fix(translator): handle empty item type and string content in OpenAI response parser

feat(amp): require API key authentication for management routes

config.example.yaml

@@ -136,8 +136,8 @@ ws-auth: false
 #   upstream-url: "https://ampcode.com"
 #   # Optional: Override API key for Amp upstream (otherwise uses env or file)
 #   upstream-api-key: ""
-#   # Restrict Amp management routes (/api/auth, /api/user, etc.) to localhost only (recommended)
-#   restrict-management-to-localhost: true
+#   # Restrict Amp management routes (/api/auth, /api/user, etc.) to localhost only (default: false)
+#   restrict-management-to-localhost: false
 #   # Force model mappings to run before checking local API keys (default: false)
 #   force-model-mappings: false
 #   # Amp Model Mappings

internal/api/handlers/management/auth_files.go

@@ -26,6 +26,7 @@ import (
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/auth/qwen"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/misc"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
 	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
@@ -266,6 +267,54 @@ func (h *Handler) ListAuthFiles(c *gin.Context) {
 	c.JSON(200, gin.H{"files": files})
 }
 
+// GetAuthFileModels returns the models supported by a specific auth file
+func (h *Handler) GetAuthFileModels(c *gin.Context) {
+	name := c.Query("name")
+	if name == "" {
+		c.JSON(400, gin.H{"error": "name is required"})
+		return
+	}
+
+	// Try to find auth ID via authManager
+	var authID string
+	if h.authManager != nil {
+		auths := h.authManager.List()
+		for _, auth := range auths {
+			if auth.FileName == name || auth.ID == name {
+				authID = auth.ID
+				break
+			}
+		}
+	}
+
+	if authID == "" {
+		authID = name // fallback to filename as ID
+	}
+
+	// Get models from registry
+	reg := registry.GetGlobalRegistry()
+	models := reg.GetModelsForClient(authID)
+
+	result := make([]gin.H, 0, len(models))
+	for _, m := range models {
+		entry := gin.H{
+			"id": m.ID,
+		}
+		if m.DisplayName != "" {
+			entry["display_name"] = m.DisplayName
+		}
+		if m.Type != "" {
+			entry["type"] = m.Type
+		}
+		if m.OwnedBy != "" {
+			entry["owned_by"] = m.OwnedBy
+		}
+		result = append(result, entry)
+	}
+
+	c.JSON(200, gin.H{"models": result})
+}
+
 // List auth files from disk when the auth manager is unavailable.
 func (h *Handler) listAuthFilesFromDisk(c *gin.Context) {
 	entries, err := os.ReadDir(h.cfg.AuthDir)
@@ -1722,6 +1771,17 @@ func (h *Handler) RequestIFlowCookieToken(c *gin.Context) {
 		return
 	}
 
+	// Check for duplicate BXAuth before authentication
+	bxAuth := iflowauth.ExtractBXAuth(cookieValue)
+	if existingFile, err := iflowauth.CheckDuplicateBXAuth(h.cfg.AuthDir, bxAuth); err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"status": "error", "error": "failed to check duplicate"})
+		return
+	} else if existingFile != "" {
+		existingFileName := filepath.Base(existingFile)
+		c.JSON(http.StatusConflict, gin.H{"status": "error", "error": "duplicate BXAuth found", "existing_file": existingFileName})
+		return
+	}
+
 	authSvc := iflowauth.NewIFlowAuth(h.cfg)
 	tokenData, errAuth := authSvc.AuthenticateWithCookie(ctx, cookieValue)
 	if errAuth != nil {
@@ -1744,11 +1804,12 @@ func (h *Handler) RequestIFlowCookieToken(c *gin.Context) {
 	}
 
 	tokenStorage.Email = email
+	timestamp := time.Now().Unix()
 
 	record := &coreauth.Auth{
-		ID:       fmt.Sprintf("iflow-%s.json", fileName),
+		ID:       fmt.Sprintf("iflow-%s-%d.json", fileName, timestamp),
 		Provider: "iflow",
-		FileName: fmt.Sprintf("iflow-%s.json", fileName),
+		FileName: fmt.Sprintf("iflow-%s-%d.json", fileName, timestamp),
 		Storage:  tokenStorage,
 		Metadata: map[string]any{
 			"email":        email,

internal/api/modules/amp/amp.go

@@ -137,7 +137,8 @@ func (m *AmpModule) Register(ctx modules.Context) error {
 		m.registerProviderAliases(ctx.Engine, ctx.BaseHandler, auth)
 
 		// Register management proxy routes once; middleware will gate access when upstream is unavailable.
-		m.registerManagementRoutes(ctx.Engine, ctx.BaseHandler)
+		// Pass auth middleware to require valid API key for all management routes.
+		m.registerManagementRoutes(ctx.Engine, ctx.BaseHandler, auth)
 
 		// If no upstream URL, skip proxy routes but provider aliases are still available
 		if upstreamURL == "" {
@@ -187,9 +188,6 @@ func (m *AmpModule) OnConfigUpdated(cfg *config.Config) error {
 
 	if oldSettings != nil && oldSettings.RestrictManagementToLocalhost != newSettings.RestrictManagementToLocalhost {
 		m.setRestrictToLocalhost(newSettings.RestrictManagementToLocalhost)
-		if !newSettings.RestrictManagementToLocalhost {
-			log.Warnf("amp management routes now accessible from any IP - this is insecure!")
-		}
 	}
 
 	newUpstreamURL := strings.TrimSpace(newSettings.UpstreamURL)

internal/api/modules/amp/fallback_handlers.go

@@ -64,7 +64,7 @@ func logAmpRouting(routeType AmpRouteType, requestedModel, resolvedModel, provid
 		fields["cost"] = "amp_credits"
 		fields["source"] = "ampcode.com"
 		fields["model_id"] = requestedModel // Explicit model_id for easy config reference
-		log.WithFields(fields).Warnf("forwarding to ampcode.com (uses amp credits) - model_id: %s | To use local proxy, add to config: amp-model-mappings: [{from: \"%s\", to: \"<your-local-model>\"}]", requestedModel, requestedModel)
+		log.WithFields(fields).Warnf("forwarding to ampcode.com (uses amp credits) - model_id: %s | To use local provider, add to config: ampcode.model-mappings: [{from: \"%s\", to: \"<your-local-model>\"}]", requestedModel, requestedModel)
 
 	case RouteTypeNoProvider:
 		fields["cost"] = "none"

internal/api/modules/amp/proxy.go

@@ -41,6 +41,11 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
 		originalDirector(req)
 		req.Host = parsed.Host
 
+		// Remove client's Authorization header - it was only used for CLI Proxy API authentication
+		// We will set our own Authorization using the configured upstream-api-key
+		req.Header.Del("Authorization")
+		req.Header.Del("X-Api-Key")
+
 		// Preserve correlation headers for debugging
 		if req.Header.Get("X-Request-ID") == "" {
 			// Could generate one here if needed
@@ -50,7 +55,7 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
 		// Users going through ampcode.com proxy are paying for the service and should get all features
 		// including 1M context window (context-1m-2025-08-07)
 
-		// Inject API key from secret source (precedence: config > env > file)
+		// Inject API key from secret source (only uses upstream-api-key from config)
 		if key, err := secretSource.Get(req.Context()); err == nil && key != "" {
 			req.Header.Set("X-Api-Key", key)
 			req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", key))

internal/api/modules/amp/response_rewriter.go

@@ -39,7 +39,13 @@ func (rw *ResponseRewriter) Write(data []byte) (int, error) {
 	}
 
 	if rw.isStreaming {
-		return rw.ResponseWriter.Write(rw.rewriteStreamChunk(data))
+		n, err := rw.ResponseWriter.Write(rw.rewriteStreamChunk(data))
+		if err == nil {
+			if flusher, ok := rw.ResponseWriter.(http.Flusher); ok {
+				flusher.Flush()
+			}
+		}
+		return n, err
 	}
 	return rw.body.Write(data)
 }

internal/api/modules/amp/routes.go

@@ -98,7 +98,8 @@ func (m *AmpModule) managementAvailabilityMiddleware() gin.HandlerFunc {
 // registerManagementRoutes registers Amp management proxy routes
 // These routes proxy through to the Amp control plane for OAuth, user management, etc.
 // Uses dynamic middleware and proxy getter for hot-reload support.
-func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *handlers.BaseAPIHandler) {
+// The auth middleware validates Authorization header against configured API keys.
+func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *handlers.BaseAPIHandler, auth gin.HandlerFunc) {
 	ampAPI := engine.Group("/api")
 
 	// Always disable CORS for management routes to prevent browser-based attacks
@@ -107,8 +108,9 @@ func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *ha
 	// Apply dynamic localhost-only restriction (hot-reloadable via m.IsRestrictedToLocalhost())
 	ampAPI.Use(m.localhostOnlyMiddleware())
 
-	if !m.IsRestrictedToLocalhost() {
-		log.Warn("amp management routes are NOT restricted to localhost - this is insecure!")
+	// Apply authentication middleware - requires valid API key in Authorization header
+	if auth != nil {
+		ampAPI.Use(auth)
 	}
 
 	// Dynamic proxy handler that uses m.getProxy() for hot-reload support
@@ -154,6 +156,9 @@ func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *ha
 	// Root-level routes that AMP CLI expects without /api prefix
 	// These need the same security middleware as the /api/* routes (dynamic for hot-reload)
 	rootMiddleware := []gin.HandlerFunc{m.managementAvailabilityMiddleware(), noCORSMiddleware(), m.localhostOnlyMiddleware()}
+	if auth != nil {
+		rootMiddleware = append(rootMiddleware, auth)
+	}
 	engine.GET("/threads/*path", append(rootMiddleware, proxyHandler)...)
 	engine.GET("/threads.rss", append(rootMiddleware, proxyHandler)...)
 	engine.GET("/news.rss", append(rootMiddleware, proxyHandler)...)

internal/api/server.go

@@ -568,6 +568,7 @@ func (s *Server) registerManagementRoutes() {
 		mgmt.DELETE("/oauth-excluded-models", s.mgmt.DeleteOAuthExcludedModels)
 
 		mgmt.GET("/auth-files", s.mgmt.ListAuthFiles)
+		mgmt.GET("/auth-files/models", s.mgmt.GetAuthFileModels)
 		mgmt.GET("/auth-files/download", s.mgmt.DownloadAuthFile)
 		mgmt.POST("/auth-files", s.mgmt.UploadAuthFile)
 		mgmt.DELETE("/auth-files", s.mgmt.DeleteAuthFile)

internal/auth/iflow/cookie_helpers.go

@@ -1,7 +1,10 @@
 package iflow
 
 import (
+	"encoding/json"
 	"fmt"
+	"os"
+	"path/filepath"
 	"strings"
 )
 
@@ -36,3 +39,61 @@ func SanitizeIFlowFileName(raw string) string {
 	}
 	return strings.TrimSpace(result.String())
 }
+
+// ExtractBXAuth extracts the BXAuth value from a cookie string.
+func ExtractBXAuth(cookie string) string {
+	parts := strings.Split(cookie, ";")
+	for _, part := range parts {
+		part = strings.TrimSpace(part)
+		if strings.HasPrefix(part, "BXAuth=") {
+			return strings.TrimPrefix(part, "BXAuth=")
+		}
+	}
+	return ""
+}
+
+// CheckDuplicateBXAuth checks if the given BXAuth value already exists in any iflow auth file.
+// Returns the path of the existing file if found, empty string otherwise.
+func CheckDuplicateBXAuth(authDir, bxAuth string) (string, error) {
+	if bxAuth == "" {
+		return "", nil
+	}
+
+	entries, err := os.ReadDir(authDir)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return "", nil
+		}
+		return "", fmt.Errorf("read auth dir failed: %w", err)
+	}
+
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		name := entry.Name()
+		if !strings.HasPrefix(name, "iflow-") || !strings.HasSuffix(name, ".json") {
+			continue
+		}
+
+		filePath := filepath.Join(authDir, name)
+		data, err := os.ReadFile(filePath)
+		if err != nil {
+			continue
+		}
+
+		var tokenData struct {
+			Cookie string `json:"cookie"`
+		}
+		if err := json.Unmarshal(data, &tokenData); err != nil {
+			continue
+		}
+
+		existingBXAuth := ExtractBXAuth(tokenData.Cookie)
+		if existingBXAuth != "" && existingBXAuth == bxAuth {
+			return filePath, nil
+		}
+	}
+
+	return "", nil
+}

internal/auth/iflow/iflow_auth.go

@@ -494,11 +494,18 @@ func (ia *IFlowAuth) CreateCookieTokenStorage(data *IFlowTokenData) *IFlowTokenS
 		return nil
 	}
 
+	// Only save the BXAuth field from the cookie
+	bxAuth := ExtractBXAuth(data.Cookie)
+	cookieToSave := ""
+	if bxAuth != "" {
+		cookieToSave = "BXAuth=" + bxAuth + ";"
+	}
+
 	return &IFlowTokenStorage{
 		APIKey:      data.APIKey,
 		Email:       data.Email,
 		Expire:      data.Expire,
-		Cookie:      data.Cookie,
+		Cookie:      cookieToSave,
 		LastRefresh: time.Now().Format(time.RFC3339),
 		Type:        "iflow",
 	}

internal/cmd/iflow_cookie.go

@@ -5,7 +5,9 @@ import (
 	"context"
 	"fmt"
 	"os"
+	"path/filepath"
 	"strings"
+	"time"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/auth/iflow"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
@@ -37,6 +39,16 @@ func DoIFlowCookieAuth(cfg *config.Config, options *LoginOptions) {
 		return
 	}
 
+	// Check for duplicate BXAuth before authentication
+	bxAuth := iflow.ExtractBXAuth(cookie)
+	if existingFile, err := iflow.CheckDuplicateBXAuth(cfg.AuthDir, bxAuth); err != nil {
+		fmt.Printf("Failed to check duplicate: %v\n", err)
+		return
+	} else if existingFile != "" {
+		fmt.Printf("Duplicate BXAuth found, authentication already exists: %s\n", filepath.Base(existingFile))
+		return
+	}
+
 	// Authenticate with cookie
 	auth := iflow.NewIFlowAuth(cfg)
 	ctx := context.Background()
@@ -82,5 +94,5 @@ func promptForCookie(promptFn func(string) (string, error)) (string, error) {
 // getAuthFilePath returns the auth file path for the given provider and email
 func getAuthFilePath(cfg *config.Config, provider, email string) string {
 	fileName := iflow.SanitizeIFlowFileName(email)
-	return fmt.Sprintf("%s/%s-%s.json", cfg.AuthDir, provider, fileName)
+	return fmt.Sprintf("%s/%s-%s-%d.json", cfg.AuthDir, provider, fileName, time.Now().Unix())
 }

internal/config/config.go

@@ -139,7 +139,7 @@ type AmpCode struct {
 
 	// RestrictManagementToLocalhost restricts Amp management routes (/api/user, /api/threads, etc.)
 	// to only accept connections from localhost (127.0.0.1, ::1). When true, prevents drive-by
-	// browser attacks and remote access to management endpoints. Default: true (recommended).
+	// browser attacks and remote access to management endpoints. Default: false (API key auth is sufficient).
 	RestrictManagementToLocalhost bool `yaml:"restrict-management-to-localhost" json:"restrict-management-to-localhost"`
 
 	// ModelMappings defines model name mappings for Amp CLI requests.
@@ -327,7 +327,7 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	cfg.LoggingToFile = false
 	cfg.UsageStatisticsEnabled = false
 	cfg.DisableCooling = false
-	cfg.AmpCode.RestrictManagementToLocalhost = true // Default to secure: only localhost access
+	cfg.AmpCode.RestrictManagementToLocalhost = false // Default to false: API key auth is sufficient
 	if err = yaml.Unmarshal(data, &cfg); err != nil {
 		if optional {
 			// In cloud deploy mode, if YAML parsing fails, return empty config instead of error.

internal/registry/model_definitions.go

@@ -580,7 +580,7 @@ func GetOpenAIModels() []*ModelInfo {
 			ContextLength:       400000,
 			MaxCompletionTokens: 128000,
 			SupportedParameters: []string{"tools"},
-			Thinking:            &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
+			Thinking:            &ThinkingSupport{Levels: []string{"none", "low", "medium", "high", "xhigh"}},
 		},
 	}
 }
@@ -648,10 +648,11 @@ func GetIFlowModels() []*ModelInfo {
 		{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400},
 		{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model", Created: 1752192000},
 		{ID: "kimi-k2-thinking", DisplayName: "Kimi-K2-Thinking", Description: "Moonshot Kimi K2 thinking model", Created: 1762387200, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
-		{ID: "deepseek-v3.2-chat", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2", Created: 1764576000},
+		{ID: "deepseek-v3.2-chat", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2 Chat", Created: 1764576000},
+		{ID: "deepseek-v3.2-reasoner", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2 Reasoner", Created: 1764576000},
 		{ID: "deepseek-v3.2", DisplayName: "DeepSeek-V3.2-Exp", Description: "DeepSeek V3.2 experimental", Created: 1759104000},
 		{ID: "deepseek-v3.1", DisplayName: "DeepSeek-V3.1-Terminus", Description: "DeepSeek V3.1 Terminus", Created: 1756339200},
-		{ID: "deepseek-r1", DisplayName: "DeepSeek-R1", Description: "DeepSeek reasoning model R1", Created: 1737331200, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
+		{ID: "deepseek-r1", DisplayName: "DeepSeek-R1", Description: "DeepSeek reasoning model R1", Created: 1737331200},
 		{ID: "deepseek-v3", DisplayName: "DeepSeek-V3-671B", Description: "DeepSeek V3 671B", Created: 1734307200},
 		{ID: "qwen3-32b", DisplayName: "Qwen3-32B", Description: "Qwen3 32B", Created: 1747094400},
 		{ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},

internal/registry/model_registry.go

@@ -90,6 +90,9 @@ type ModelRegistry struct {
 	models map[string]*ModelRegistration
 	// clientModels maps client ID to the models it provides
 	clientModels map[string][]string
+	// clientModelInfos maps client ID to a map of model ID -> ModelInfo
+	// This preserves the original model info provided by each client
+	clientModelInfos map[string]map[string]*ModelInfo
 	// clientProviders maps client ID to its provider identifier
 	clientProviders map[string]string
 	// mutex ensures thread-safe access to the registry
@@ -104,10 +107,11 @@ var registryOnce sync.Once
 func GetGlobalRegistry() *ModelRegistry {
 	registryOnce.Do(func() {
 		globalRegistry = &ModelRegistry{
-			models:          make(map[string]*ModelRegistration),
-			clientModels:    make(map[string][]string),
-			clientProviders: make(map[string]string),
-			mutex:           &sync.RWMutex{},
+			models:           make(map[string]*ModelRegistration),
+			clientModels:     make(map[string][]string),
+			clientModelInfos: make(map[string]map[string]*ModelInfo),
+			clientProviders:  make(map[string]string),
+			mutex:            &sync.RWMutex{},
 		}
 	})
 	return globalRegistry
@@ -144,6 +148,7 @@ func (r *ModelRegistry) RegisterClient(clientID, clientProvider string, models [
 		// No models supplied; unregister existing client state if present.
 		r.unregisterClientInternal(clientID)
 		delete(r.clientModels, clientID)
+		delete(r.clientModelInfos, clientID)
 		delete(r.clientProviders, clientID)
 		misc.LogCredentialSeparator()
 		return
@@ -152,7 +157,7 @@ func (r *ModelRegistry) RegisterClient(clientID, clientProvider string, models [
 	now := time.Now()
 
 	oldModels, hadExisting := r.clientModels[clientID]
-	oldProvider, _ := r.clientProviders[clientID]
+	oldProvider := r.clientProviders[clientID]
 	providerChanged := oldProvider != provider
 	if !hadExisting {
 		// Pure addition path.
@@ -161,6 +166,12 @@ func (r *ModelRegistry) RegisterClient(clientID, clientProvider string, models [
 			r.addModelRegistration(modelID, provider, model, now)
 		}
 		r.clientModels[clientID] = append([]string(nil), rawModelIDs...)
+		// Store client's own model infos
+		clientInfos := make(map[string]*ModelInfo, len(newModels))
+		for id, m := range newModels {
+			clientInfos[id] = cloneModelInfo(m)
+		}
+		r.clientModelInfos[clientID] = clientInfos
 		if provider != "" {
 			r.clientProviders[clientID] = provider
 		} else {
@@ -287,6 +298,12 @@ func (r *ModelRegistry) RegisterClient(clientID, clientProvider string, models [
 	if len(rawModelIDs) > 0 {
 		r.clientModels[clientID] = append([]string(nil), rawModelIDs...)
 	}
+	// Update client's own model infos
+	clientInfos := make(map[string]*ModelInfo, len(newModels))
+	for id, m := range newModels {
+		clientInfos[id] = cloneModelInfo(m)
+	}
+	r.clientModelInfos[clientID] = clientInfos
 	if provider != "" {
 		r.clientProviders[clientID] = provider
 	} else {
@@ -436,6 +453,7 @@ func (r *ModelRegistry) unregisterClientInternal(clientID string) {
 	}
 
 	delete(r.clientModels, clientID)
+	delete(r.clientModelInfos, clientID)
 	if hasProvider {
 		delete(r.clientProviders, clientID)
 	}
@@ -871,3 +889,44 @@ func (r *ModelRegistry) GetFirstAvailableModel(handlerType string) (string, erro
 
 	return "", fmt.Errorf("no available clients for any model in handler type: %s", handlerType)
 }
+
+// GetModelsForClient returns the models registered for a specific client.
+// Parameters:
+//   - clientID: The client identifier (typically auth file name or auth ID)
+//
+// Returns:
+//   - []*ModelInfo: List of models registered for this client, nil if client not found
+func (r *ModelRegistry) GetModelsForClient(clientID string) []*ModelInfo {
+	r.mutex.RLock()
+	defer r.mutex.RUnlock()
+
+	modelIDs, exists := r.clientModels[clientID]
+	if !exists || len(modelIDs) == 0 {
+		return nil
+	}
+
+	// Try to use client-specific model infos first
+	clientInfos := r.clientModelInfos[clientID]
+
+	seen := make(map[string]struct{})
+	result := make([]*ModelInfo, 0, len(modelIDs))
+	for _, modelID := range modelIDs {
+		if _, dup := seen[modelID]; dup {
+			continue
+		}
+		seen[modelID] = struct{}{}
+
+		// Prefer client's own model info to preserve original type/owned_by
+		if clientInfos != nil {
+			if info, ok := clientInfos[modelID]; ok && info != nil {
+				result = append(result, info)
+				continue
+			}
+		}
+		// Fallback to global registry (for backwards compatibility)
+		if reg, ok := r.models[modelID]; ok && reg.Info != nil {
+			result = append(result, reg.Info)
+		}
+	}
+	return result
+}

internal/runtime/executor/aistudio_executor.go

@@ -322,7 +322,7 @@ func (e *AIStudioExecutor) translateRequest(req cliproxyexecutor.Request, opts c
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
-	payload = applyThinkingMetadata(payload, req.Metadata, req.Model)
+	payload = ApplyThinkingMetadata(payload, req.Metadata, req.Model)
 	payload = util.ApplyDefaultThinkingIfNeeded(req.Model, payload)
 	payload = util.ConvertThinkingLevelToBudget(payload)
 	payload = util.NormalizeGeminiThinkingBudget(req.Model, payload)
@@ -384,8 +384,16 @@ func ensureColonSpacedJSON(payload []byte) []byte {
 
 	for i := 0; i < len(indented); i++ {
 		ch := indented[i]
-		if ch == '"' && (i == 0 || indented[i-1] != '\\') {
-			inString = !inString
+		if ch == '"' {
+			// A quote is escaped only when preceded by an odd number of consecutive backslashes.
+			// For example: "\\\"" keeps the quote inside the string, but "\\\\" closes the string.
+			backslashes := 0
+			for j := i - 1; j >= 0 && indented[j] == '\\'; j-- {
+				backslashes++
+			}
+			if backslashes%2 == 0 {
+				inString = !inString
+			}
 		}
 
 		if !inString {

internal/runtime/executor/codex_executor.go

@@ -54,9 +54,9 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("codex")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort")
-	body = normalizeThinkingConfig(body, upstreamModel)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -152,9 +152,9 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	to := sdktranslator.FromString("codex")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort")
-	body = normalizeThinkingConfig(body, upstreamModel)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -254,7 +254,7 @@ func (e *CodexExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth
 
 	modelForCounting := req.Model
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort")
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
 	body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
 	body, _ = sjson.SetBytes(body, "stream", false)

internal/runtime/executor/gemini_cli_executor.go

@@ -11,6 +11,8 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"regexp"
+	"strconv"
 	"strings"
 	"time"
 
@@ -784,20 +786,45 @@ func parseRetryDelay(errorBody []byte) (*time.Duration, error) {
 	// Try to parse the retryDelay from the error response
 	// Format: error.details[].retryDelay where @type == "type.googleapis.com/google.rpc.RetryInfo"
 	details := gjson.GetBytes(errorBody, "error.details")
-	if !details.Exists() || !details.IsArray() {
-		return nil, fmt.Errorf("no error.details found")
+	if details.Exists() && details.IsArray() {
+		for _, detail := range details.Array() {
+			typeVal := detail.Get("@type").String()
+			if typeVal == "type.googleapis.com/google.rpc.RetryInfo" {
+				retryDelay := detail.Get("retryDelay").String()
+				if retryDelay != "" {
+					// Parse duration string like "0.847655010s"
+					duration, err := time.ParseDuration(retryDelay)
+					if err != nil {
+						return nil, fmt.Errorf("failed to parse duration")
+					}
+					return &duration, nil
+				}
+			}
+		}
+
+		// Fallback: try ErrorInfo.metadata.quotaResetDelay (e.g., "373.801628ms")
+		for _, detail := range details.Array() {
+			typeVal := detail.Get("@type").String()
+			if typeVal == "type.googleapis.com/google.rpc.ErrorInfo" {
+				quotaResetDelay := detail.Get("metadata.quotaResetDelay").String()
+				if quotaResetDelay != "" {
+					duration, err := time.ParseDuration(quotaResetDelay)
+					if err == nil {
+						return &duration, nil
+					}
+				}
+			}
+		}
 	}
 
-	for _, detail := range details.Array() {
-		typeVal := detail.Get("@type").String()
-		if typeVal == "type.googleapis.com/google.rpc.RetryInfo" {
-			retryDelay := detail.Get("retryDelay").String()
-			if retryDelay != "" {
-				// Parse duration string like "0.847655010s"
-				duration, err := time.ParseDuration(retryDelay)
-				if err != nil {
-					return nil, fmt.Errorf("failed to parse duration")
-				}
+	// Fallback: parse from error.message "Your quota will reset after Xs."
+	message := gjson.GetBytes(errorBody, "error.message").String()
+	if message != "" {
+		re := regexp.MustCompile(`after\s+(\d+)s\.?`)
+		if matches := re.FindStringSubmatch(message); len(matches) > 1 {
+			seconds, err := strconv.Atoi(matches[1])
+			if err == nil {
+				duration := time.Duration(seconds) * time.Second
 				return &duration, nil
 			}
 		}

internal/runtime/executor/gemini_executor.go

@@ -83,7 +83,7 @@ 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)
-	body = applyThinkingMetadata(body, req.Metadata, req.Model)
+	body = ApplyThinkingMetadata(body, req.Metadata, req.Model)
 	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
 	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
 	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
@@ -178,7 +178,7 @@ 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)
-	body = applyThinkingMetadata(body, req.Metadata, req.Model)
+	body = ApplyThinkingMetadata(body, req.Metadata, req.Model)
 	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
 	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
 	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
@@ -290,7 +290,7 @@ 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)
-	translatedReq = applyThinkingMetadata(translatedReq, req.Metadata, req.Model)
+	translatedReq = ApplyThinkingMetadata(translatedReq, req.Metadata, req.Model)
 	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
 	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)

internal/runtime/executor/iflow_executor.go

@@ -57,13 +57,13 @@ func (e *IFlowExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort")
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -148,13 +148,13 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort")
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	// Ensure tools array exists to avoid provider quirks similar to Qwen's behaviour.
@@ -219,7 +219,7 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 		}()
 
 		scanner := bufio.NewScanner(httpResp.Body)
-		scanner.Buffer(nil, 52_428_800) // 50MB 
+		scanner.Buffer(nil, 52_428_800) // 50MB
 		var param any
 		for scanner.Scan() {
 			line := scanner.Bytes()

internal/runtime/executor/openai_compat_executor.go

@@ -54,17 +54,19 @@ func (e *OpenAICompatExecutor) Execute(ctx context.Context, auth *cliproxyauth.A
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("openai")
 	translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), opts.Stream)
-	if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
+	modelOverride := e.resolveUpstreamModel(req.Model, auth)
+	if modelOverride != "" {
 		translated = e.overrideModel(translated, modelOverride)
 	}
 	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, to.String(), "", translated)
-	translated = applyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort")
+	allowCompat := e.allowCompatReasoningEffort(req.Model, auth)
+	translated = ApplyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" {
+	if upstreamModel != "" && modelOverride == "" {
 		translated, _ = sjson.SetBytes(translated, "model", upstreamModel)
 	}
-	translated = normalizeThinkingConfig(translated, upstreamModel)
-	if errValidate := validateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
+	if errValidate := ValidateThinkingConfig(translated, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 
@@ -148,17 +150,19 @@ func (e *OpenAICompatExecutor) ExecuteStream(ctx context.Context, auth *cliproxy
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("openai")
 	translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
+	modelOverride := e.resolveUpstreamModel(req.Model, auth)
+	if modelOverride != "" {
 		translated = e.overrideModel(translated, modelOverride)
 	}
 	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, to.String(), "", translated)
-	translated = applyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort")
+	allowCompat := e.allowCompatReasoningEffort(req.Model, auth)
+	translated = ApplyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" {
+	if upstreamModel != "" && modelOverride == "" {
 		translated, _ = sjson.SetBytes(translated, "model", upstreamModel)
 	}
-	translated = normalizeThinkingConfig(translated, upstreamModel)
-	if errValidate := validateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
+	if errValidate := ValidateThinkingConfig(translated, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 
@@ -323,6 +327,27 @@ func (e *OpenAICompatExecutor) resolveUpstreamModel(alias string, auth *cliproxy
 	return ""
 }
 
+func (e *OpenAICompatExecutor) allowCompatReasoningEffort(model string, auth *cliproxyauth.Auth) bool {
+	trimmed := strings.TrimSpace(model)
+	if trimmed == "" || e == nil || e.cfg == nil {
+		return false
+	}
+	compat := e.resolveCompatConfig(auth)
+	if compat == nil || len(compat.Models) == 0 {
+		return false
+	}
+	for i := range compat.Models {
+		entry := compat.Models[i]
+		if strings.EqualFold(strings.TrimSpace(entry.Alias), trimmed) {
+			return true
+		}
+		if strings.EqualFold(strings.TrimSpace(entry.Name), trimmed) {
+			return true
+		}
+	}
+	return false
+}
+
 func (e *OpenAICompatExecutor) resolveCompatConfig(auth *cliproxyauth.Auth) *config.OpenAICompatibility {
 	if auth == nil || e.cfg == nil {
 		return nil

internal/runtime/executor/payload_helpers.go

@@ -11,9 +11,9 @@ import (
 	"github.com/tidwall/sjson"
 )
 
-// applyThinkingMetadata applies thinking config from model suffix metadata (e.g., (high), (8192))
+// ApplyThinkingMetadata applies thinking config from model suffix metadata (e.g., (high), (8192))
 // for standard Gemini format payloads. It normalizes the budget when the model supports thinking.
-func applyThinkingMetadata(payload []byte, metadata map[string]any, model string) []byte {
+func ApplyThinkingMetadata(payload []byte, metadata map[string]any, model string) []byte {
 	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
 	if !ok || (budgetOverride == nil && includeOverride == nil) {
 		return payload
@@ -45,22 +45,44 @@ func applyThinkingMetadataCLI(payload []byte, metadata map[string]any, model str
 	return util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)
 }
 
-// applyReasoningEffortMetadata applies reasoning effort overrides from metadata to the given JSON path.
+// ApplyReasoningEffortMetadata applies reasoning effort overrides from metadata to the given JSON path.
 // Metadata values take precedence over any existing field when the model supports thinking, intentionally
 // overwriting caller-provided values to honor suffix/default metadata priority.
-func applyReasoningEffortMetadata(payload []byte, metadata map[string]any, model, field string) []byte {
+func ApplyReasoningEffortMetadata(payload []byte, metadata map[string]any, model, field string, allowCompat bool) []byte {
 	if len(metadata) == 0 {
 		return payload
 	}
-	if !util.ModelSupportsThinking(model) {
-		return payload
-	}
 	if field == "" {
 		return payload
 	}
+	baseModel := util.ResolveOriginalModel(model, metadata)
+	if baseModel == "" {
+		baseModel = model
+	}
+	if !util.ModelSupportsThinking(baseModel) && !allowCompat {
+		return payload
+	}
 	if effort, ok := util.ReasoningEffortFromMetadata(metadata); ok && effort != "" {
-		if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
-			return updated
+		if util.ModelUsesThinkingLevels(baseModel) || allowCompat {
+			if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
+				return updated
+			}
+		}
+	}
+	// Fallback: numeric thinking_budget suffix for level-based (OpenAI-style) models.
+	if util.ModelUsesThinkingLevels(baseModel) || allowCompat {
+		if budget, _, _, matched := util.ThinkingFromMetadata(metadata); matched && budget != nil {
+			if effort, ok := util.OpenAIThinkingBudgetToEffort(baseModel, *budget); ok && effort != "" {
+				if *budget == 0 && effort == "none" && util.ModelUsesThinkingLevels(baseModel) {
+					if _, supported := util.NormalizeReasoningEffortLevel(baseModel, effort); !supported {
+						return StripThinkingFields(payload, false)
+					}
+				}
+
+				if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
+					return updated
+				}
+			}
 		}
 	}
 	return payload
@@ -216,34 +238,43 @@ func matchModelPattern(pattern, model string) bool {
 	return pi == len(pattern)
 }
 
-// normalizeThinkingConfig normalizes thinking-related fields in the payload
+// NormalizeThinkingConfig normalizes thinking-related fields in the payload
 // based on model capabilities. For models without thinking support, it strips
 // reasoning fields. For models with level-based thinking, it validates and
-// normalizes the reasoning effort level.
-func normalizeThinkingConfig(payload []byte, model string) []byte {
+// normalizes the reasoning effort level. For models with numeric budget thinking,
+// it strips the effort string fields.
+func NormalizeThinkingConfig(payload []byte, model string, allowCompat bool) []byte {
 	if len(payload) == 0 || model == "" {
 		return payload
 	}
 
 	if !util.ModelSupportsThinking(model) {
-		return stripThinkingFields(payload)
+		if allowCompat {
+			return payload
+		}
+		return StripThinkingFields(payload, false)
 	}
 
 	if util.ModelUsesThinkingLevels(model) {
-		return normalizeReasoningEffortLevel(payload, model)
+		return NormalizeReasoningEffortLevel(payload, model)
 	}
 
-	return payload
+	// Model supports thinking but uses numeric budgets, not levels.
+	// Strip effort string fields since they are not applicable.
+	return StripThinkingFields(payload, true)
 }
 
-// stripThinkingFields removes thinking-related fields from the payload for
-// models that do not support thinking.
-func stripThinkingFields(payload []byte) []byte {
+// StripThinkingFields removes thinking-related fields from the payload for
+// models that do not support thinking. If effortOnly is true, only removes
+// effort string fields (for models using numeric budgets).
+func StripThinkingFields(payload []byte, effortOnly bool) []byte {
 	fieldsToRemove := []string{
-		"reasoning",
 		"reasoning_effort",
 		"reasoning.effort",
 	}
+	if !effortOnly {
+		fieldsToRemove = append([]string{"reasoning"}, fieldsToRemove...)
+	}
 	out := payload
 	for _, field := range fieldsToRemove {
 		if gjson.GetBytes(out, field).Exists() {
@@ -253,9 +284,9 @@ func stripThinkingFields(payload []byte) []byte {
 	return out
 }
 
-// normalizeReasoningEffortLevel validates and normalizes the reasoning_effort
+// NormalizeReasoningEffortLevel validates and normalizes the reasoning_effort
 // or reasoning.effort field for level-based thinking models.
-func normalizeReasoningEffortLevel(payload []byte, model string) []byte {
+func NormalizeReasoningEffortLevel(payload []byte, model string) []byte {
 	out := payload
 
 	if effort := gjson.GetBytes(out, "reasoning_effort"); effort.Exists() {
@@ -273,10 +304,10 @@ func normalizeReasoningEffortLevel(payload []byte, model string) []byte {
 	return out
 }
 
-// validateThinkingConfig checks for unsupported reasoning levels on level-based models.
+// ValidateThinkingConfig checks for unsupported reasoning levels on level-based models.
 // Returns a statusErr with 400 when an unsupported level is supplied to avoid silently
 // downgrading requests.
-func validateThinkingConfig(payload []byte, model string) error {
+func ValidateThinkingConfig(payload []byte, model string) error {
 	if len(payload) == 0 || model == "" {
 		return nil
 	}

internal/runtime/executor/qwen_executor.go

@@ -51,13 +51,13 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort")
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -131,13 +131,13 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	body = applyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort")
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
 	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
 	if upstreamModel != "" {
 		body, _ = sjson.SetBytes(body, "model", upstreamModel)
 	}
-	body = normalizeThinkingConfig(body, upstreamModel)
-	if errValidate := validateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = NormalizeThinkingConfig(body, upstreamModel, false)
+	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
 	toolsResult := gjson.GetBytes(body, "tools")

internal/translator/antigravity/gemini/antigravity_gemini_request.go

@@ -122,6 +122,38 @@ type FunctionCallGroup struct {
 	ResponsesNeeded int
 }
 
+// parseFunctionResponse attempts to unmarshal a function response part.
+// Falls back to gjson extraction if standard json.Unmarshal fails.
+func parseFunctionResponse(response gjson.Result) map[string]interface{} {
+	var responseMap map[string]interface{}
+	err := json.Unmarshal([]byte(response.Raw), &responseMap)
+	if err == nil {
+		return responseMap
+	}
+
+	log.Debugf("unmarshal function response failed, using fallback: %v", err)
+	funcResp := response.Get("functionResponse")
+	if funcResp.Exists() {
+		fr := map[string]interface{}{
+			"name": funcResp.Get("name").String(),
+			"response": map[string]interface{}{
+				"result": funcResp.Get("response").String(),
+			},
+		}
+		if id := funcResp.Get("id").String(); id != "" {
+			fr["id"] = id
+		}
+		return map[string]interface{}{"functionResponse": fr}
+	}
+
+	return map[string]interface{}{
+		"functionResponse": map[string]interface{}{
+			"name":     "unknown",
+			"response": map[string]interface{}{"result": response.String()},
+		},
+	}
+}
+
 // fixCLIToolResponse performs sophisticated tool response format conversion and grouping.
 // This function transforms the CLI tool response format by intelligently grouping function calls
 // with their corresponding responses, ensuring proper conversation flow and API compatibility.
@@ -180,13 +212,7 @@ func fixCLIToolResponse(input string) (string, error) {
 					// Create merged function response content
 					var responseParts []interface{}
 					for _, response := range groupResponses {
-						var responseMap map[string]interface{}
-						errUnmarshal := json.Unmarshal([]byte(response.Raw), &responseMap)
-						if errUnmarshal != nil {
-							log.Warnf("failed to unmarshal function response: %v\n", errUnmarshal)
-							continue
-						}
-						responseParts = append(responseParts, responseMap)
+						responseParts = append(responseParts, parseFunctionResponse(response))
 					}
 
 					if len(responseParts) > 0 {
@@ -265,13 +291,7 @@ func fixCLIToolResponse(input string) (string, error) {
 
 			var responseParts []interface{}
 			for _, response := range groupResponses {
-				var responseMap map[string]interface{}
-				errUnmarshal := json.Unmarshal([]byte(response.Raw), &responseMap)
-				if errUnmarshal != nil {
-					log.Warnf("failed to unmarshal function response: %v\n", errUnmarshal)
-					continue
-				}
-				responseParts = append(responseParts, responseMap)
+				responseParts = append(responseParts, parseFunctionResponse(response))
 			}
 
 			if len(responseParts) > 0 {

internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go

@@ -39,31 +39,13 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
 	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.include_thoughts", true)
-		case "medium":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 8192)
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
-		case "high":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 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)
-		}
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+		out = util.ApplyReasoningEffortToGeminiCLI(out, re.String())
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)
-	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+	// Only apply for models that use numeric budgets, not discrete levels.
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
 		if tc := gjson.GetBytes(rawJSON, "extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
 			var setBudget bool
 			var budget int

internal/translator/claude/gemini/claude_gemini_request.go

@@ -114,14 +114,16 @@ func ConvertGeminiRequestToClaude(modelName string, inputRawJSON []byte, stream
 			}
 		}
 		// Include thoughts configuration for reasoning process visibility
-		if thinkingConfig := genConfig.Get("thinkingConfig"); thinkingConfig.Exists() && thinkingConfig.IsObject() {
-			if includeThoughts := thinkingConfig.Get("include_thoughts"); includeThoughts.Exists() {
-				if includeThoughts.Type == gjson.True {
-					out, _ = sjson.Set(out, "thinking.type", "enabled")
-					if thinkingBudget := thinkingConfig.Get("thinkingBudget"); thinkingBudget.Exists() {
-						out, _ = sjson.Set(out, "thinking.budget_tokens", thinkingBudget.Int())
-					}
-				}
+		// Only apply for models that support thinking and use numeric budgets, not discrete levels.
+		if thinkingConfig := genConfig.Get("thinkingConfig"); thinkingConfig.Exists() && thinkingConfig.IsObject() && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+			// Check for thinkingBudget first - if present, enable thinking with budget
+			if thinkingBudget := thinkingConfig.Get("thinkingBudget"); thinkingBudget.Exists() && thinkingBudget.Int() > 0 {
+				out, _ = sjson.Set(out, "thinking.type", "enabled")
+				normalizedBudget := util.NormalizeThinkingBudget(modelName, int(thinkingBudget.Int()))
+				out, _ = sjson.Set(out, "thinking.budget_tokens", normalizedBudget)
+			} else if includeThoughts := thinkingConfig.Get("include_thoughts"); includeThoughts.Exists() && includeThoughts.Type == gjson.True {
+				// Fallback to include_thoughts if no budget specified
+				out, _ = sjson.Set(out, "thinking.type", "enabled")
 			}
 		}
 	}

internal/translator/claude/openai/chat-completions/claude_openai_request.go

@@ -16,6 +16,7 @@ import (
 	"strings"
 
 	"github.com/google/uuid"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -65,18 +66,23 @@ func ConvertOpenAIRequestToClaude(modelName string, inputRawJSON []byte, stream
 
 	root := gjson.ParseBytes(rawJSON)
 
-	if v := root.Get("reasoning_effort"); v.Exists() {
-		out, _ = sjson.Set(out, "thinking.type", "enabled")
-
-		switch v.String() {
-		case "none":
-			out, _ = sjson.Set(out, "thinking.type", "disabled")
-		case "low":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 1024)
-		case "medium":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 8192)
-		case "high":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 24576)
+	if v := root.Get("reasoning_effort"); v.Exists() && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+		effort := strings.ToLower(strings.TrimSpace(v.String()))
+		if effort != "" {
+			budget, ok := util.ThinkingEffortToBudget(modelName, effort)
+			if ok {
+				switch budget {
+				case 0:
+					out, _ = sjson.Set(out, "thinking.type", "disabled")
+				case -1:
+					out, _ = sjson.Set(out, "thinking.type", "enabled")
+				default:
+					if budget > 0 {
+						out, _ = sjson.Set(out, "thinking.type", "enabled")
+						out, _ = sjson.Set(out, "thinking.budget_tokens", budget)
+					}
+				}
+			}
 		}
 	}
 

internal/translator/claude/openai/responses/claude_openai-responses_request.go

@@ -10,6 +10,7 @@ import (
 	"strings"
 
 	"github.com/google/uuid"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -52,20 +53,23 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
 
 	root := gjson.ParseBytes(rawJSON)
 
-	if v := root.Get("reasoning.effort"); v.Exists() {
-		out, _ = sjson.Set(out, "thinking.type", "enabled")
-
-		switch v.String() {
-		case "none":
-			out, _ = sjson.Set(out, "thinking.type", "disabled")
-		case "minimal":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 1024)
-		case "low":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 4096)
-		case "medium":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 8192)
-		case "high":
-			out, _ = sjson.Set(out, "thinking.budget_tokens", 24576)
+	if v := root.Get("reasoning.effort"); v.Exists() && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+		effort := strings.ToLower(strings.TrimSpace(v.String()))
+		if effort != "" {
+			budget, ok := util.ThinkingEffortToBudget(modelName, effort)
+			if ok {
+				switch budget {
+				case 0:
+					out, _ = sjson.Set(out, "thinking.type", "disabled")
+				case -1:
+					out, _ = sjson.Set(out, "thinking.type", "enabled")
+				default:
+					if budget > 0 {
+						out, _ = sjson.Set(out, "thinking.type", "enabled")
+						out, _ = sjson.Set(out, "thinking.budget_tokens", budget)
+					}
+				}
+			}
 		}
 	}
 

internal/translator/codex/claude/codex_claude_request.go

@@ -12,6 +12,7 @@ import (
 	"strings"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/misc"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -214,7 +215,22 @@ func ConvertClaudeRequestToCodex(modelName string, inputRawJSON []byte, _ bool)
 
 	// Add additional configuration parameters for the Codex API.
 	template, _ = sjson.Set(template, "parallel_tool_calls", true)
-	template, _ = sjson.Set(template, "reasoning.effort", "low")
+
+	// Convert thinking.budget_tokens to reasoning.effort for level-based models
+	reasoningEffort := "medium" // default
+	if thinking := rootResult.Get("thinking"); thinking.Exists() && thinking.IsObject() {
+		if thinking.Get("type").String() == "enabled" {
+			if util.ModelUsesThinkingLevels(modelName) {
+				if budgetTokens := thinking.Get("budget_tokens"); budgetTokens.Exists() {
+					budget := int(budgetTokens.Int())
+					if effort, ok := util.OpenAIThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
+						reasoningEffort = effort
+					}
+				}
+			}
+		}
+	}
+	template, _ = sjson.Set(template, "reasoning.effort", reasoningEffort)
 	template, _ = sjson.Set(template, "reasoning.summary", "auto")
 	template, _ = sjson.Set(template, "stream", true)
 	template, _ = sjson.Set(template, "store", false)

internal/translator/codex/gemini/codex_gemini_request.go

@@ -245,7 +245,22 @@ func ConvertGeminiRequestToCodex(modelName string, inputRawJSON []byte, _ bool)
 
 	// Fixed flags aligning with Codex expectations
 	out, _ = sjson.Set(out, "parallel_tool_calls", true)
-	out, _ = sjson.Set(out, "reasoning.effort", "low")
+
+	// Convert thinkingBudget to reasoning.effort for level-based models
+	reasoningEffort := "medium" // default
+	if genConfig := root.Get("generationConfig"); genConfig.Exists() {
+		if thinkingConfig := genConfig.Get("thinkingConfig"); thinkingConfig.Exists() && thinkingConfig.IsObject() {
+			if util.ModelUsesThinkingLevels(modelName) {
+				if thinkingBudget := thinkingConfig.Get("thinkingBudget"); thinkingBudget.Exists() {
+					budget := int(thinkingBudget.Int())
+					if effort, ok := util.OpenAIThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
+						reasoningEffort = effort
+					}
+				}
+			}
+		}
+	}
+	out, _ = sjson.Set(out, "reasoning.effort", reasoningEffort)
 	out, _ = sjson.Set(out, "reasoning.summary", "auto")
 	out, _ = sjson.Set(out, "stream", true)
 	out, _ = sjson.Set(out, "store", false)

internal/translator/codex/openai/chat-completions/codex_openai_request.go

@@ -60,7 +60,7 @@ func ConvertOpenAIRequestToCodex(modelName string, inputRawJSON []byte, stream b
 	if v := gjson.GetBytes(rawJSON, "reasoning_effort"); v.Exists() {
 		out, _ = sjson.Set(out, "reasoning.effort", v.Value())
 	} else {
-		out, _ = sjson.Set(out, "reasoning.effort", "low")
+		out, _ = sjson.Set(out, "reasoning.effort", "medium")
 	}
 	out, _ = sjson.Set(out, "parallel_tool_calls", true)
 	out, _ = sjson.Set(out, "reasoning.summary", "auto")

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

@@ -39,31 +39,13 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
 	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.include_thoughts", true)
-		case "medium":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 8192)
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
-		case "high":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 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)
-		}
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+		out = util.ApplyReasoningEffortToGeminiCLI(out, re.String())
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)
-	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+	// Only apply for models that use numeric budgets, not discrete levels.
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
 		if tc := gjson.GetBytes(rawJSON, "extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
 			var setBudget bool
 			var budget int

internal/translator/gemini/claude/gemini_claude_request.go

@@ -154,7 +154,8 @@ func ConvertClaudeRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 	}
 
 	// Map Anthropic thinking -> Gemini thinkingBudget/include_thoughts when enabled
-	if t := gjson.GetBytes(rawJSON, "thinking"); t.Exists() && t.IsObject() && util.ModelSupportsThinking(modelName) {
+	// Only apply for models that use numeric budgets, not discrete levels.
+	if t := gjson.GetBytes(rawJSON, "thinking"); t.Exists() && t.IsObject() && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
 		if t.Get("type").String() == "enabled" {
 			if b := t.Get("budget_tokens"); b.Exists() && b.Type == gjson.Number {
 				budget := int(b.Int())

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

@@ -37,33 +37,17 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 
 	// Reasoning effort -> thinkingBudget/include_thoughts
 	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
+	// Only convert for models that use numeric budgets (not discrete levels) to avoid
+	// incorrectly applying thinkingBudget for level-based models like gpt-5.
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
 	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.include_thoughts", true)
-		case "medium":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 8192)
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.include_thoughts", true)
-		case "high":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 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)
-		}
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+		out = util.ApplyReasoningEffortToGemini(out, re.String())
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)
-	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+	// Only apply for models that use numeric budgets, not discrete levels.
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
 		if tc := gjson.GetBytes(rawJSON, "extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
 			var setBudget bool
 			var budget int

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

@@ -389,36 +389,16 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 	}
 
 	// OpenAI official reasoning fields take precedence
+	// Only convert for models that use numeric budgets (not discrete levels).
 	hasOfficialThinking := root.Get("reasoning.effort").Exists()
-	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(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.include_thoughts", true)
-		case "low":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 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.include_thoughts", true)
-		case "high":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 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)
-		}
+		out = string(util.ApplyReasoningEffortToGemini([]byte(out), reasoningEffort.String()))
 	}
 
 	// Cherry Studio extension (applies only when official fields are missing)
-	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+	// Only apply for models that use numeric budgets, not discrete levels.
+	if !hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
 		if tc := root.Get("extra_body.google.thinking_config"); tc.Exists() && tc.IsObject() {
 			var setBudget bool
 			var budget int

internal/translator/openai/claude/openai_claude_request.go

@@ -10,6 +10,7 @@ import (
 	"encoding/json"
 	"strings"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -60,6 +61,18 @@ func ConvertClaudeRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 	// Stream
 	out, _ = sjson.Set(out, "stream", stream)
 
+	// Thinking: Convert Claude thinking.budget_tokens to OpenAI reasoning_effort
+	if thinking := root.Get("thinking"); thinking.Exists() && thinking.IsObject() {
+		if thinkingType := thinking.Get("type"); thinkingType.Exists() && thinkingType.String() == "enabled" {
+			if budgetTokens := thinking.Get("budget_tokens"); budgetTokens.Exists() {
+				budget := int(budgetTokens.Int())
+				if effort, ok := util.OpenAIThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
+					out, _ = sjson.Set(out, "reasoning_effort", effort)
+				}
+			}
+		}
+	}
+
 	// Process messages and system
 	var messagesJSON = "[]"
 

internal/translator/openai/gemini/openai_gemini_request.go

@@ -13,6 +13,7 @@ import (
 	"math/big"
 	"strings"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -76,6 +77,17 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 				out, _ = sjson.Set(out, "stop", stops)
 			}
 		}
+
+		// Convert thinkingBudget to reasoning_effort
+		// Always perform conversion to support allowCompat models that may not be in registry
+		if thinkingConfig := genConfig.Get("thinkingConfig"); thinkingConfig.Exists() && thinkingConfig.IsObject() {
+			if thinkingBudget := thinkingConfig.Get("thinkingBudget"); thinkingBudget.Exists() {
+				budget := int(thinkingBudget.Int())
+				if effort, ok := util.OpenAIThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
+					out, _ = sjson.Set(out, "reasoning_effort", effort)
+				}
+			}
+		}
 	}
 
 	// Stream parameter

internal/translator/openai/openai/responses/openai_openai-responses_request.go

@@ -2,6 +2,7 @@ package responses
 
 import (
 	"bytes"
+	"strings"
 
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
@@ -64,7 +65,7 @@ func ConvertOpenAIResponsesRequestToOpenAIChatCompletions(modelName string, inpu
 			}
 
 			switch itemType {
-			case "message":
+			case "message", "":
 				// Handle regular message conversion
 				role := item.Get("role").String()
 				message := `{"role":"","content":""}`
@@ -106,6 +107,8 @@ func ConvertOpenAIResponsesRequestToOpenAIChatCompletions(modelName string, inpu
 					if len(toolCalls) > 0 {
 						message, _ = sjson.Set(message, "tool_calls", toolCalls)
 					}
+				} else if content.Type == gjson.String {
+					message, _ = sjson.Set(message, "content", content.String())
 				}
 
 				out, _ = sjson.SetRaw(out, "messages.-1", message)
@@ -189,23 +192,9 @@ func ConvertOpenAIResponsesRequestToOpenAIChatCompletions(modelName string, inpu
 	}
 
 	if reasoningEffort := root.Get("reasoning.effort"); reasoningEffort.Exists() {
-		switch reasoningEffort.String() {
-		case "none":
-			out, _ = sjson.Set(out, "reasoning_effort", "none")
-		case "auto":
-			out, _ = sjson.Set(out, "reasoning_effort", "auto")
-		case "minimal":
-			out, _ = sjson.Set(out, "reasoning_effort", "low")
-		case "low":
-			out, _ = sjson.Set(out, "reasoning_effort", "low")
-		case "medium":
-			out, _ = sjson.Set(out, "reasoning_effort", "medium")
-		case "high":
-			out, _ = sjson.Set(out, "reasoning_effort", "high")
-		case "xhigh":
-			out, _ = sjson.Set(out, "reasoning_effort", "xhigh")
-		default:
-			out, _ = sjson.Set(out, "reasoning_effort", "auto")
+		effort := strings.ToLower(strings.TrimSpace(reasoningEffort.String()))
+		if effort != "" {
+			out, _ = sjson.Set(out, "reasoning_effort", effort)
 		}
 	}
 

internal/util/claude_thinking.go

@@ -28,6 +28,9 @@ func ApplyClaudeThinkingConfig(body []byte, budget *int) []byte {
 // It uses the unified ResolveThinkingConfigFromMetadata and normalizes the budget.
 // Returns the normalized budget (nil if thinking should not be enabled) and whether it matched.
 func ResolveClaudeThinkingConfig(modelName string, metadata map[string]any) (*int, bool) {
+	if !ModelSupportsThinking(modelName) {
+		return nil, false
+	}
 	budget, include, matched := ResolveThinkingConfigFromMetadata(modelName, metadata)
 	if !matched {
 		return nil, false

internal/util/gemini_thinking.go

@@ -25,9 +25,15 @@ func ApplyGeminiThinkingConfig(body []byte, budget *int, includeThoughts *bool)
 			updated = rewritten
 		}
 	}
-	if includeThoughts != nil {
+	// Default to including thoughts when a budget override is present but no explicit include flag is provided.
+	incl := includeThoughts
+	if incl == nil && budget != nil && *budget != 0 {
+		defaultInclude := true
+		incl = &defaultInclude
+	}
+	if incl != nil {
 		valuePath := "generationConfig.thinkingConfig.include_thoughts"
-		rewritten, err := sjson.SetBytes(updated, valuePath, *includeThoughts)
+		rewritten, err := sjson.SetBytes(updated, valuePath, *incl)
 		if err == nil {
 			updated = rewritten
 		}
@@ -47,9 +53,15 @@ func ApplyGeminiCLIThinkingConfig(body []byte, budget *int, includeThoughts *boo
 			updated = rewritten
 		}
 	}
-	if includeThoughts != nil {
+	// Default to including thoughts when a budget override is present but no explicit include flag is provided.
+	incl := includeThoughts
+	if incl == nil && budget != nil && *budget != 0 {
+		defaultInclude := true
+		incl = &defaultInclude
+	}
+	if incl != nil {
 		valuePath := "request.generationConfig.thinkingConfig.include_thoughts"
-		rewritten, err := sjson.SetBytes(updated, valuePath, *includeThoughts)
+		rewritten, err := sjson.SetBytes(updated, valuePath, *incl)
 		if err == nil {
 			updated = rewritten
 		}
@@ -140,6 +152,71 @@ func NormalizeGeminiCLIThinkingBudget(model string, body []byte) []byte {
 	return updated
 }
 
+// ReasoningEffortBudgetMapping defines the thinkingBudget values for each reasoning effort level.
+var ReasoningEffortBudgetMapping = map[string]int{
+	"none":    0,
+	"auto":    -1,
+	"minimal": 512,
+	"low":     1024,
+	"medium":  8192,
+	"high":    24576,
+	"xhigh":   32768,
+}
+
+// ApplyReasoningEffortToGemini applies OpenAI reasoning_effort to Gemini thinkingConfig
+// for standard Gemini API format (generationConfig.thinkingConfig path).
+// Returns the modified body with thinkingBudget and include_thoughts set.
+func ApplyReasoningEffortToGemini(body []byte, effort string) []byte {
+	normalized := strings.ToLower(strings.TrimSpace(effort))
+	if normalized == "" {
+		return body
+	}
+
+	budgetPath := "generationConfig.thinkingConfig.thinkingBudget"
+	includePath := "generationConfig.thinkingConfig.include_thoughts"
+
+	if normalized == "none" {
+		body, _ = sjson.DeleteBytes(body, "generationConfig.thinkingConfig")
+		return body
+	}
+
+	budget, ok := ReasoningEffortBudgetMapping[normalized]
+	if !ok {
+		return body
+	}
+
+	body, _ = sjson.SetBytes(body, budgetPath, budget)
+	body, _ = sjson.SetBytes(body, includePath, true)
+	return body
+}
+
+// ApplyReasoningEffortToGeminiCLI applies OpenAI reasoning_effort to Gemini CLI thinkingConfig
+// for Gemini CLI API format (request.generationConfig.thinkingConfig path).
+// Returns the modified body with thinkingBudget and include_thoughts set.
+func ApplyReasoningEffortToGeminiCLI(body []byte, effort string) []byte {
+	normalized := strings.ToLower(strings.TrimSpace(effort))
+	if normalized == "" {
+		return body
+	}
+
+	budgetPath := "request.generationConfig.thinkingConfig.thinkingBudget"
+	includePath := "request.generationConfig.thinkingConfig.include_thoughts"
+
+	if normalized == "none" {
+		body, _ = sjson.DeleteBytes(body, "request.generationConfig.thinkingConfig")
+		return body
+	}
+
+	budget, ok := ReasoningEffortBudgetMapping[normalized]
+	if !ok {
+		return body
+	}
+
+	body, _ = sjson.SetBytes(body, budgetPath, budget)
+	body, _ = sjson.SetBytes(body, includePath, true)
+	return body
+}
+
 // ConvertThinkingLevelToBudget checks for "generationConfig.thinkingConfig.thinkingLevel"
 // and converts it to "thinkingBudget".
 // "high" -> 32768

internal/util/openai_thinking.go

@@ -0,0 +1,37 @@
+package util
+
+// OpenAIThinkingBudgetToEffort maps a numeric thinking budget (tokens)
+// into an OpenAI-style reasoning effort level for level-based models.
+//
+// Ranges:
+//   - 0            -> "none"
+//   - -1           -> "auto"
+//   - 1..1024      -> "low"
+//   - 1025..8192   -> "medium"
+//   - 8193..24576  -> "high"
+//   - 24577..      -> highest supported level for the model (defaults to "xhigh")
+//
+// Negative values other than -1 are treated as unsupported.
+func OpenAIThinkingBudgetToEffort(model string, budget int) (string, bool) {
+	switch {
+	case budget == -1:
+		return "auto", true
+	case budget < -1:
+		return "", false
+	case budget == 0:
+		return "none", true
+	case budget > 0 && budget <= 1024:
+		return "low", true
+	case budget <= 8192:
+		return "medium", true
+	case budget <= 24576:
+		return "high", true
+	case budget > 24576:
+		if levels := GetModelThinkingLevels(model); len(levels) > 0 {
+			return levels[len(levels)-1], true
+		}
+		return "xhigh", true
+	default:
+		return "", false
+	}
+}

internal/util/thinking.go

@@ -25,33 +25,33 @@ func ModelSupportsThinking(model string) bool {
 // 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 found, minBudget, maxBudget, zeroAllowed, dynamicAllowed := thinkingRangeFromRegistry(model); found {
 			if dynamicAllowed {
 				return -1
 			}
-			mid := (min + max) / 2
+			mid := (minBudget + maxBudget) / 2
 			if mid <= 0 && zeroAllowed {
 				return 0
 			}
 			if mid <= 0 {
-				return min
+				return minBudget
 			}
 			return mid
 		}
 		return -1
 	}
-	if found, min, max, zeroAllowed, _ := thinkingRangeFromRegistry(model); found {
+	if found, minBudget, maxBudget, zeroAllowed, _ := thinkingRangeFromRegistry(model); found {
 		if budget == 0 {
 			if zeroAllowed {
 				return 0
 			}
-			return min
+			return minBudget
 		}
-		if budget < min {
-			return min
+		if budget < minBudget {
+			return minBudget
 		}
-		if budget > max {
-			return max
+		if budget > maxBudget {
+			return maxBudget
 		}
 		return budget
 	}
@@ -105,3 +105,16 @@ func NormalizeReasoningEffortLevel(model, effort string) (string, bool) {
 	}
 	return "", false
 }
+
+// IsOpenAICompatibilityModel reports whether the model is registered as an OpenAI-compatibility model.
+// These models may not advertise Thinking metadata in the registry.
+func IsOpenAICompatibilityModel(model string) bool {
+	if model == "" {
+		return false
+	}
+	info := registry.GetGlobalRegistry().GetModelInfo(model)
+	if info == nil {
+		return false
+	}
+	return strings.EqualFold(strings.TrimSpace(info.Type), "openai-compatibility")
+}

internal/util/thinking_suffix.go

@@ -163,6 +163,11 @@ func ResolveThinkingConfigFromMetadata(model string, metadata map[string]any) (*
 	if !matched {
 		return nil, nil, false
 	}
+	// Level-based models (OpenAI-style) do not accept numeric thinking budgets in
+	// Claude/Gemini-style protocols, so we don't derive budgets for them here.
+	if ModelUsesThinkingLevels(model) {
+		return nil, nil, false
+	}
 
 	if budget == nil && effort != nil {
 		if derived, ok := ThinkingEffortToBudget(model, *effort); ok {

internal/watcher/watcher.go

@@ -14,6 +14,7 @@ import (
 	"os"
 	"path/filepath"
 	"reflect"
+	"runtime"
 	"sort"
 	"strings"
 	"sync"
@@ -61,6 +62,7 @@ type Watcher struct {
 	reloadCallback    func(*config.Config)
 	watcher           *fsnotify.Watcher
 	lastAuthHashes    map[string]string
+	lastRemoveTimes   map[string]time.Time
 	lastConfigHash    string
 	authQueue         chan<- AuthUpdate
 	currentAuths      map[string]*coreauth.Auth
@@ -127,8 +129,9 @@ type AuthUpdate struct {
 const (
 	// replaceCheckDelay is a short delay to allow atomic replace (rename) to settle
 	// before deciding whether a Remove event indicates a real deletion.
-	replaceCheckDelay    = 50 * time.Millisecond
-	configReloadDebounce = 150 * time.Millisecond
+	replaceCheckDelay        = 50 * time.Millisecond
+	configReloadDebounce     = 150 * time.Millisecond
+	authRemoveDebounceWindow = 1 * time.Second
 )
 
 // NewWatcher creates a new file watcher instance
@@ -721,8 +724,9 @@ func (w *Watcher) authFileUnchanged(path string) (bool, error) {
 	sum := sha256.Sum256(data)
 	curHash := hex.EncodeToString(sum[:])
 
+	normalized := w.normalizeAuthPath(path)
 	w.clientsMutex.RLock()
-	prevHash, ok := w.lastAuthHashes[path]
+	prevHash, ok := w.lastAuthHashes[normalized]
 	w.clientsMutex.RUnlock()
 	if ok && prevHash == curHash {
 		return true, nil
@@ -731,19 +735,63 @@ func (w *Watcher) authFileUnchanged(path string) (bool, error) {
 }
 
 func (w *Watcher) isKnownAuthFile(path string) bool {
+	normalized := w.normalizeAuthPath(path)
 	w.clientsMutex.RLock()
 	defer w.clientsMutex.RUnlock()
-	_, ok := w.lastAuthHashes[path]
+	_, ok := w.lastAuthHashes[normalized]
 	return ok
 }
 
+func (w *Watcher) normalizeAuthPath(path string) string {
+	trimmed := strings.TrimSpace(path)
+	if trimmed == "" {
+		return ""
+	}
+	cleaned := filepath.Clean(trimmed)
+	if runtime.GOOS == "windows" {
+		cleaned = strings.TrimPrefix(cleaned, `\\?\`)
+		cleaned = strings.ToLower(cleaned)
+	}
+	return cleaned
+}
+
+func (w *Watcher) shouldDebounceRemove(normalizedPath string, now time.Time) bool {
+	if normalizedPath == "" {
+		return false
+	}
+	w.clientsMutex.Lock()
+	if w.lastRemoveTimes == nil {
+		w.lastRemoveTimes = make(map[string]time.Time)
+	}
+	if last, ok := w.lastRemoveTimes[normalizedPath]; ok {
+		if now.Sub(last) < authRemoveDebounceWindow {
+			w.clientsMutex.Unlock()
+			return true
+		}
+	}
+	w.lastRemoveTimes[normalizedPath] = now
+	if len(w.lastRemoveTimes) > 128 {
+		cutoff := now.Add(-2 * authRemoveDebounceWindow)
+		for p, t := range w.lastRemoveTimes {
+			if t.Before(cutoff) {
+				delete(w.lastRemoveTimes, p)
+			}
+		}
+	}
+	w.clientsMutex.Unlock()
+	return false
+}
+
 // handleEvent processes individual file system events
 func (w *Watcher) handleEvent(event fsnotify.Event) {
 	// Filter only relevant events: config file or auth-dir JSON files.
 	configOps := fsnotify.Write | fsnotify.Create | fsnotify.Rename
-	isConfigEvent := event.Name == w.configPath && event.Op&configOps != 0
+	normalizedName := w.normalizeAuthPath(event.Name)
+	normalizedConfigPath := w.normalizeAuthPath(w.configPath)
+	normalizedAuthDir := w.normalizeAuthPath(w.authDir)
+	isConfigEvent := normalizedName == normalizedConfigPath && event.Op&configOps != 0
 	authOps := fsnotify.Create | fsnotify.Write | fsnotify.Remove | fsnotify.Rename
-	isAuthJSON := strings.HasPrefix(event.Name, w.authDir) && strings.HasSuffix(event.Name, ".json") && event.Op&authOps != 0
+	isAuthJSON := strings.HasPrefix(normalizedName, normalizedAuthDir) && strings.HasSuffix(normalizedName, ".json") && event.Op&authOps != 0
 	if !isConfigEvent && !isAuthJSON {
 		// Ignore unrelated files (e.g., cookie snapshots *.cookie) and other noise.
 		return
@@ -761,6 +809,10 @@ func (w *Watcher) handleEvent(event fsnotify.Event) {
 
 	// Handle auth directory changes incrementally (.json only)
 	if event.Op&(fsnotify.Remove|fsnotify.Rename) != 0 {
+		if w.shouldDebounceRemove(normalizedName, now) {
+			log.Debugf("debouncing remove event for %s", filepath.Base(event.Name))
+			return
+		}
 		// Atomic replace on some platforms may surface as Rename (or Remove) before the new file is ready.
 		// Wait briefly; if the path exists again, treat as an update instead of removal.
 		time.Sleep(replaceCheckDelay)
@@ -978,7 +1030,8 @@ func (w *Watcher) reloadClients(rescanAuth bool, affectedOAuthProviders []string
 				if !info.IsDir() && strings.HasSuffix(strings.ToLower(info.Name()), ".json") {
 					if data, errReadFile := os.ReadFile(path); errReadFile == nil && len(data) > 0 {
 						sum := sha256.Sum256(data)
-						w.lastAuthHashes[path] = hex.EncodeToString(sum[:])
+						normalizedPath := w.normalizeAuthPath(path)
+						w.lastAuthHashes[normalizedPath] = hex.EncodeToString(sum[:])
 					}
 				}
 				return nil
@@ -1025,6 +1078,7 @@ func (w *Watcher) addOrUpdateClient(path string) {
 
 	sum := sha256.Sum256(data)
 	curHash := hex.EncodeToString(sum[:])
+	normalized := w.normalizeAuthPath(path)
 
 	w.clientsMutex.Lock()
 
@@ -1034,14 +1088,14 @@ func (w *Watcher) addOrUpdateClient(path string) {
 		w.clientsMutex.Unlock()
 		return
 	}
-	if prev, ok := w.lastAuthHashes[path]; ok && prev == curHash {
+	if prev, ok := w.lastAuthHashes[normalized]; ok && prev == curHash {
 		log.Debugf("auth file unchanged (hash match), skipping reload: %s", filepath.Base(path))
 		w.clientsMutex.Unlock()
 		return
 	}
 
 	// Update hash cache
-	w.lastAuthHashes[path] = curHash
+	w.lastAuthHashes[normalized] = curHash
 
 	w.clientsMutex.Unlock() // Unlock before the callback
 
@@ -1056,10 +1110,11 @@ func (w *Watcher) addOrUpdateClient(path string) {
 
 // removeClient handles the removal of a single client.
 func (w *Watcher) removeClient(path string) {
+	normalized := w.normalizeAuthPath(path)
 	w.clientsMutex.Lock()
 
 	cfg := w.config
-	delete(w.lastAuthHashes, path)
+	delete(w.lastAuthHashes, normalized)
 
 	w.clientsMutex.Unlock() // Release the lock before the callback
 

sdk/api/handlers/claude/code_handlers.go

@@ -7,7 +7,6 @@
 package claude
 
 import (
-	"bufio"
 	"bytes"
 	"compress/gzip"
 	"context"
@@ -219,52 +218,24 @@ func (h *ClaudeCodeAPIHandler) handleStreamingResponse(c *gin.Context, rawJSON [
 }
 
 func (h *ClaudeCodeAPIHandler) forwardClaudeStream(c *gin.Context, flusher http.Flusher, cancel func(error), data <-chan []byte, errs <-chan *interfaces.ErrorMessage) {
-	// v6.1: Intelligent Buffered Streamer strategy
-	// Enhanced buffering with larger buffer size (16KB) and longer flush interval (120ms).
-	// Smart flush only when buffer is sufficiently filled (≥50%), dramatically reducing
-	// flush frequency from ~12.5Hz to ~5-8Hz while maintaining low latency.
-	writer := bufio.NewWriterSize(c.Writer, 16*1024) // 4KB → 16KB
-	ticker := time.NewTicker(120 * time.Millisecond) // 80ms → 120ms
-	defer ticker.Stop()
-
-	var chunkIdx int
-
+	// OpenAI-style stream forwarding: write each SSE chunk and flush immediately.
+	// This guarantees clients see incremental output even for small responses.
 	for {
 		select {
 		case <-c.Request.Context().Done():
-			// Context cancelled, flush any remaining data before exit
-			_ = writer.Flush()
 			cancel(c.Request.Context().Err())
 			return
 
-		case <-ticker.C:
-			// Smart flush: only flush when buffer has sufficient data (≥50% full)
-			// This reduces flush frequency while ensuring data flows naturally
-			buffered := writer.Buffered()
-			if buffered >= 8*1024 { // At least 8KB (50% of 16KB buffer)
-				if err := writer.Flush(); err != nil {
-					// Error flushing, cancel and return
-					cancel(err)
-					return
-				}
-				flusher.Flush() // Also flush the underlying http.ResponseWriter
-			}
-
 		case chunk, ok := <-data:
 			if !ok {
-				// Stream ended, flush remaining data
-				_ = writer.Flush()
+				flusher.Flush()
 				cancel(nil)
 				return
 			}
-
-			// Forward the complete SSE event block directly (already formatted by the translator).
-			// The translator returns a complete SSE-compliant event block, including event:, data:, and separators.
-			// The handler just needs to forward it without reassembly.
 			if len(chunk) > 0 {
-				_, _ = writer.Write(chunk)
+				_, _ = c.Writer.Write(chunk)
+				flusher.Flush()
 			}
-			chunkIdx++
 
 		case errMsg, ok := <-errs:
 			if !ok {
@@ -276,21 +247,20 @@ func (h *ClaudeCodeAPIHandler) forwardClaudeStream(c *gin.Context, flusher http.
 					status = errMsg.StatusCode
 				}
 				c.Status(status)
+
 				// An error occurred: emit as a proper SSE error event
 				errorBytes, _ := json.Marshal(h.toClaudeError(errMsg))
-				_, _ = writer.WriteString("event: error\n")
-				_, _ = writer.WriteString("data: ")
-				_, _ = writer.Write(errorBytes)
-				_, _ = writer.WriteString("\n\n")
-				_ = writer.Flush()
+				_, _ = fmt.Fprintf(c.Writer, "event: error\ndata: %s\n\n", errorBytes)
 				flusher.Flush()
 			}
+
 			var execErr error
 			if errMsg != nil {
 				execErr = errMsg.Error
 			}
 			cancel(execErr)
 			return
+		case <-time.After(500 * time.Millisecond):
 		}
 	}
 }

sdk/api/handlers/handlers.go

@@ -116,19 +116,29 @@ func (h *BaseAPIHandler) GetContextWithCancel(handler interfaces.APIHandler, c *
 	newCtx = context.WithValue(newCtx, "gin", c)
 	newCtx = context.WithValue(newCtx, "handler", handler)
 	return newCtx, func(params ...interface{}) {
-		if h.Cfg.RequestLog {
-			if len(params) == 1 {
-				data := params[0]
-				switch data.(type) {
-				case []byte:
-					appendAPIResponse(c, data.([]byte))
-				case error:
-					appendAPIResponse(c, []byte(data.(error).Error()))
-				case string:
-					appendAPIResponse(c, []byte(data.(string)))
-				case bool:
-				case nil:
+		if h.Cfg.RequestLog && len(params) == 1 {
+			var payload []byte
+			switch data := params[0].(type) {
+			case []byte:
+				payload = data
+			case error:
+				if data != nil {
+					payload = []byte(data.Error())
 				}
+			case string:
+				payload = []byte(data)
+			}
+			if len(payload) > 0 {
+				if existing, exists := c.Get("API_RESPONSE"); exists {
+					if existingBytes, ok := existing.([]byte); ok && len(existingBytes) > 0 {
+						trimmedPayload := bytes.TrimSpace(payload)
+						if len(trimmedPayload) > 0 && bytes.Contains(existingBytes, trimmedPayload) {
+							cancel()
+							return
+						}
+					}
+				}
+				appendAPIResponse(c, payload)
 			}
 		}
 

sdk/auth/iflow.go

@@ -107,7 +107,7 @@ func (a *IFlowAuthenticator) Login(ctx context.Context, cfg *config.Config, opts
 		return nil, fmt.Errorf("iflow authentication failed: missing account identifier")
 	}
 
-	fileName := fmt.Sprintf("iflow-%s.json", email)
+	fileName := fmt.Sprintf("iflow-%s-%d.json", email, time.Now().Unix())
 	metadata := map[string]any{
 		"email":         email,
 		"api_key":       tokenStorage.APIKey,

sdk/cliproxy/auth/manager.go

@@ -375,10 +375,19 @@ func (m *Manager) executeWithProvider(ctx context.Context, provider string, req
 		}
 
 		accountType, accountInfo := auth.AccountInfo()
+		proxyInfo := auth.ProxyInfo()
 		if accountType == "api_key" {
-			log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
+			if proxyInfo != "" {
+				log.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
+			} else {
+				log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
+			}
 		} else if accountType == "oauth" {
-			log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
+			if proxyInfo != "" {
+				log.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
+			} else {
+				log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
+			}
 		}
 
 		tried[auth.ID] = struct{}{}
@@ -423,10 +432,19 @@ func (m *Manager) executeCountWithProvider(ctx context.Context, provider string,
 		}
 
 		accountType, accountInfo := auth.AccountInfo()
+		proxyInfo := auth.ProxyInfo()
 		if accountType == "api_key" {
-			log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
+			if proxyInfo != "" {
+				log.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
+			} else {
+				log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
+			}
 		} else if accountType == "oauth" {
-			log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
+			if proxyInfo != "" {
+				log.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
+			} else {
+				log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
+			}
 		}
 
 		tried[auth.ID] = struct{}{}
@@ -471,10 +489,19 @@ func (m *Manager) executeStreamWithProvider(ctx context.Context, provider string
 		}
 
 		accountType, accountInfo := auth.AccountInfo()
+		proxyInfo := auth.ProxyInfo()
 		if accountType == "api_key" {
-			log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
+			if proxyInfo != "" {
+				log.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
+			} else {
+				log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
+			}
 		} else if accountType == "oauth" {
-			log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
+			if proxyInfo != "" {
+				log.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
+			} else {
+				log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
+			}
 		}
 
 		tried[auth.ID] = struct{}{}

sdk/cliproxy/auth/types.go

@@ -157,6 +157,20 @@ func (m *ModelState) Clone() *ModelState {
 	return &copyState
 }
 
+func (a *Auth) ProxyInfo() string {
+	if a == nil {
+		return ""
+	}
+	proxyStr := strings.TrimSpace(a.ProxyURL)
+	if proxyStr == "" {
+		return ""
+	}
+	if idx := strings.Index(proxyStr, "://"); idx > 0 {
+		return "via " + proxyStr[:idx] + " proxy"
+	}
+	return "via proxy"
+}
+
 func (a *Auth) AccountInfo() (string, string) {
 	if a == nil {
 		return "", ""

test/thinking_conversion_test.go

@@ -0,0 +1,760 @@
+package test
+
+import (
+	"fmt"
+	"strings"
+	"testing"
+	"time"
+
+	_ "github.com/router-for-me/CLIProxyAPI/v6/internal/translator"
+
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/runtime/executor"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
+	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+// isOpenAICompatModel returns true if the model is configured as an OpenAI-compatible
+// model that should have reasoning effort passed through even if not in registry.
+// This simulates the allowCompat behavior from OpenAICompatExecutor.
+func isOpenAICompatModel(model string) bool {
+	return model == "openai-compat"
+}
+
+// registerCoreModels loads representative models across providers into the registry
+// so NormalizeThinkingBudget and level validation use real ranges.
+func registerCoreModels(t *testing.T) func() {
+	t.Helper()
+	reg := registry.GetGlobalRegistry()
+	uid := fmt.Sprintf("thinking-core-%d", time.Now().UnixNano())
+	reg.RegisterClient(uid+"-gemini", "gemini", registry.GetGeminiModels())
+	reg.RegisterClient(uid+"-claude", "claude", registry.GetClaudeModels())
+	reg.RegisterClient(uid+"-openai", "codex", registry.GetOpenAIModels())
+	reg.RegisterClient(uid+"-qwen", "qwen", registry.GetQwenModels())
+	// Custom openai-compatible model with forced thinking suffix passthrough.
+	// No Thinking field - simulates an external model added via openai-compat
+	// where the registry has no knowledge of its thinking capabilities.
+	// The allowCompat flag should preserve reasoning effort for such models.
+	customOpenAIModels := []*registry.ModelInfo{
+		{
+			ID:          "openai-compat",
+			Object:      "model",
+			Created:     1700000000,
+			OwnedBy:     "custom-provider",
+			Type:        "openai",
+			DisplayName: "OpenAI Compatible Model",
+			Description: "OpenAI-compatible model with forced thinking suffix support",
+		},
+	}
+	reg.RegisterClient(uid+"-custom-openai", "codex", customOpenAIModels)
+	return func() {
+		reg.UnregisterClient(uid + "-gemini")
+		reg.UnregisterClient(uid + "-claude")
+		reg.UnregisterClient(uid + "-openai")
+		reg.UnregisterClient(uid + "-qwen")
+		reg.UnregisterClient(uid + "-custom-openai")
+	}
+}
+
+var (
+	thinkingTestModels = []string{
+		"gpt-5",           // level-based thinking model
+		"gemini-2.5-pro",  // numeric-budget thinking model
+		"qwen3-code-plus", // no thinking support
+		"openai-compat",   // allowCompat=true (OpenAI-compatible channel)
+	}
+	thinkingTestFromProtocols = []string{"openai", "claude", "gemini", "openai-response"}
+	thinkingTestToProtocols   = []string{"gemini", "claude", "openai", "codex"}
+
+	// Numeric budgets and their level equivalents:
+	// -1 -> auto
+	// 0 -> none
+	// 1..1024 -> low
+	// 1025..8192 -> medium
+	// 8193..24576 -> high
+	// >24576 -> model highest level (right-most in Levels)
+	thinkingNumericSamples = []int{-1, 0, 1023, 1025, 8193, 64000}
+
+	// Levels and their numeric equivalents:
+	// auto -> -1
+	// none -> 0
+	// minimal -> 512
+	// low -> 1024
+	// medium -> 8192
+	// high -> 24576
+	// xhigh -> 32768
+	// invalid -> invalid (no mapping)
+	thinkingLevelSamples = []string{"auto", "none", "minimal", "low", "medium", "high", "xhigh", "invalid"}
+)
+
+func buildRawPayload(fromProtocol, modelWithSuffix string) []byte {
+	switch fromProtocol {
+	case "gemini":
+		return []byte(fmt.Sprintf(`{"model":"%s","contents":[{"role":"user","parts":[{"text":"hi"}]}]}`, modelWithSuffix))
+	case "openai-response":
+		return []byte(fmt.Sprintf(`{"model":"%s","input":[{"role":"user","content":[{"type":"text","text":"hi"}]}]}`, modelWithSuffix))
+	default: // openai / claude and other chat-style payloads
+		return []byte(fmt.Sprintf(`{"model":"%s","messages":[{"role":"user","content":"hi"}]}`, modelWithSuffix))
+	}
+}
+
+// normalizeCodexPayload mirrors codex_executor's reasoning + streaming tweaks.
+func normalizeCodexPayload(body []byte, upstreamModel string, allowCompat bool) ([]byte, error) {
+	body = executor.NormalizeThinkingConfig(body, upstreamModel, allowCompat)
+	if err := executor.ValidateThinkingConfig(body, upstreamModel); err != nil {
+		return body, err
+	}
+	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body, _ = sjson.SetBytes(body, "stream", true)
+	body, _ = sjson.DeleteBytes(body, "previous_response_id")
+	return body, nil
+}
+
+// buildBodyForProtocol runs a minimal request through the same translation and
+// thinking pipeline used in executors for the given target protocol.
+func buildBodyForProtocol(t *testing.T, fromProtocol, toProtocol, modelWithSuffix string) ([]byte, error) {
+	t.Helper()
+	normalizedModel, metadata := util.NormalizeThinkingModel(modelWithSuffix)
+	upstreamModel := util.ResolveOriginalModel(normalizedModel, metadata)
+	raw := buildRawPayload(fromProtocol, modelWithSuffix)
+	stream := fromProtocol != toProtocol
+
+	body := sdktranslator.TranslateRequest(
+		sdktranslator.FromString(fromProtocol),
+		sdktranslator.FromString(toProtocol),
+		normalizedModel,
+		raw,
+		stream,
+	)
+
+	var err error
+	allowCompat := isOpenAICompatModel(normalizedModel)
+	switch toProtocol {
+	case "gemini":
+		body = executor.ApplyThinkingMetadata(body, metadata, normalizedModel)
+		body = util.ApplyDefaultThinkingIfNeeded(normalizedModel, body)
+		body = util.NormalizeGeminiThinkingBudget(normalizedModel, body)
+		body = util.StripThinkingConfigIfUnsupported(normalizedModel, body)
+	case "claude":
+		if budget, ok := util.ResolveClaudeThinkingConfig(normalizedModel, metadata); ok {
+			body = util.ApplyClaudeThinkingConfig(body, budget)
+		}
+	case "openai":
+		body = executor.ApplyReasoningEffortMetadata(body, metadata, normalizedModel, "reasoning_effort", allowCompat)
+		body = executor.NormalizeThinkingConfig(body, upstreamModel, allowCompat)
+		err = executor.ValidateThinkingConfig(body, upstreamModel)
+	case "codex": // OpenAI responses / codex
+		// Codex does not support allowCompat; always use false.
+		body = executor.ApplyReasoningEffortMetadata(body, metadata, normalizedModel, "reasoning.effort", false)
+		// Mirror CodexExecutor final normalization and model override so tests log the final body.
+		body, err = normalizeCodexPayload(body, upstreamModel, false)
+	default:
+	}
+
+	// Mirror executor behavior: final payload uses the upstream (base) model name.
+	if upstreamModel != "" {
+		body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	}
+
+	// For tests we only keep model + thinking-related fields to avoid noise.
+	body = filterThinkingBody(toProtocol, body, upstreamModel, normalizedModel)
+	return body, err
+}
+
+// filterThinkingBody projects the translated payload down to only model and
+// thinking-related fields for the given target protocol.
+func filterThinkingBody(toProtocol string, body []byte, upstreamModel, normalizedModel string) []byte {
+	if len(body) == 0 {
+		return body
+	}
+	out := []byte(`{}`)
+
+	// Preserve model if present, otherwise fall back to upstream/normalized model.
+	if m := gjson.GetBytes(body, "model"); m.Exists() {
+		out, _ = sjson.SetBytes(out, "model", m.Value())
+	} else if upstreamModel != "" {
+		out, _ = sjson.SetBytes(out, "model", upstreamModel)
+	} else if normalizedModel != "" {
+		out, _ = sjson.SetBytes(out, "model", normalizedModel)
+	}
+
+	switch toProtocol {
+	case "gemini":
+		if tc := gjson.GetBytes(body, "generationConfig.thinkingConfig"); tc.Exists() {
+			out, _ = sjson.SetRawBytes(out, "generationConfig.thinkingConfig", []byte(tc.Raw))
+		}
+	case "claude":
+		if tcfg := gjson.GetBytes(body, "thinking"); tcfg.Exists() {
+			out, _ = sjson.SetRawBytes(out, "thinking", []byte(tcfg.Raw))
+		}
+	case "openai":
+		if re := gjson.GetBytes(body, "reasoning_effort"); re.Exists() {
+			out, _ = sjson.SetBytes(out, "reasoning_effort", re.Value())
+		}
+	case "codex":
+		if re := gjson.GetBytes(body, "reasoning.effort"); re.Exists() {
+			out, _ = sjson.SetBytes(out, "reasoning.effort", re.Value())
+		}
+	}
+	return out
+}
+
+func TestThinkingConversionsAcrossProtocolsAndModels(t *testing.T) {
+	cleanup := registerCoreModels(t)
+	defer cleanup()
+
+	type scenario struct {
+		name        string
+		modelSuffix string
+	}
+
+	numericName := func(budget int) string {
+		if budget < 0 {
+			return "numeric-neg1"
+		}
+		return fmt.Sprintf("numeric-%d", budget)
+	}
+
+	for _, model := range thinkingTestModels {
+		_ = registry.GetGlobalRegistry().GetModelInfo(model)
+
+		for _, from := range thinkingTestFromProtocols {
+			// Scenario selection follows protocol semantics:
+			// - OpenAI-style protocols (openai/openai-response) express thinking as levels.
+			// - Claude/Gemini-style protocols express thinking as numeric budgets.
+			cases := []scenario{
+				{name: "no-suffix", modelSuffix: model},
+			}
+			if from == "openai" || from == "openai-response" {
+				for _, lvl := range thinkingLevelSamples {
+					cases = append(cases, scenario{
+						name:        "level-" + lvl,
+						modelSuffix: fmt.Sprintf("%s(%s)", model, lvl),
+					})
+				}
+			} else { // claude or gemini
+				for _, budget := range thinkingNumericSamples {
+					budget := budget
+					cases = append(cases, scenario{
+						name:        numericName(budget),
+						modelSuffix: fmt.Sprintf("%s(%d)", model, budget),
+					})
+				}
+			}
+
+			for _, to := range thinkingTestToProtocols {
+				if from == to {
+					continue
+				}
+				t.Logf("─────────────────────────────────────────────────────────────────────────────────")
+				t.Logf("  %s -> %s | model: %s", from, to, model)
+				t.Logf("─────────────────────────────────────────────────────────────────────────────────")
+				for _, cs := range cases {
+					from := from
+					to := to
+					cs := cs
+					testName := fmt.Sprintf("%s->%s/%s/%s", from, to, model, cs.name)
+					t.Run(testName, func(t *testing.T) {
+						normalizedModel, metadata := util.NormalizeThinkingModel(cs.modelSuffix)
+						expectPresent, expectValue, expectErr := func() (bool, string, bool) {
+							switch to {
+							case "gemini":
+								budget, include, ok := util.ResolveThinkingConfigFromMetadata(normalizedModel, metadata)
+								if !ok || !util.ModelSupportsThinking(normalizedModel) {
+									return false, "", false
+								}
+								if include != nil && !*include {
+									return false, "", false
+								}
+								if budget == nil {
+									return false, "", false
+								}
+								norm := util.NormalizeThinkingBudget(normalizedModel, *budget)
+								return true, fmt.Sprintf("%d", norm), false
+							case "claude":
+								if !util.ModelSupportsThinking(normalizedModel) {
+									return false, "", false
+								}
+								budget, ok := util.ResolveClaudeThinkingConfig(normalizedModel, metadata)
+								if !ok || budget == nil {
+									return false, "", false
+								}
+								return true, fmt.Sprintf("%d", *budget), false
+							case "openai":
+								allowCompat := isOpenAICompatModel(normalizedModel)
+								if !util.ModelSupportsThinking(normalizedModel) && !allowCompat {
+									return false, "", false
+								}
+								// For allowCompat models, pass through effort directly without validation
+								if allowCompat {
+									effort, ok := util.ReasoningEffortFromMetadata(metadata)
+									if ok && strings.TrimSpace(effort) != "" {
+										return true, strings.ToLower(strings.TrimSpace(effort)), false
+									}
+									// Check numeric budget fallback for allowCompat
+									if budget, _, _, matched := util.ThinkingFromMetadata(metadata); matched && budget != nil {
+										if mapped, okMap := util.OpenAIThinkingBudgetToEffort(normalizedModel, *budget); okMap && mapped != "" {
+											return true, mapped, false
+										}
+									}
+									return false, "", false
+								}
+								if !util.ModelUsesThinkingLevels(normalizedModel) {
+									// Non-levels models don't support effort strings in openai
+									return false, "", false
+								}
+								effort, ok := util.ReasoningEffortFromMetadata(metadata)
+								if !ok || strings.TrimSpace(effort) == "" {
+									if budget, _, _, matched := util.ThinkingFromMetadata(metadata); matched && budget != nil {
+										if mapped, okMap := util.OpenAIThinkingBudgetToEffort(normalizedModel, *budget); okMap {
+											effort = mapped
+											ok = true
+										}
+									}
+								}
+								if !ok || strings.TrimSpace(effort) == "" {
+									return false, "", false
+								}
+								effort = strings.ToLower(strings.TrimSpace(effort))
+								if normalized, okLevel := util.NormalizeReasoningEffortLevel(normalizedModel, effort); okLevel {
+									return true, normalized, false
+								}
+								return false, "", true // validation would fail
+							case "codex":
+								// Codex does not support allowCompat; require thinking-capable level models.
+								if !util.ModelSupportsThinking(normalizedModel) || !util.ModelUsesThinkingLevels(normalizedModel) {
+									return false, "", false
+								}
+								effort, ok := util.ReasoningEffortFromMetadata(metadata)
+								if ok && strings.TrimSpace(effort) != "" {
+									effort = strings.ToLower(strings.TrimSpace(effort))
+									if normalized, okLevel := util.NormalizeReasoningEffortLevel(normalizedModel, effort); okLevel {
+										return true, normalized, false
+									}
+									return false, "", true
+								}
+								if budget, _, _, matched := util.ThinkingFromMetadata(metadata); matched && budget != nil {
+									if mapped, okMap := util.OpenAIThinkingBudgetToEffort(normalizedModel, *budget); okMap && mapped != "" {
+										mapped = strings.ToLower(strings.TrimSpace(mapped))
+										if normalized, okLevel := util.NormalizeReasoningEffortLevel(normalizedModel, mapped); okLevel {
+											return true, normalized, false
+										}
+										return false, "", true
+									}
+								}
+								if from != "openai-response" {
+									// Codex translators default reasoning.effort to "medium" when
+									// no explicit thinking suffix/metadata is provided.
+									return true, "medium", false
+								}
+								return false, "", false
+							default:
+								return false, "", false
+							}
+						}()
+
+						body, err := buildBodyForProtocol(t, from, to, cs.modelSuffix)
+						actualPresent, actualValue := func() (bool, string) {
+							path := ""
+							switch to {
+							case "gemini":
+								path = "generationConfig.thinkingConfig.thinkingBudget"
+							case "claude":
+								path = "thinking.budget_tokens"
+							case "openai":
+								path = "reasoning_effort"
+							case "codex":
+								path = "reasoning.effort"
+							}
+							if path == "" {
+								return false, ""
+							}
+							val := gjson.GetBytes(body, path)
+							if to == "codex" && !val.Exists() {
+								reasoning := gjson.GetBytes(body, "reasoning")
+								if reasoning.Exists() {
+									val = reasoning.Get("effort")
+								}
+							}
+							if !val.Exists() {
+								return false, ""
+							}
+							if val.Type == gjson.Number {
+								return true, fmt.Sprintf("%d", val.Int())
+							}
+							return true, val.String()
+						}()
+
+						t.Logf("from=%s to=%s model=%s suffix=%s present(expect=%v got=%v) value(expect=%s got=%s) err(expect=%v got=%v) body=%s",
+							from, to, model, cs.modelSuffix, expectPresent, actualPresent, expectValue, actualValue, expectErr, err != nil, string(body))
+
+						if expectErr {
+							if err == nil {
+								t.Fatalf("expected validation error but got none, body=%s", string(body))
+							}
+							return
+						}
+						if err != nil {
+							t.Fatalf("unexpected error: %v body=%s", err, string(body))
+						}
+
+						if expectPresent != actualPresent {
+							t.Fatalf("presence mismatch: expect %v got %v body=%s", expectPresent, actualPresent, string(body))
+						}
+						if expectPresent && expectValue != actualValue {
+							t.Fatalf("value mismatch: expect %s got %s body=%s", expectValue, actualValue, string(body))
+						}
+					})
+				}
+			}
+		}
+	}
+}
+
+// buildRawPayloadWithThinking creates a payload with thinking parameters already in the body.
+// This tests the path where thinking comes from the raw payload, not model suffix.
+func buildRawPayloadWithThinking(fromProtocol, model string, thinkingParam any) []byte {
+	switch fromProtocol {
+	case "gemini":
+		base := fmt.Sprintf(`{"model":"%s","contents":[{"role":"user","parts":[{"text":"hi"}]}]}`, model)
+		if budget, ok := thinkingParam.(int); ok {
+			base, _ = sjson.Set(base, "generationConfig.thinkingConfig.thinkingBudget", budget)
+		}
+		return []byte(base)
+	case "openai-response":
+		base := fmt.Sprintf(`{"model":"%s","input":[{"role":"user","content":[{"type":"text","text":"hi"}]}]}`, model)
+		if effort, ok := thinkingParam.(string); ok && effort != "" {
+			base, _ = sjson.Set(base, "reasoning.effort", effort)
+		}
+		return []byte(base)
+	case "openai":
+		base := fmt.Sprintf(`{"model":"%s","messages":[{"role":"user","content":"hi"}]}`, model)
+		if effort, ok := thinkingParam.(string); ok && effort != "" {
+			base, _ = sjson.Set(base, "reasoning_effort", effort)
+		}
+		return []byte(base)
+	case "claude":
+		base := fmt.Sprintf(`{"model":"%s","messages":[{"role":"user","content":"hi"}]}`, model)
+		if budget, ok := thinkingParam.(int); ok {
+			base, _ = sjson.Set(base, "thinking.type", "enabled")
+			base, _ = sjson.Set(base, "thinking.budget_tokens", budget)
+		}
+		return []byte(base)
+	default:
+		return []byte(fmt.Sprintf(`{"model":"%s","messages":[{"role":"user","content":"hi"}]}`, model))
+	}
+}
+
+// buildBodyForProtocolWithRawThinking translates payload with raw thinking params.
+func buildBodyForProtocolWithRawThinking(t *testing.T, fromProtocol, toProtocol, model string, thinkingParam any) ([]byte, error) {
+	t.Helper()
+	raw := buildRawPayloadWithThinking(fromProtocol, model, thinkingParam)
+	stream := fromProtocol != toProtocol
+
+	body := sdktranslator.TranslateRequest(
+		sdktranslator.FromString(fromProtocol),
+		sdktranslator.FromString(toProtocol),
+		model,
+		raw,
+		stream,
+	)
+
+	var err error
+	allowCompat := isOpenAICompatModel(model)
+	switch toProtocol {
+	case "gemini":
+		body = util.ApplyDefaultThinkingIfNeeded(model, body)
+		body = util.NormalizeGeminiThinkingBudget(model, body)
+		body = util.StripThinkingConfigIfUnsupported(model, body)
+	case "claude":
+		// For raw payload, Claude thinking is passed through by translator
+		// No additional processing needed as thinking is already in body
+	case "openai":
+		body = executor.NormalizeThinkingConfig(body, model, allowCompat)
+		err = executor.ValidateThinkingConfig(body, model)
+	case "codex":
+		// Codex does not support allowCompat; always use false.
+		body, err = normalizeCodexPayload(body, model, false)
+	}
+
+	body, _ = sjson.SetBytes(body, "model", model)
+	body = filterThinkingBody(toProtocol, body, model, model)
+	return body, err
+}
+
+func TestRawPayloadThinkingConversions(t *testing.T) {
+	cleanup := registerCoreModels(t)
+	defer cleanup()
+
+	type scenario struct {
+		name          string
+		thinkingParam any // int for budget, string for effort level
+	}
+
+	numericName := func(budget int) string {
+		if budget < 0 {
+			return "budget-neg1"
+		}
+		return fmt.Sprintf("budget-%d", budget)
+	}
+
+	for _, model := range thinkingTestModels {
+		supportsThinking := util.ModelSupportsThinking(model)
+		usesLevels := util.ModelUsesThinkingLevels(model)
+		allowCompat := isOpenAICompatModel(model)
+
+		for _, from := range thinkingTestFromProtocols {
+			var cases []scenario
+			switch from {
+			case "openai", "openai-response":
+				cases = []scenario{
+					{name: "no-thinking", thinkingParam: nil},
+				}
+				for _, lvl := range thinkingLevelSamples {
+					cases = append(cases, scenario{
+						name:          "effort-" + lvl,
+						thinkingParam: lvl,
+					})
+				}
+			case "gemini", "claude":
+				cases = []scenario{
+					{name: "no-thinking", thinkingParam: nil},
+				}
+				for _, budget := range thinkingNumericSamples {
+					budget := budget
+					cases = append(cases, scenario{
+						name:          numericName(budget),
+						thinkingParam: budget,
+					})
+				}
+			}
+
+			for _, to := range thinkingTestToProtocols {
+				if from == to {
+					continue
+				}
+				t.Logf("═══════════════════════════════════════════════════════════════════════════════")
+				t.Logf("  RAW PAYLOAD: %s -> %s | model: %s", from, to, model)
+				t.Logf("═══════════════════════════════════════════════════════════════════════════════")
+
+				for _, cs := range cases {
+					from := from
+					to := to
+					cs := cs
+					testName := fmt.Sprintf("raw/%s->%s/%s/%s", from, to, model, cs.name)
+					t.Run(testName, func(t *testing.T) {
+						expectPresent, expectValue, expectErr := func() (bool, string, bool) {
+							if cs.thinkingParam == nil {
+								if to == "codex" && from != "openai-response" && supportsThinking && usesLevels {
+									// Codex translators default reasoning.effort to "medium" for thinking-capable level models
+									return true, "medium", false
+								}
+								return false, "", false
+							}
+
+							switch to {
+							case "gemini":
+								if !supportsThinking || usesLevels {
+									return false, "", false
+								}
+								// Gemini expects numeric budget (only for non-level models)
+								if budget, ok := cs.thinkingParam.(int); ok {
+									norm := util.NormalizeThinkingBudget(model, budget)
+									return true, fmt.Sprintf("%d", norm), false
+								}
+								// Convert effort level to budget for non-level models only
+								if effort, ok := cs.thinkingParam.(string); ok && effort != "" {
+									// "none" disables thinking - no thinkingBudget in output
+									if strings.ToLower(effort) == "none" {
+										return false, "", false
+									}
+									if budget, okB := util.ThinkingEffortToBudget(model, effort); okB {
+										// ThinkingEffortToBudget already returns normalized budget
+										return true, fmt.Sprintf("%d", budget), false
+									}
+									// Invalid effort does not map to a budget
+									return false, "", false
+								}
+								return false, "", false
+							case "claude":
+								if !supportsThinking || usesLevels {
+									return false, "", false
+								}
+								// Claude expects numeric budget (only for non-level models)
+								if budget, ok := cs.thinkingParam.(int); ok && budget > 0 {
+									norm := util.NormalizeThinkingBudget(model, budget)
+									return true, fmt.Sprintf("%d", norm), false
+								}
+								// Convert effort level to budget for non-level models only
+								if effort, ok := cs.thinkingParam.(string); ok && effort != "" {
+									// "none" and "auto" don't produce budget_tokens
+									lower := strings.ToLower(effort)
+									if lower == "none" || lower == "auto" {
+										return false, "", false
+									}
+									if budget, okB := util.ThinkingEffortToBudget(model, effort); okB {
+										// ThinkingEffortToBudget already returns normalized budget
+										return true, fmt.Sprintf("%d", budget), false
+									}
+									// Invalid effort - claude sets thinking.type:enabled but no budget_tokens
+									return false, "", false
+								}
+								return false, "", false
+							case "openai":
+								if allowCompat {
+									if effort, ok := cs.thinkingParam.(string); ok && strings.TrimSpace(effort) != "" {
+										normalized := strings.ToLower(strings.TrimSpace(effort))
+										return true, normalized, false
+									}
+									if budget, ok := cs.thinkingParam.(int); ok {
+										if mapped, okM := util.OpenAIThinkingBudgetToEffort(model, budget); okM && mapped != "" {
+											return true, mapped, false
+										}
+									}
+									return false, "", false
+								}
+								if !supportsThinking || !usesLevels {
+									return false, "", false
+								}
+								if effort, ok := cs.thinkingParam.(string); ok && effort != "" {
+									if normalized, okN := util.NormalizeReasoningEffortLevel(model, effort); okN {
+										return true, normalized, false
+									}
+									return false, "", true // invalid level
+								}
+								if budget, ok := cs.thinkingParam.(int); ok {
+									if mapped, okM := util.OpenAIThinkingBudgetToEffort(model, budget); okM && mapped != "" {
+										// Check if the mapped effort is valid for this model
+										if _, validLevel := util.NormalizeReasoningEffortLevel(model, mapped); !validLevel {
+											return true, mapped, true // expect validation error
+										}
+										return true, mapped, false
+									}
+								}
+								return false, "", false
+							case "codex":
+								// Codex does not support allowCompat; require thinking-capable level models.
+								if !supportsThinking || !usesLevels {
+									return false, "", false
+								}
+								if effort, ok := cs.thinkingParam.(string); ok && effort != "" {
+									if normalized, okN := util.NormalizeReasoningEffortLevel(model, effort); okN {
+										return true, normalized, false
+									}
+									return false, "", true
+								}
+								if budget, ok := cs.thinkingParam.(int); ok {
+									if mapped, okM := util.OpenAIThinkingBudgetToEffort(model, budget); okM && mapped != "" {
+										// Check if the mapped effort is valid for this model
+										if _, validLevel := util.NormalizeReasoningEffortLevel(model, mapped); !validLevel {
+											return true, mapped, true // expect validation error
+										}
+										return true, mapped, false
+									}
+								}
+								if from != "openai-response" {
+									// Codex translators default reasoning.effort to "medium" for thinking-capable models
+									return true, "medium", false
+								}
+								return false, "", false
+							}
+							return false, "", false
+						}()
+
+						body, err := buildBodyForProtocolWithRawThinking(t, from, to, model, cs.thinkingParam)
+						actualPresent, actualValue := func() (bool, string) {
+							path := ""
+							switch to {
+							case "gemini":
+								path = "generationConfig.thinkingConfig.thinkingBudget"
+							case "claude":
+								path = "thinking.budget_tokens"
+							case "openai":
+								path = "reasoning_effort"
+							case "codex":
+								path = "reasoning.effort"
+							}
+							if path == "" {
+								return false, ""
+							}
+							val := gjson.GetBytes(body, path)
+							if to == "codex" && !val.Exists() {
+								reasoning := gjson.GetBytes(body, "reasoning")
+								if reasoning.Exists() {
+									val = reasoning.Get("effort")
+								}
+							}
+							if !val.Exists() {
+								return false, ""
+							}
+							if val.Type == gjson.Number {
+								return true, fmt.Sprintf("%d", val.Int())
+							}
+							return true, val.String()
+						}()
+
+						t.Logf("from=%s to=%s model=%s param=%v present(expect=%v got=%v) value(expect=%s got=%s) err(expect=%v got=%v) body=%s",
+							from, to, model, cs.thinkingParam, expectPresent, actualPresent, expectValue, actualValue, expectErr, err != nil, string(body))
+
+						if expectErr {
+							if err == nil {
+								t.Fatalf("expected validation error but got none, body=%s", string(body))
+							}
+							return
+						}
+						if err != nil {
+							t.Fatalf("unexpected error: %v body=%s", err, string(body))
+						}
+
+						if expectPresent != actualPresent {
+							t.Fatalf("presence mismatch: expect %v got %v body=%s", expectPresent, actualPresent, string(body))
+						}
+						if expectPresent && expectValue != actualValue {
+							t.Fatalf("value mismatch: expect %s got %s body=%s", expectValue, actualValue, string(body))
+						}
+					})
+				}
+			}
+		}
+	}
+}
+
+func TestOpenAIThinkingBudgetToEffortRanges(t *testing.T) {
+	cleanup := registerCoreModels(t)
+	defer cleanup()
+
+	cases := []struct {
+		name   string
+		model  string
+		budget int
+		want   string
+		ok     bool
+	}{
+		{name: "dynamic-auto", model: "gpt-5", budget: -1, want: "auto", ok: true},
+		{name: "zero-none", model: "gpt-5", budget: 0, want: "none", ok: true},
+		{name: "low-min", model: "gpt-5", budget: 1, want: "low", ok: true},
+		{name: "low-max", model: "gpt-5", budget: 1024, want: "low", ok: true},
+		{name: "medium-min", model: "gpt-5", budget: 1025, want: "medium", ok: true},
+		{name: "medium-max", model: "gpt-5", budget: 8192, want: "medium", ok: true},
+		{name: "high-min", model: "gpt-5", budget: 8193, want: "high", ok: true},
+		{name: "high-max", model: "gpt-5", budget: 24576, want: "high", ok: true},
+		{name: "over-max-clamps-to-highest", model: "gpt-5", budget: 64000, want: "high", ok: true},
+		{name: "over-max-xhigh-model", model: "gpt-5.2", budget: 50000, want: "xhigh", ok: true},
+		{name: "negative-unsupported", model: "gpt-5", budget: -5, want: "", ok: false},
+	}
+
+	for _, cs := range cases {
+		cs := cs
+		t.Run(cs.name, func(t *testing.T) {
+			got, ok := util.OpenAIThinkingBudgetToEffort(cs.model, cs.budget)
+			if ok != cs.ok {
+				t.Fatalf("ok mismatch for model=%s budget=%d: expect %v got %v", cs.model, cs.budget, cs.ok, ok)
+			}
+			if got != cs.want {
+				t.Fatalf("value mismatch for model=%s budget=%d: expect %q got %q", cs.model, cs.budget, cs.want, got)
+			}
+		})
+	}
+}