""
 
 	// Create server instance
+	providerNames := make([]string, 0, len(cfg.OpenAICompatibility))
+	for _, p := range cfg.OpenAICompatibility {
+		providerNames = append(providerNames, p.Name)
+	}
 	s := &Server{
 		engine:              engine,
-		handlers:            handlers.NewBaseAPIHandlers(&cfg.SDKConfig, authManager),
+		handlers:            handlers.NewBaseAPIHandlers(&cfg.SDKConfig, authManager, providerNames),
 		cfg:                 cfg,
 		accessManager:       accessManager,
 		requestLogger:       requestLogger,
@@ -823,6 +827,13 @@ func (s *Server) UpdateClients(cfg *config.Config) {
 	managementasset.SetCurrentConfig(cfg)
 	// Save YAML snapshot for next comparison
 	s.oldConfigYaml, _ = yaml.Marshal(cfg)
+
+	providerNames := make([]string, 0, len(cfg.OpenAICompatibility))
+	for _, p := range cfg.OpenAICompatibility {
+		providerNames = append(providerNames, p.Name)
+	}
+	s.handlers.OpenAICompatProviders = providerNames
+
 	s.handlers.UpdateClients(&cfg.SDKConfig)
 
 	if !cfg.RemoteManagement.DisableControlPanel {
@@ -903,5 +914,3 @@ func AuthMiddleware(manager *sdkaccess.Manager) gin.HandlerFunc {
 		}
 	}
 }
-
-// legacy clientsToSlice removed; handlers no longer consume legacy client slices

internal/logging/request_logger.go

@@ -15,6 +15,10 @@ import (
 	"strings"
 	"time"
 
+	"github.com/andybalholm/brotli"
+	"github.com/klauspost/compress/zstd"
+	log "github.com/sirupsen/logrus"
+
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 )
@@ -411,6 +415,10 @@ func (l *FileRequestLogger) decompressResponse(responseHeaders map[string][]stri
 		return l.decompressGzip(response)
 	case "deflate":
 		return l.decompressDeflate(response)
+	case "br":
+		return l.decompressBrotli(response)
+	case "zstd":
+		return l.decompressZstd(response)
 	default:
 		// No compression or unsupported compression
 		return response, nil
@@ -431,7 +439,9 @@ func (l *FileRequestLogger) decompressGzip(data []byte) ([]byte, error) {
 		return nil, fmt.Errorf("failed to create gzip reader: %w", err)
 	}
 	defer func() {
-		_ = reader.Close()
+		if errClose := reader.Close(); errClose != nil {
+			log.WithError(errClose).Warn("failed to close gzip reader in request logger")
+		}
 	}()
 
 	decompressed, err := io.ReadAll(reader)
@@ -453,7 +463,9 @@ func (l *FileRequestLogger) decompressGzip(data []byte) ([]byte, error) {
 func (l *FileRequestLogger) decompressDeflate(data []byte) ([]byte, error) {
 	reader := flate.NewReader(bytes.NewReader(data))
 	defer func() {
-		_ = reader.Close()
+		if errClose := reader.Close(); errClose != nil {
+			log.WithError(errClose).Warn("failed to close deflate reader in request logger")
+		}
 	}()
 
 	decompressed, err := io.ReadAll(reader)
@@ -464,6 +476,48 @@ func (l *FileRequestLogger) decompressDeflate(data []byte) ([]byte, error) {
 	return decompressed, nil
 }
 
+// decompressBrotli decompresses brotli-encoded data.
+//
+// Parameters:
+//   - data: The brotli-encoded data to decompress
+//
+// Returns:
+//   - []byte: The decompressed data
+//   - error: An error if decompression fails, nil otherwise
+func (l *FileRequestLogger) decompressBrotli(data []byte) ([]byte, error) {
+	reader := brotli.NewReader(bytes.NewReader(data))
+
+	decompressed, err := io.ReadAll(reader)
+	if err != nil {
+		return nil, fmt.Errorf("failed to decompress brotli data: %w", err)
+	}
+
+	return decompressed, nil
+}
+
+// decompressZstd decompresses zstd-encoded data.
+//
+// Parameters:
+//   - data: The zstd-encoded data to decompress
+//
+// Returns:
+//   - []byte: The decompressed data
+//   - error: An error if decompression fails, nil otherwise
+func (l *FileRequestLogger) decompressZstd(data []byte) ([]byte, error) {
+	decoder, err := zstd.NewReader(bytes.NewReader(data))
+	if err != nil {
+		return nil, fmt.Errorf("failed to create zstd reader: %w", err)
+	}
+	defer decoder.Close()
+
+	decompressed, err := io.ReadAll(decoder)
+	if err != nil {
+		return nil, fmt.Errorf("failed to decompress zstd data: %w", err)
+	}
+
+	return decompressed, nil
+}
+
 // formatRequestInfo creates the request information section of the log.
 //
 // Parameters:

internal/registry/model_definitions.go

@@ -68,84 +68,8 @@ func GetClaudeModels() []*ModelInfo {
 	}
 }
 
-// GetGeminiModels returns the standard Gemini model definitions
-func GetGeminiModels() []*ModelInfo {
-	return []*ModelInfo{
-		{
-			ID:                         "gemini-2.5-flash",
-			Object:                     "model",
-			Created:                    time.Now().Unix(),
-			OwnedBy:                    "google",
-			Type:                       "gemini",
-			Name:                       "models/gemini-2.5-flash",
-			Version:                    "001",
-			DisplayName:                "Gemini 2.5 Flash",
-			Description:                "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
-			InputTokenLimit:            1048576,
-			OutputTokenLimit:           65536,
-			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
-		},
-		{
-			ID:                         "gemini-2.5-pro",
-			Object:                     "model",
-			Created:                    time.Now().Unix(),
-			OwnedBy:                    "google",
-			Type:                       "gemini",
-			Name:                       "models/gemini-2.5-pro",
-			Version:                    "2.5",
-			DisplayName:                "Gemini 2.5 Pro",
-			Description:                "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
-			InputTokenLimit:            1048576,
-			OutputTokenLimit:           65536,
-			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
-		},
-		{
-			ID:                         "gemini-2.5-flash-lite",
-			Object:                     "model",
-			Created:                    time.Now().Unix(),
-			OwnedBy:                    "google",
-			Type:                       "gemini",
-			Name:                       "models/gemini-2.5-flash-lite",
-			Version:                    "2.5",
-			DisplayName:                "Gemini 2.5 Flash Lite",
-			Description:                "Stable release (June 17th, 2025) of Gemini 2.5 Flash Lite",
-			InputTokenLimit:            1048576,
-			OutputTokenLimit:           65536,
-			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
-		},
-		{
-			ID:                         "gemini-2.5-flash-image-preview",
-			Object:                     "model",
-			Created:                    time.Now().Unix(),
-			OwnedBy:                    "google",
-			Type:                       "gemini",
-			Name:                       "models/gemini-2.5-flash-image-preview",
-			Version:                    "2.5",
-			DisplayName:                "Gemini 2.5 Flash Image Preview",
-			Description:                "State-of-the-art image generation and editing model.",
-			InputTokenLimit:            1048576,
-			OutputTokenLimit:           8192,
-			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
-		},
-		{
-			ID:                         "gemini-2.5-flash-image",
-			Object:                     "model",
-			Created:                    time.Now().Unix(),
-			OwnedBy:                    "google",
-			Type:                       "gemini",
-			Name:                       "models/gemini-2.5-flash-image",
-			Version:                    "2.5",
-			DisplayName:                "Gemini 2.5 Flash Image",
-			Description:                "State-of-the-art image generation and editing model.",
-			InputTokenLimit:            1048576,
-			OutputTokenLimit:           8192,
-			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
-		},
-	}
-}
-
-// GetGeminiCLIModels returns the standard Gemini model definitions
-func GetGeminiCLIModels() []*ModelInfo {
+// GeminiModels returns the shared base Gemini model set used by multiple providers.
+func GeminiModels() []*ModelInfo {
 	return []*ModelInfo{
 		{
 			ID:                         "gemini-2.5-flash",
@@ -160,6 +84,7 @@ func GetGeminiCLIModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
 		},
 		{
 			ID:                         "gemini-2.5-pro",
@@ -174,6 +99,7 @@ func GetGeminiCLIModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
 		},
 		{
 			ID:                         "gemini-2.5-flash-lite",
@@ -188,6 +114,7 @@ func GetGeminiCLIModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 512, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
 		},
 		{
 			ID:                         "gemini-2.5-flash-image-preview",
@@ -202,6 +129,7 @@ func GetGeminiCLIModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           8192,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			// image models don't support thinkingConfig; leave Thinking nil
 		},
 		{
 			ID:                         "gemini-2.5-flash-image",
@@ -216,10 +144,69 @@ func GetGeminiCLIModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           8192,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			// image models don't support thinkingConfig; leave Thinking nil
 		},
 	}
 }
 
+// GetGeminiModels returns the standard Gemini model definitions
+func GetGeminiModels() []*ModelInfo { return GeminiModels() }
+
+// GetGeminiCLIModels returns the standard Gemini model definitions
+func GetGeminiCLIModels() []*ModelInfo { return GeminiModels() }
+
+// GetAIStudioModels returns the Gemini model definitions for AI Studio integrations
+func GetAIStudioModels() []*ModelInfo {
+	base := GeminiModels()
+	return append(base,
+		&ModelInfo{
+			ID:                         "gemini-pro-latest",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-pro-latest",
+			Version:                    "2.5",
+			DisplayName:                "Gemini Pro Latest",
+			Description:                "Latest release of Gemini Pro",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           65536,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
+		},
+		&ModelInfo{
+			ID:                         "gemini-flash-latest",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-flash-latest",
+			Version:                    "2.5",
+			DisplayName:                "Gemini Flash Latest",
+			Description:                "Latest release of Gemini Flash",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           65536,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
+		},
+		&ModelInfo{
+			ID:                         "gemini-flash-lite-latest",
+			Object:                     "model",
+			Created:                    time.Now().Unix(),
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-flash-lite-latest",
+			Version:                    "2.5",
+			DisplayName:                "Gemini Flash-Lite Latest",
+			Description:                "Latest release of Gemini Flash-Lite",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           65536,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 512, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
+		},
+	)
+}
+
 // GetOpenAIModels returns the standard OpenAI model definitions
 func GetOpenAIModels() []*ModelInfo {
 	return []*ModelInfo{
@@ -417,7 +404,6 @@ func GetIFlowModels() []*ModelInfo {
 		{ID: "qwen3-vl-plus", DisplayName: "Qwen3-VL-Plus", Description: "Qwen3 multimodal vision-language"},
 		{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build"},
 		{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905"},
-		{ID: "glm-4.5", DisplayName: "GLM-4.5", Description: "Zhipu GLM 4.5 general model"},
 		{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model"},
 		{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model"},
 		{ID: "deepseek-v3.2", DisplayName: "DeepSeek-V3.2-Exp", Description: "DeepSeek V3.2 experimental"},

internal/registry/model_registry.go

@@ -45,6 +45,23 @@ type ModelInfo struct {
 	MaxCompletionTokens int `json:"max_completion_tokens,omitempty"`
 	// SupportedParameters lists supported parameters
 	SupportedParameters []string `json:"supported_parameters,omitempty"`
+
+	// Thinking holds provider-specific reasoning/thinking budget capabilities.
+	// This is optional and currently used for Gemini thinking budget normalization.
+	Thinking *ThinkingSupport `json:"thinking,omitempty"`
+}
+
+// ThinkingSupport describes a model family's supported internal reasoning budget range.
+// Values are interpreted in provider-native token units.
+type ThinkingSupport struct {
+	// Min is the minimum allowed thinking budget (inclusive).
+	Min int `json:"min,omitempty"`
+	// Max is the maximum allowed thinking budget (inclusive).
+	Max int `json:"max,omitempty"`
+	// ZeroAllowed indicates whether 0 is a valid value (to disable thinking).
+	ZeroAllowed bool `json:"zero_allowed,omitempty"`
+	// DynamicAllowed indicates whether -1 is a valid value (dynamic thinking budget).
+	DynamicAllowed bool `json:"dynamic_allowed,omitempty"`
 }
 
 // ModelRegistration tracks a model's availability
@@ -652,6 +669,17 @@ func (r *ModelRegistry) GetModelProviders(modelID string) []string {
 	return result
 }
 
+// GetModelInfo returns the registered ModelInfo for the given model ID, if present.
+// Returns nil if the model is unknown to the registry.
+func (r *ModelRegistry) GetModelInfo(modelID string) *ModelInfo {
+	r.mutex.RLock()
+	defer r.mutex.RUnlock()
+	if reg, ok := r.models[modelID]; ok && reg != nil {
+		return reg.Info
+	}
+	return nil
+}
+
 // convertModelToMap converts ModelInfo to the appropriate format for different handler types
 func (r *ModelRegistry) convertModelToMap(model *ModelInfo, handlerType string) map[string]any {
 	if model == nil {

internal/runtime/executor/aistudio_executor.go

@@ -19,27 +19,27 @@ import (
 	"github.com/tidwall/sjson"
 )
 
-// AistudioExecutor routes AI Studio requests through a websocket-backed transport.
-type AistudioExecutor struct {
+// AIStudioExecutor routes AI Studio requests through a websocket-backed transport.
+type AIStudioExecutor struct {
 	provider string
 	relay    *wsrelay.Manager
 	cfg      *config.Config
 }
 
-// NewAistudioExecutor constructs a websocket executor for the provider name.
-func NewAistudioExecutor(cfg *config.Config, provider string, relay *wsrelay.Manager) *AistudioExecutor {
-	return &AistudioExecutor{provider: strings.ToLower(provider), relay: relay, cfg: cfg}
+// NewAIStudioExecutor constructs a websocket executor for the provider name.
+func NewAIStudioExecutor(cfg *config.Config, provider string, relay *wsrelay.Manager) *AIStudioExecutor {
+	return &AIStudioExecutor{provider: strings.ToLower(provider), relay: relay, cfg: cfg}
 }
 
-// Identifier returns the provider key served by this executor.
-func (e *AistudioExecutor) Identifier() string { return e.provider }
+// Identifier returns the logical provider key for routing.
+func (e *AIStudioExecutor) Identifier() string { return "aistudio" }
 
 // PrepareRequest is a no-op because websocket transport already injects headers.
-func (e *AistudioExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error {
+func (e *AIStudioExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error {
 	return nil
 }
 
-func (e *AistudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
+func (e *AIStudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
@@ -66,14 +66,14 @@ func (e *AistudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth,
 		Method:    http.MethodPost,
 		Headers:   wsReq.Headers.Clone(),
 		Body:      bytes.Clone(body.payload),
-		Provider:  e.provider,
+		Provider:  e.Identifier(),
 		AuthID:    authID,
 		AuthLabel: authLabel,
 		AuthType:  authType,
 		AuthValue: authValue,
 	})
 
-	wsResp, err := e.relay.NonStream(ctx, e.provider, wsReq)
+	wsResp, err := e.relay.NonStream(ctx, authID, wsReq)
 	if err != nil {
 		recordAPIResponseError(ctx, e.cfg, err)
 		return resp, err
@@ -92,7 +92,7 @@ func (e *AistudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth,
 	return resp, nil
 }
 
-func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (stream <-chan cliproxyexecutor.StreamChunk, err error) {
+func (e *AIStudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (stream <-chan cliproxyexecutor.StreamChunk, err error) {
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
@@ -118,13 +118,13 @@ func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
 		Method:    http.MethodPost,
 		Headers:   wsReq.Headers.Clone(),
 		Body:      bytes.Clone(body.payload),
-		Provider:  e.provider,
+		Provider:  e.Identifier(),
 		AuthID:    authID,
 		AuthLabel: authLabel,
 		AuthType:  authType,
 		AuthValue: authValue,
 	})
-	wsStream, err := e.relay.Stream(ctx, e.provider, wsReq)
+	wsStream, err := e.relay.Stream(ctx, authID, wsReq)
 	if err != nil {
 		recordAPIResponseError(ctx, e.cfg, err)
 		return nil, err
@@ -151,7 +151,7 @@ func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
 			case wsrelay.MessageTypeStreamChunk:
 				if len(event.Payload) > 0 {
 					appendAPIResponseChunk(ctx, e.cfg, bytes.Clone(event.Payload))
-					filtered := filterAistudioUsageMetadata(event.Payload)
+					filtered := filterAIStudioUsageMetadata(event.Payload)
 					if detail, ok := parseGeminiStreamUsage(filtered); ok {
 						reporter.publish(ctx, detail)
 					}
@@ -188,7 +188,7 @@ func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
 	return stream, nil
 }
 
-func (e *AistudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
+func (e *AIStudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
 	_, body, err := e.translateRequest(req, opts, false)
 	if err != nil {
 		return cliproxyexecutor.Response{}, err
@@ -215,13 +215,13 @@ func (e *AistudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.A
 		Method:    http.MethodPost,
 		Headers:   wsReq.Headers.Clone(),
 		Body:      bytes.Clone(body.payload),
-		Provider:  e.provider,
+		Provider:  e.Identifier(),
 		AuthID:    authID,
 		AuthLabel: authLabel,
 		AuthType:  authType,
 		AuthValue: authValue,
 	})
-	resp, err := e.relay.NonStream(ctx, e.provider, wsReq)
+	resp, err := e.relay.NonStream(ctx, authID, wsReq)
 	if err != nil {
 		recordAPIResponseError(ctx, e.cfg, err)
 		return cliproxyexecutor.Response{}, err
@@ -241,7 +241,7 @@ func (e *AistudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.A
 	return cliproxyexecutor.Response{Payload: []byte(translated)}, nil
 }
 
-func (e *AistudioExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {
+func (e *AIStudioExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {
 	_ = ctx
 	return auth, nil
 }
@@ -252,14 +252,18 @@ type translatedPayload struct {
 	toFormat sdktranslator.Format
 }
 
-func (e *AistudioExecutor) translateRequest(req cliproxyexecutor.Request, opts cliproxyexecutor.Options, stream bool) ([]byte, translatedPayload, error) {
+func (e *AIStudioExecutor) translateRequest(req cliproxyexecutor.Request, opts cliproxyexecutor.Options, stream bool) ([]byte, translatedPayload, error) {
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
-	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		payload = util.ApplyGeminiThinkingConfig(payload, budgetOverride, includeOverride)
 	}
-	payload = disableGeminiThinkingConfig(payload, req.Model)
+	payload = util.StripThinkingConfigIfUnsupported(req.Model, payload)
 	payload = fixGeminiImageAspectRatio(req.Model, payload)
 	metadataAction := "generateContent"
 	if req.Metadata != nil {
@@ -275,7 +279,7 @@ func (e *AistudioExecutor) translateRequest(req cliproxyexecutor.Request, opts c
 	return payload, translatedPayload{payload: payload, action: action, toFormat: to}, nil
 }
 
-func (e *AistudioExecutor) buildEndpoint(model, action, alt string) string {
+func (e *AIStudioExecutor) buildEndpoint(model, action, alt string) string {
 	base := fmt.Sprintf("%s/%s/models/%s:%s", glEndpoint, glAPIVersion, model, action)
 	if action == "streamGenerateContent" {
 		if alt == "" {
@@ -289,9 +293,9 @@ func (e *AistudioExecutor) buildEndpoint(model, action, alt string) string {
 	return base
 }
 
-// filterAistudioUsageMetadata removes usageMetadata from intermediate SSE events so that
+// filterAIStudioUsageMetadata removes usageMetadata from intermediate SSE events so that
 // only the terminal chunk retains token statistics.
-func filterAistudioUsageMetadata(payload []byte) []byte {
+func filterAIStudioUsageMetadata(payload []byte) []byte {
 	if len(payload) == 0 {
 		return payload
 	}

internal/runtime/executor/claude_executor.go

@@ -3,6 +3,8 @@ package executor
 import (
 	"bufio"
 	"bytes"
+	"compress/flate"
+	"compress/gzip"
 	"context"
 	"fmt"
 	"io"
@@ -10,6 +12,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/andybalholm/brotli"
 	"github.com/klauspost/compress/zstd"
 	claudeauth "github.com/router-for-me/CLIProxyAPI/v6/internal/auth/claude"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
@@ -89,31 +92,31 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 		recordAPIResponseError(ctx, e.cfg, err)
 		return resp, err
 	}
-	defer func() {
-		if errClose := httpResp.Body.Close(); errClose != nil {
-			log.Errorf("response body close error: %v", errClose)
-		}
-	}()
 	recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
 		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, string(b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
+		if errClose := httpResp.Body.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
+		}
 		return resp, err
 	}
-	reader := io.Reader(httpResp.Body)
-	var decoder *zstd.Decoder
-	if hasZSTDEcoding(httpResp.Header.Get("Content-Encoding")) {
-		decoder, err = zstd.NewReader(httpResp.Body)
-		if err != nil {
-			recordAPIResponseError(ctx, e.cfg, err)
-			return resp, fmt.Errorf("failed to initialize zstd decoder: %w", err)
+	decodedBody, err := decodeResponseBody(httpResp.Body, httpResp.Header.Get("Content-Encoding"))
+	if err != nil {
+		recordAPIResponseError(ctx, e.cfg, err)
+		if errClose := httpResp.Body.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
 		}
-		reader = decoder
-		defer decoder.Close()
+		return resp, err
 	}
-	data, err := io.ReadAll(reader)
+	defer func() {
+		if errClose := decodedBody.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
+		}
+	}()
+	data, err := io.ReadAll(decodedBody)
 	if err != nil {
 		recordAPIResponseError(ctx, e.cfg, err)
 		return resp, err
@@ -192,19 +195,27 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return nil, err
 	}
+	decodedBody, err := decodeResponseBody(httpResp.Body, httpResp.Header.Get("Content-Encoding"))
+	if err != nil {
+		recordAPIResponseError(ctx, e.cfg, err)
+		if errClose := httpResp.Body.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
+		}
+		return nil, err
+	}
 	out := make(chan cliproxyexecutor.StreamChunk)
 	stream = out
 	go func() {
 		defer close(out)
 		defer func() {
-			if errClose := httpResp.Body.Close(); errClose != nil {
+			if errClose := decodedBody.Close(); errClose != nil {
 				log.Errorf("response body close error: %v", errClose)
 			}
 		}()
 
 		// If from == to (Claude → Claude), directly forward the SSE stream without translation
 		if from == to {
-			scanner := bufio.NewScanner(httpResp.Body)
+			scanner := bufio.NewScanner(decodedBody)
 			buf := make([]byte, 20_971_520)
 			scanner.Buffer(buf, 20_971_520)
 			for scanner.Scan() {
@@ -228,7 +239,7 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 		}
 
 		// For other formats, use translation
-		scanner := bufio.NewScanner(httpResp.Body)
+		scanner := bufio.NewScanner(decodedBody)
 		buf := make([]byte, 20_971_520)
 		scanner.Buffer(buf, 20_971_520)
 		var param any
@@ -304,29 +315,29 @@ func (e *ClaudeExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
 		recordAPIResponseError(ctx, e.cfg, err)
 		return cliproxyexecutor.Response{}, err
 	}
-	defer func() {
-		if errClose := resp.Body.Close(); errClose != nil {
-			log.Errorf("response body close error: %v", errClose)
-		}
-	}()
 	recordAPIResponseMetadata(ctx, e.cfg, resp.StatusCode, resp.Header.Clone())
 	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
 		b, _ := io.ReadAll(resp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
+		if errClose := resp.Body.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
+		}
 		return cliproxyexecutor.Response{}, statusErr{code: resp.StatusCode, msg: string(b)}
 	}
-	reader := io.Reader(resp.Body)
-	var decoder *zstd.Decoder
-	if hasZSTDEcoding(resp.Header.Get("Content-Encoding")) {
-		decoder, err = zstd.NewReader(resp.Body)
-		if err != nil {
-			recordAPIResponseError(ctx, e.cfg, err)
-			return cliproxyexecutor.Response{}, fmt.Errorf("failed to initialize zstd decoder: %w", err)
+	decodedBody, err := decodeResponseBody(resp.Body, resp.Header.Get("Content-Encoding"))
+	if err != nil {
+		recordAPIResponseError(ctx, e.cfg, err)
+		if errClose := resp.Body.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
 		}
-		reader = decoder
-		defer decoder.Close()
+		return cliproxyexecutor.Response{}, err
 	}
-	data, err := io.ReadAll(reader)
+	defer func() {
+		if errClose := decodedBody.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
+		}
+	}()
+	data, err := io.ReadAll(decodedBody)
 	if err != nil {
 		recordAPIResponseError(ctx, e.cfg, err)
 		return cliproxyexecutor.Response{}, err
@@ -419,7 +430,7 @@ func (e *ClaudeExecutor) resolveClaudeConfig(auth *cliproxyauth.Auth) *config.Cl
 			continue
 		}
 		if attrKey != "" && strings.EqualFold(cfgKey, attrKey) {
-			if attrBase == "" || cfgBase == "" || strings.EqualFold(cfgBase, attrBase) {
+			if cfgBase == "" || strings.EqualFold(cfgBase, attrBase) {
 				return entry
 			}
 		}
@@ -438,17 +449,84 @@ func (e *ClaudeExecutor) resolveClaudeConfig(auth *cliproxyauth.Auth) *config.Cl
 	return nil
 }
 
-func hasZSTDEcoding(contentEncoding string) bool {
-	if contentEncoding == "" {
-		return false
-	}
-	parts := strings.Split(contentEncoding, ",")
-	for i := range parts {
-		if strings.EqualFold(strings.TrimSpace(parts[i]), "zstd") {
-			return true
+type compositeReadCloser struct {
+	io.Reader
+	closers []func() error
+}
+
+func (c *compositeReadCloser) Close() error {
+	var firstErr error
+	for i := range c.closers {
+		if c.closers[i] == nil {
+			continue
+		}
+		if err := c.closers[i](); err != nil && firstErr == nil {
+			firstErr = err
 		}
 	}
-	return false
+	return firstErr
+}
+
+func decodeResponseBody(body io.ReadCloser, contentEncoding string) (io.ReadCloser, error) {
+	if body == nil {
+		return nil, fmt.Errorf("response body is nil")
+	}
+	if contentEncoding == "" {
+		return body, nil
+	}
+	encodings := strings.Split(contentEncoding, ",")
+	for _, raw := range encodings {
+		encoding := strings.TrimSpace(strings.ToLower(raw))
+		switch encoding {
+		case "", "identity":
+			continue
+		case "gzip":
+			gzipReader, err := gzip.NewReader(body)
+			if err != nil {
+				_ = body.Close()
+				return nil, fmt.Errorf("failed to create gzip reader: %w", err)
+			}
+			return &compositeReadCloser{
+				Reader: gzipReader,
+				closers: []func() error{
+					gzipReader.Close,
+					func() error { return body.Close() },
+				},
+			}, nil
+		case "deflate":
+			deflateReader := flate.NewReader(body)
+			return &compositeReadCloser{
+				Reader: deflateReader,
+				closers: []func() error{
+					deflateReader.Close,
+					func() error { return body.Close() },
+				},
+			}, nil
+		case "br":
+			return &compositeReadCloser{
+				Reader: brotli.NewReader(body),
+				closers: []func() error{
+					func() error { return body.Close() },
+				},
+			}, nil
+		case "zstd":
+			decoder, err := zstd.NewReader(body)
+			if err != nil {
+				_ = body.Close()
+				return nil, fmt.Errorf("failed to create zstd reader: %w", err)
+			}
+			return &compositeReadCloser{
+				Reader: decoder,
+				closers: []func() error{
+					func() error { decoder.Close(); return nil },
+					func() error { return body.Close() },
+				},
+			}, nil
+		default:
+			continue
+		}
+	}
+	return body, nil
 }
 
 func applyClaudeHeaders(r *http.Request, apiKey string, stream bool) {
@@ -473,8 +551,8 @@ func applyClaudeHeaders(r *http.Request, apiKey string, stream bool) {
 	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Arch", "arm64")
 	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Os", "MacOS")
 	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Timeout", "60")
+	misc.EnsureHeader(r.Header, ginHeaders, "User-Agent", "claude-cli/1.0.83 (external, cli)")
 	r.Header.Set("Connection", "keep-alive")
-	r.Header.Set("User-Agent", "claude-cli/1.0.83 (external, cli)")
 	r.Header.Set("Accept-Encoding", "gzip, deflate, br, zstd")
 	if stream {
 		r.Header.Set("Accept", "text/event-stream")

internal/runtime/executor/codex_executor.go

@@ -532,6 +532,7 @@ func applyCodexHeaders(r *http.Request, auth *cliproxyauth.Auth, token string) {
 	misc.EnsureHeader(r.Header, ginHeaders, "Version", "0.21.0")
 	misc.EnsureHeader(r.Header, ginHeaders, "Openai-Beta", "responses=experimental")
 	misc.EnsureHeader(r.Header, ginHeaders, "Session_id", uuid.NewString())
+	misc.EnsureHeader(r.Header, ginHeaders, "User-Agent", "codex_cli_rs/0.50.0 (Mac OS 26.0.1; arm64) Apple_Terminal/464")
 
 	r.Header.Set("Accept", "text/event-stream")
 	r.Header.Set("Connection", "Keep-Alive")

internal/runtime/executor/gemini_cli_executor.go

@@ -63,9 +63,14 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 	to := sdktranslator.FromString("gemini-cli")
 	budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
 	basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	if hasOverride {
+	if hasOverride && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
 	}
+	basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
 	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
 
 	action := "generateContent"
@@ -92,7 +97,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 	var lastStatus int
 	var lastBody []byte
 
-	for _, attemptModel := range models {
+	for idx, attemptModel := range models {
 		payload := append([]byte(nil), basePayload...)
 		if action == "countTokens" {
 			payload = deleteJSONField(payload, "project")
@@ -101,7 +106,6 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 			payload = setJSONField(payload, "project", projectID)
 			payload = setJSONField(payload, "model", attemptModel)
 		}
-		payload = disableGeminiThinkingConfig(payload, attemptModel)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -166,7 +170,11 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 		lastBody = append([]byte(nil), data...)
 		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, string(data))
 		if httpResp.StatusCode == 429 {
-			log.Debugf("gemini cli executor: rate limited, retrying with next model")
+			if idx+1 < len(models) {
+				log.Debugf("gemini cli executor: rate limited, retrying with next model: %s", models[idx+1])
+			} else {
+				log.Debug("gemini cli executor: rate limited, no additional fallback model")
+			}
 			continue
 		}
 
@@ -196,9 +204,14 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 	to := sdktranslator.FromString("gemini-cli")
 	budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
 	basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	if hasOverride {
+	if hasOverride && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
 	}
+	basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
 	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
 
 	projectID := strings.TrimSpace(stringValue(auth.Metadata, "project_id"))
@@ -219,11 +232,10 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 	var lastStatus int
 	var lastBody []byte
 
-	for _, attemptModel := range models {
+	for idx, attemptModel := range models {
 		payload := append([]byte(nil), basePayload...)
 		payload = setJSONField(payload, "project", projectID)
 		payload = setJSONField(payload, "model", attemptModel)
-		payload = disableGeminiThinkingConfig(payload, attemptModel)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {
@@ -282,7 +294,11 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 			lastBody = append([]byte(nil), data...)
 			log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, string(data))
 			if httpResp.StatusCode == 429 {
-				log.Debugf("gemini cli executor: rate limited, retrying with next model")
+				if idx+1 < len(models) {
+					log.Debugf("gemini cli executor: rate limited, retrying with next model: %s", models[idx+1])
+				} else {
+					log.Debug("gemini cli executor: rate limited, no additional fallback model")
+				}
 				continue
 			}
 			err = statusErr{code: httpResp.StatusCode, msg: string(data)}
@@ -393,12 +409,16 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
 	budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
 	for _, attemptModel := range models {
 		payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
-		if hasOverride {
+		if hasOverride && util.ModelSupportsThinking(req.Model) {
+			if budgetOverride != nil {
+				norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+				budgetOverride = &norm
+			}
 			payload = util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)
 		}
 		payload = deleteJSONField(payload, "project")
 		payload = deleteJSONField(payload, "model")
-		payload = disableGeminiThinkingConfig(payload, attemptModel)
+		payload = util.StripThinkingConfigIfUnsupported(req.Model, payload)
 		payload = fixGeminiCLIImageAspectRatio(attemptModel, payload)
 
 		tok, errTok := tokenSource.Token()
@@ -623,29 +643,6 @@ func cliPreviewFallbackOrder(model string) []string {
 	}
 }
 
-func disableGeminiThinkingConfig(body []byte, model string) []byte {
-	if !geminiModelDisallowsThinking(model) {
-		return body
-	}
-
-	updated := deleteJSONField(body, "request.generationConfig.thinkingConfig")
-	updated = deleteJSONField(updated, "generationConfig.thinkingConfig")
-	return updated
-}
-
-func geminiModelDisallowsThinking(model string) bool {
-	if model == "" {
-		return false
-	}
-	lower := strings.ToLower(model)
-	for _, marker := range []string{"gemini-2.5-flash-image-preview", "gemini-2.5-flash-image"} {
-		if strings.Contains(lower, marker) {
-			return true
-		}
-	}
-	return false
-}
-
 // setJSONField sets a top-level JSON field on a byte slice payload via sjson.
 func setJSONField(body []byte, key, value string) []byte {
 	if key == "" {

internal/runtime/executor/gemini_executor.go

@@ -78,10 +78,14 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
 	}
-	body = disableGeminiThinkingConfig(body, req.Model)
+	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
 	body = fixGeminiImageAspectRatio(req.Model, body)
 
 	action := "generateContent"
@@ -166,10 +170,14 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
 	}
-	body = disableGeminiThinkingConfig(body, req.Model)
+	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
 	body = fixGeminiImageAspectRatio(req.Model, body)
 
 	url := fmt.Sprintf("%s/%s/models/%s:%s", glEndpoint, glAPIVersion, req.Model, "streamGenerateContent")
@@ -269,10 +277,14 @@ func (e *GeminiExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
+	if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+		if budgetOverride != nil {
+			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			budgetOverride = &norm
+		}
 		translatedReq = util.ApplyGeminiThinkingConfig(translatedReq, budgetOverride, includeOverride)
 	}
-	translatedReq = disableGeminiThinkingConfig(translatedReq, req.Model)
+	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
 	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")

internal/translator/gemini-cli/claude/gemini-cli_claude_request.go

@@ -11,6 +11,7 @@ import (
 	"strings"
 
 	client "github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -136,7 +137,7 @@ func ConvertClaudeRequestToCLI(modelName string, inputRawJSON []byte, _ bool) []
 	}
 
 	// Build output Gemini CLI request JSON
-	out := `{"model":"","request":{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}}}`
+	out := `{"model":"","request":{"contents":[]}}`
 	out, _ = sjson.Set(out, "model", modelName)
 	if systemInstruction != nil {
 		b, _ := json.Marshal(systemInstruction)
@@ -151,21 +152,16 @@ func ConvertClaudeRequestToCLI(modelName string, inputRawJSON []byte, _ bool) []
 		out, _ = sjson.SetRaw(out, "request.tools", string(b))
 	}
 
-	// Map reasoning and sampling configs
-	reasoningEffortResult := gjson.GetBytes(rawJSON, "reasoning_effort")
-	if reasoningEffortResult.String() == "none" {
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.include_thoughts", false)
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", 0)
-	} else if reasoningEffortResult.String() == "auto" {
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
-	} else if reasoningEffortResult.String() == "low" {
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", 1024)
-	} else if reasoningEffortResult.String() == "medium" {
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", 8192)
-	} else if reasoningEffortResult.String() == "high" {
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", 24576)
-	} else {
-		out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+	// Map Anthropic thinking -> Gemini thinkingBudget/include_thoughts when type==enabled
+	if t := gjson.GetBytes(rawJSON, "thinking"); t.Exists() && t.IsObject() && util.ModelSupportsThinking(modelName) {
+		if t.Get("type").String() == "enabled" {
+			if b := t.Get("budget_tokens"); b.Exists() && b.Type == gjson.Number {
+				budget := int(b.Int())
+				budget = util.NormalizeThinkingBudget(modelName, budget)
+				out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", budget)
+				out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
+			}
+		}
 	}
 	if v := gjson.GetBytes(rawJSON, "temperature"); v.Exists() && v.Type == gjson.Number {
 		out, _ = sjson.Set(out, "request.generationConfig.temperature", v.Num)

internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go

@@ -26,32 +26,57 @@ import (
 //   - []byte: The transformed request data in Gemini CLI API format
 func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
-	// Base envelope
-	out := []byte(`{"project":"","request":{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}},"model":"gemini-2.5-pro"}`)
+	// Base envelope (no default thinkingConfig)
+	out := []byte(`{"project":"","request":{"contents":[]},"model":"gemini-2.5-pro"}`)
 
 	// Model
 	out, _ = sjson.SetBytes(out, "model", modelName)
 
 	// Reasoning effort -> thinkingBudget/include_thoughts
+	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
-	if re.Exists() {
+	hasOfficialThinking := re.Exists()
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
 		switch re.String() {
 		case "none":
 			out, _ = sjson.DeleteBytes(out, "request.generationConfig.thinkingConfig.include_thoughts")
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 0)
 		case "auto":
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "low":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 1024)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "medium":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 8192)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "high":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 24576)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		default:
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
+		}
+	}
+
+	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+		if tc := gjson.GetBytes(rawJSON, "extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
+			var setBudget bool
+			var normalized int
+			if v := tc.Get("thinking_budget"); v.Exists() {
+				normalized = util.NormalizeThinkingBudget(modelName, int(v.Int()))
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", normalized)
+				setBudget = true
+			}
+			if v := tc.Get("include_thoughts"); v.Exists() {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", v.Bool())
+			} else if setBudget {
+				if normalized != 0 {
+					out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
+				}
+			}
 		}
-	} else {
-		out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
 	}
 
 	// Temperature/top_p/top_k
@@ -250,8 +275,34 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 			if t.Get("type").String() == "function" {
 				fn := t.Get("function")
 				if fn.Exists() && fn.IsObject() {
-					parametersJsonSchema, _ := util.RenameKey(fn.Raw, "parameters", "parametersJsonSchema")
-					out, _ = sjson.SetRawBytes(out, fdPath+".-1", []byte(parametersJsonSchema))
+					fnRaw := fn.Raw
+					if fn.Get("parameters").Exists() {
+						renamed, errRename := util.RenameKey(fnRaw, "parameters", "parametersJsonSchema")
+						if errRename != nil {
+							log.Warnf("Failed to rename parameters for tool '%s': %v", fn.Get("name").String(), errRename)
+						} else {
+							fnRaw = renamed
+						}
+					} else {
+						var errSet error
+						fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.type", "object")
+						if errSet != nil {
+							log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
+							continue
+						}
+						fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+						if errSet != nil {
+							log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
+							continue
+						}
+					}
+
+					tmp, errSet := sjson.SetRawBytes(out, fdPath+".-1", []byte(fnRaw))
+					if errSet != nil {
+						log.Warnf("Failed to append tool declaration for '%s': %v", fn.Get("name").String(), errSet)
+						continue
+					}
+					out = tmp
 				}
 			}
 		}

internal/translator/gemini/claude/gemini_claude_request.go

@@ -11,6 +11,7 @@ import (
 	"strings"
 
 	client "github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -129,7 +130,7 @@ func ConvertClaudeRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 	}
 
 	// Build output Gemini CLI request JSON
-	out := `{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}}`
+	out := `{"contents":[]}`
 	out, _ = sjson.Set(out, "model", modelName)
 	if systemInstruction != nil {
 		b, _ := json.Marshal(systemInstruction)
@@ -144,21 +145,16 @@ func ConvertClaudeRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 		out, _ = sjson.SetRaw(out, "tools", string(b))
 	}
 
-	// Map reasoning and sampling configs
-	reasoningEffortResult := gjson.GetBytes(rawJSON, "reasoning_effort")
-	if reasoningEffortResult.String() == "none" {
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", false)
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 0)
-	} else if reasoningEffortResult.String() == "auto" {
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
-	} else if reasoningEffortResult.String() == "low" {
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 1024)
-	} else if reasoningEffortResult.String() == "medium" {
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 8192)
-	} else if reasoningEffortResult.String() == "high" {
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 24576)
-	} else {
-		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+	// Map Anthropic thinking -> Gemini thinkingBudget/include_thoughts when enabled
+	if t := gjson.GetBytes(rawJSON, "thinking"); t.Exists() && t.IsObject() && util.ModelSupportsThinking(modelName) {
+		if t.Get("type").String() == "enabled" {
+			if b := t.Get("budget_tokens"); b.Exists() && b.Type == gjson.Number {
+				budget := int(b.Int())
+				budget = util.NormalizeThinkingBudget(modelName, budget)
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", budget)
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
+			}
+		}
 	}
 	if v := gjson.GetBytes(rawJSON, "temperature"); v.Exists() && v.Type == gjson.Number {
 		out, _ = sjson.Set(out, "generationConfig.temperature", v.Num)

internal/translator/gemini/openai/chat-completions/gemini_openai_request.go

@@ -26,32 +26,58 @@ import (
 //   - []byte: The transformed request data in Gemini API format
 func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
-	// Base envelope
-	out := []byte(`{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}}`)
+	// Base envelope (no default thinkingConfig)
+	out := []byte(`{"contents":[]}`)
 
 	// Model
 	out, _ = sjson.SetBytes(out, "model", modelName)
 
 	// Reasoning effort -> thinkingBudget/include_thoughts
+	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
-	if re.Exists() {
+	hasOfficialThinking := re.Exists()
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
 		switch re.String() {
 		case "none":
 			out, _ = sjson.DeleteBytes(out, "generationConfig.thinkingConfig.include_thoughts")
 			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 0)
 		case "auto":
 			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "low":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 1024)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "medium":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 8192)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "high":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 24576)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		default:
 			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
+		}
+	}
+
+	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+		if tc := gjson.GetBytes(rawJSON, "extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
+			var setBudget bool
+			var normalized int
+			if v := tc.Get("thinking_budget"); v.Exists() {
+				// Normalize budget to model range
+				normalized = util.NormalizeThinkingBudget(modelName, int(v.Int()))
+				out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", normalized)
+				setBudget = true
+			}
+			if v := tc.Get("include_thoughts"); v.Exists() {
+				out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", v.Bool())
+			} else if setBudget {
+				if normalized != 0 {
+					out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
+				}
+			}
 		}
-	} else {
-		out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
 	}
 
 	// Temperature/top_p/top_k

internal/translator/gemini/openai/responses/gemini_openai-responses_request.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"strings"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -15,8 +16,8 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 	_ = modelName // Unused but required by interface
 	_ = stream    // Unused but required by interface
 
-	// Base Gemini API template
-	out := `{"contents":[],"generationConfig":{"thinkingConfig":{"include_thoughts":true}}}`
+	// Base Gemini API template (do not include thinkingConfig by default)
+	out := `{"contents":[]}`
 
 	root := gjson.ParseBytes(rawJSON)
 
@@ -242,23 +243,52 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 		out, _ = sjson.Set(out, "generationConfig.stopSequences", sequences)
 	}
 
-	if reasoningEffort := root.Get("reasoning.effort"); reasoningEffort.Exists() {
+	// OpenAI official reasoning fields take precedence
+	hasOfficialThinking := root.Get("reasoning.effort").Exists()
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+		reasoningEffort := root.Get("reasoning.effort")
 		switch reasoningEffort.String() {
 		case "none":
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", false)
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 0)
 		case "auto":
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "minimal":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 1024)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "low":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 4096)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 4096))
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "medium":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 8192)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "high":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 24576)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		default:
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
+		}
+	}
+
+	// Cherry Studio extension (applies only when official fields are missing)
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+		if tc := root.Get("extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
+			var setBudget bool
+			var normalized int
+			if v := tc.Get("thinking_budget"); v.Exists() {
+				normalized = util.NormalizeThinkingBudget(modelName, int(v.Int()))
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", normalized)
+				setBudget = true
+			}
+			if v := tc.Get("include_thoughts"); v.Exists() {
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", v.Bool())
+			} else if setBudget {
+				if normalized != 0 {
+					out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
+				}
+			}
 		}
 	}
 	return []byte(out)

internal/translator/openai/openai/chat-completions/openai_openai_request.go

@@ -4,6 +4,7 @@ package chat_completions
 
 import (
 	"bytes"
+	"github.com/tidwall/sjson"
 )
 
 // ConvertOpenAIRequestToOpenAI converts an OpenAI Chat Completions request (raw JSON)
@@ -17,5 +18,14 @@ import (
 // Returns:
 //   - []byte: The transformed request data in Gemini CLI API format
 func ConvertOpenAIRequestToOpenAI(modelName string, inputRawJSON []byte, _ bool) []byte {
-	return bytes.Clone(inputRawJSON)
+	// Update the "model" field in the JSON payload with the provided modelName
+	// The sjson.SetBytes function returns a new byte slice with the updated JSON.
+	updatedJSON, err := sjson.SetBytes(inputRawJSON, "model", modelName)
+	if err != nil {
+		// If there's an error, return the original JSON or handle the error appropriately.
+		// For now, we'll return the original, but in a real scenario, logging or a more robust error
+		// handling mechanism would be needed.
+		return bytes.Clone(inputRawJSON)
+	}
+	return updatedJSON
 }

internal/util/gemini_thinking.go

@@ -179,3 +179,19 @@ func GeminiThinkingFromMetadata(metadata map[string]any) (*int, *bool, bool) {
 	}
 	return budgetPtr, includePtr, matched
 }
+
+// StripThinkingConfigIfUnsupported removes thinkingConfig from the request body
+// when the target model does not advertise Thinking capability. It cleans both
+// standard Gemini and Gemini CLI JSON envelopes. This acts as a final safety net
+// in case upstream injected thinking for an unsupported model.
+func StripThinkingConfigIfUnsupported(model string, body []byte) []byte {
+	if ModelSupportsThinking(model) || len(body) == 0 {
+		return body
+	}
+	updated := body
+	// Gemini CLI path
+	updated, _ = sjson.DeleteBytes(updated, "request.generationConfig.thinkingConfig")
+	// Standard Gemini path
+	updated, _ = sjson.DeleteBytes(updated, "generationConfig.thinkingConfig")
+	return updated
+}

internal/util/thinking.go

@@ -0,0 +1,69 @@
+package util
+
+import (
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+)
+
+// ModelSupportsThinking reports whether the given model has Thinking capability
+// according to the model registry metadata (provider-agnostic).
+func ModelSupportsThinking(model string) bool {
+	if model == "" {
+		return false
+	}
+	if info := registry.GetGlobalRegistry().GetModelInfo(model); info != nil {
+		return info.Thinking != nil
+	}
+	return false
+}
+
+// NormalizeThinkingBudget clamps the requested thinking budget to the
+// supported range for the specified model using registry metadata only.
+// If the model is unknown or has no Thinking metadata, returns the original budget.
+// For dynamic (-1), returns -1 if DynamicAllowed; otherwise approximates mid-range
+// or min (0 if zero is allowed and mid <= 0).
+func NormalizeThinkingBudget(model string, budget int) int {
+	if budget == -1 { // dynamic
+		if found, min, max, zeroAllowed, dynamicAllowed := thinkingRangeFromRegistry(model); found {
+			if dynamicAllowed {
+				return -1
+			}
+			mid := (min + max) / 2
+			if mid <= 0 && zeroAllowed {
+				return 0
+			}
+			if mid <= 0 {
+				return min
+			}
+			return mid
+		}
+		return -1
+	}
+	if found, min, max, zeroAllowed, _ := thinkingRangeFromRegistry(model); found {
+		if budget == 0 {
+			if zeroAllowed {
+				return 0
+			}
+			return min
+		}
+		if budget < min {
+			return min
+		}
+		if budget > max {
+			return max
+		}
+		return budget
+	}
+	return budget
+}
+
+// thinkingRangeFromRegistry attempts to read thinking ranges from the model registry.
+func thinkingRangeFromRegistry(model string) (found bool, min int, max int, zeroAllowed bool, dynamicAllowed bool) {
+	if model == "" {
+		return false, 0, 0, false, false
+	}
+	info := registry.GetGlobalRegistry().GetModelInfo(model)
+	if info == nil || info.Thinking == nil {
+		return false, 0, 0, false, false
+	}
+	return true, info.Thinking.Min, info.Thinking.Max, info.Thinking.ZeroAllowed, info.Thinking.DynamicAllowed
+}

sdk/api/handlers/handlers.go

@@ -6,6 +6,7 @@ package handlers
 import (
 	"fmt"
 	"net/http"
+	"strings"
 
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
@@ -46,6 +47,9 @@ type BaseAPIHandler struct {
 
 	// Cfg holds the current application configuration.
 	Cfg *config.SDKConfig
+
+	// OpenAICompatProviders is a list of provider names for OpenAI compatibility.
+	OpenAICompatProviders []string
 }
 
 // NewBaseAPIHandlers creates a new API handlers instance.
@@ -57,10 +61,11 @@ type BaseAPIHandler struct {
 //
 // Returns:
 //   - *BaseAPIHandler: A new API handlers instance
-func NewBaseAPIHandlers(cfg *config.SDKConfig, authManager *coreauth.Manager) *BaseAPIHandler {
+func NewBaseAPIHandlers(cfg *config.SDKConfig, authManager *coreauth.Manager, openAICompatProviders []string) *BaseAPIHandler {
 	return &BaseAPIHandler{
-		Cfg:         cfg,
-		AuthManager: authManager,
+		Cfg:                   cfg,
+		AuthManager:           authManager,
+		OpenAICompatProviders: openAICompatProviders,
 	}
 }
 
@@ -133,10 +138,9 @@ func (h *BaseAPIHandler) GetContextWithCancel(handler interfaces.APIHandler, c *
 // ExecuteWithAuthManager executes a non-streaming request via the core auth manager.
 // This path is the only supported execution route.
 func (h *BaseAPIHandler) ExecuteWithAuthManager(ctx context.Context, handlerType, modelName string, rawJSON []byte, alt string) ([]byte, *interfaces.ErrorMessage) {
-	normalizedModel, metadata := normalizeModelMetadata(modelName)
-	providers := util.GetProviderName(normalizedModel)
-	if len(providers) == 0 {
-		return nil, &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
+	providers, normalizedModel, metadata, errMsg := h.getRequestDetails(modelName)
+	if errMsg != nil {
+		return nil, errMsg
 	}
 	req := coreexecutor.Request{
 		Model:   normalizedModel,
@@ -176,10 +180,9 @@ func (h *BaseAPIHandler) ExecuteWithAuthManager(ctx context.Context, handlerType
 // ExecuteCountWithAuthManager executes a non-streaming request via the core auth manager.
 // This path is the only supported execution route.
 func (h *BaseAPIHandler) ExecuteCountWithAuthManager(ctx context.Context, handlerType, modelName string, rawJSON []byte, alt string) ([]byte, *interfaces.ErrorMessage) {
-	normalizedModel, metadata := normalizeModelMetadata(modelName)
-	providers := util.GetProviderName(normalizedModel)
-	if len(providers) == 0 {
-		return nil, &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
+	providers, normalizedModel, metadata, errMsg := h.getRequestDetails(modelName)
+	if errMsg != nil {
+		return nil, errMsg
 	}
 	req := coreexecutor.Request{
 		Model:   normalizedModel,
@@ -219,11 +222,10 @@ func (h *BaseAPIHandler) ExecuteCountWithAuthManager(ctx context.Context, handle
 // ExecuteStreamWithAuthManager executes a streaming request via the core auth manager.
 // This path is the only supported execution route.
 func (h *BaseAPIHandler) ExecuteStreamWithAuthManager(ctx context.Context, handlerType, modelName string, rawJSON []byte, alt string) (<-chan []byte, <-chan *interfaces.ErrorMessage) {
-	normalizedModel, metadata := normalizeModelMetadata(modelName)
-	providers := util.GetProviderName(normalizedModel)
-	if len(providers) == 0 {
+	providers, normalizedModel, metadata, errMsg := h.getRequestDetails(modelName)
+	if errMsg != nil {
 		errChan := make(chan *interfaces.ErrorMessage, 1)
-		errChan <- &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
+		errChan <- errMsg
 		close(errChan)
 		return nil, errChan
 	}
@@ -292,6 +294,58 @@ func (h *BaseAPIHandler) ExecuteStreamWithAuthManager(ctx context.Context, handl
 	return dataChan, errChan
 }
 
+func (h *BaseAPIHandler) getRequestDetails(modelName string) (providers []string, normalizedModel string, metadata map[string]any, err *interfaces.ErrorMessage) {
+	providerName, extractedModelName, isDynamic := h.parseDynamicModel(modelName)
+
+	// First, normalize the model name to handle suffixes like "-thinking-128"
+	// This needs to happen before determining the provider for non-dynamic models.
+	normalizedModel, metadata = normalizeModelMetadata(modelName)
+
+	if isDynamic {
+		providers = []string{providerName}
+		// For dynamic models, the extractedModelName is already normalized by parseDynamicModel
+		// so we use it as the final normalizedModel.
+		normalizedModel = extractedModelName
+	} else {
+		// For non-dynamic models, use the normalizedModel to get the provider name.
+		providers = util.GetProviderName(normalizedModel)
+	}
+
+	if len(providers) == 0 {
+		return nil, "", nil, &interfaces.ErrorMessage{StatusCode: http.StatusBadRequest, Error: fmt.Errorf("unknown provider for model %s", modelName)}
+	}
+
+	// If it's a dynamic model, the normalizedModel was already set to extractedModelName.
+	// If it's a non-dynamic model, normalizedModel was set by normalizeModelMetadata.
+	// So, normalizedModel is already correctly set at this point.
+
+	return providers, normalizedModel, metadata, nil
+}
+
+func (h *BaseAPIHandler) parseDynamicModel(modelName string) (providerName, model string, isDynamic bool) {
+	var providerPart, modelPart string
+	for _, sep := range []string{"://"} {
+		if parts := strings.SplitN(modelName, sep, 2); len(parts) == 2 {
+			providerPart = parts[0]
+			modelPart = parts[1]
+			break
+		}
+	}
+
+	if providerPart == "" {
+		return "", modelName, false
+	}
+
+	// Check if the provider is a configured openai-compatibility provider
+	for _, pName := range h.OpenAICompatProviders {
+		if pName == providerPart {
+			return providerPart, modelPart, true
+		}
+	}
+
+	return "", modelName, false
+}
+
 func cloneBytes(src []byte) []byte {
 	if len(src) == 0 {
 		return nil

sdk/cliproxy/auth/manager.go

@@ -872,6 +872,11 @@ func (m *Manager) persist(ctx context.Context, auth *Auth) error {
 	if m.store == nil || auth == nil {
 		return nil
 	}
+	if auth.Attributes != nil {
+		if v := strings.ToLower(strings.TrimSpace(auth.Attributes["runtime_only"])); v == "true" {
+			return nil
+		}
+	}
 	// Skip persistence when metadata is absent (e.g., runtime-only auths).
 	if auth.Metadata == nil {
 		return nil

sdk/cliproxy/auth/types.go

@@ -157,15 +157,6 @@ func (a *Auth) AccountInfo() (string, string) {
 			return "oauth", v
 		}
 	}
-	if strings.HasPrefix(strings.ToLower(strings.TrimSpace(a.Provider)), "aistudio-") {
-		if label := strings.TrimSpace(a.Label); label != "" {
-			return "oauth", label
-		}
-		if id := strings.TrimSpace(a.ID); id != "" {
-			return "oauth", id
-		}
-		return "oauth", "aistudio"
-	}
 	if a.Attributes != nil {
 		if v := a.Attributes["api_key"]; v != "" {
 			return "api_key", v

sdk/cliproxy/service.go

@@ -194,15 +194,15 @@ func (s *Service) ensureWebsocketGateway() {
 	s.wsGateway = wsrelay.NewManager(opts)
 }
 
-func (s *Service) wsOnConnected(provider string) {
-	if s == nil || provider == "" {
+func (s *Service) wsOnConnected(channelID string) {
+	if s == nil || channelID == "" {
 		return
 	}
-	if !strings.HasPrefix(strings.ToLower(provider), "aistudio-") {
+	if !strings.HasPrefix(strings.ToLower(channelID), "aistudio-") {
 		return
 	}
 	if s.coreManager != nil {
-		if existing, ok := s.coreManager.GetByID(provider); ok && existing != nil {
+		if existing, ok := s.coreManager.GetByID(channelID); ok && existing != nil {
 			if !existing.Disabled && existing.Status == coreauth.StatusActive {
 				return
 			}
@@ -210,36 +210,34 @@ func (s *Service) wsOnConnected(provider string) {
 	}
 	now := time.Now().UTC()
 	auth := &coreauth.Auth{
-		ID:         provider,
-		Provider:   provider,
-		Label:      provider,
+		ID:         channelID,  // keep channel identifier as ID
+		Provider:   "aistudio", // logical provider for switch routing
+		Label:      channelID,  // display original channel id
 		Status:     coreauth.StatusActive,
 		CreatedAt:  now,
 		UpdatedAt:  now,
-		Attributes: map[string]string{"ws_provider": "gemini"},
+		Attributes: map[string]string{"runtime_only": "true"},
+		Metadata:   map[string]any{"email": channelID}, // metadata drives logging and usage tracking
 	}
-	log.Infof("websocket provider connected: %s", provider)
+	log.Infof("websocket provider connected: %s", channelID)
 	s.applyCoreAuthAddOrUpdate(context.Background(), auth)
 }
 
-func (s *Service) wsOnDisconnected(provider string, reason error) {
-	if s == nil || provider == "" {
+func (s *Service) wsOnDisconnected(channelID string, reason error) {
+	if s == nil || channelID == "" {
 		return
 	}
 	if reason != nil {
 		if strings.Contains(reason.Error(), "replaced by new connection") {
-			log.Infof("websocket provider replaced: %s", provider)
+			log.Infof("websocket provider replaced: %s", channelID)
 			return
 		}
-		log.Warnf("websocket provider disconnected: %s (%v)", provider, reason)
+		log.Warnf("websocket provider disconnected: %s (%v)", channelID, reason)
 	} else {
-		log.Infof("websocket provider disconnected: %s", provider)
+		log.Infof("websocket provider disconnected: %s", channelID)
 	}
 	ctx := context.Background()
-	s.applyCoreAuthRemoval(ctx, provider)
-	if s.coreManager != nil {
-		s.coreManager.UnregisterExecutor(provider)
-	}
+	s.applyCoreAuthRemoval(ctx, channelID)
 }
 
 func (s *Service) applyCoreAuthAddOrUpdate(ctx context.Context, auth *coreauth.Auth) {
@@ -317,17 +315,16 @@ func (s *Service) ensureExecutorsForAuth(a *coreauth.Auth) {
 		s.coreManager.RegisterExecutor(executor.NewOpenAICompatExecutor(compatProviderKey, s.cfg))
 		return
 	}
-	if strings.HasPrefix(strings.ToLower(strings.TrimSpace(a.Provider)), "aistudio-") {
-		if s.wsGateway != nil {
-			s.coreManager.RegisterExecutor(executor.NewAistudioExecutor(s.cfg, a.Provider, s.wsGateway))
-		}
-		return
-	}
 	switch strings.ToLower(a.Provider) {
 	case "gemini":
 		s.coreManager.RegisterExecutor(executor.NewGeminiExecutor(s.cfg))
 	case "gemini-cli":
 		s.coreManager.RegisterExecutor(executor.NewGeminiCLIExecutor(s.cfg))
+	case "aistudio":
+		if s.wsGateway != nil {
+			s.coreManager.RegisterExecutor(executor.NewAIStudioExecutor(s.cfg, a.ID, s.wsGateway))
+		}
+		return
 	case "claude":
 		s.coreManager.RegisterExecutor(executor.NewClaudeExecutor(s.cfg))
 	case "codex":
@@ -609,13 +606,6 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) {
 	}
 	provider := strings.ToLower(strings.TrimSpace(a.Provider))
 	compatProviderKey, compatDisplayName, compatDetected := openAICompatInfoFromAuth(a)
-	if a.Attributes != nil {
-		if strings.EqualFold(a.Attributes["ws_provider"], "gemini") {
-			models := mergeGeminiModels()
-			GlobalModelRegistry().RegisterClient(a.ID, provider, models)
-			return
-		}
-	}
 	if compatDetected {
 		provider = "openai-compatibility"
 	}
@@ -625,6 +615,8 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) {
 		models = registry.GetGeminiModels()
 	case "gemini-cli":
 		models = registry.GetGeminiCLIModels()
+	case "aistudio":
+		models = registry.GetAIStudioModels()
 	case "claude":
 		models = registry.GetClaudeModels()
 		if entry := s.resolveConfigClaudeKey(a); entry != nil && len(entry.Models) > 0 {
@@ -726,27 +718,6 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) {
 	}
 }
 
-func mergeGeminiModels() []*ModelInfo {
-	models := make([]*ModelInfo, 0, 16)
-	seen := make(map[string]struct{})
-	appendModels := func(items []*ModelInfo) {
-		for i := range items {
-			m := items[i]
-			if m == nil || m.ID == "" {
-				continue
-			}
-			if _, ok := seen[m.ID]; ok {
-				continue
-			}
-			seen[m.ID] = struct{}{}
-			models = append(models, m)
-		}
-	}
-	appendModels(registry.GetGeminiModels())
-	appendModels(registry.GetGeminiCLIModels())
-	return models
-}
-
 func (s *Service) resolveConfigClaudeKey(auth *coreauth.Auth) *config.ClaudeKey {
 	if auth == nil || s.cfg == nil {
 		return nil