Merge branch 'dev' into watcher

internal/api/modules/amp/amp_test.go

@@ -146,6 +146,9 @@ func TestAmpModule_OnConfigUpdated_CacheInvalidation(t *testing.T) {
 	m := &AmpModule{enabled: true}
 	ms := NewMultiSourceSecretWithPath("", p, time.Minute)
 	m.secretSource = ms
+	m.lastConfig = &config.AmpCode{
+		UpstreamAPIKey: "old-key",
+	}
 
 	// Warm the cache
 	if _, err := ms.Get(context.Background()); err != nil {
@@ -157,7 +160,7 @@ func TestAmpModule_OnConfigUpdated_CacheInvalidation(t *testing.T) {
 	}
 
 	// Update config - should invalidate cache
-	if err := m.OnConfigUpdated(&config.Config{AmpCode: config.AmpCode{UpstreamURL: "http://x"}}); err != nil {
+	if err := m.OnConfigUpdated(&config.Config{AmpCode: config.AmpCode{UpstreamURL: "http://x", UpstreamAPIKey: "new-key"}}); err != nil {
 		t.Fatal(err)
 	}
 

internal/api/modules/amp/routes.go

@@ -267,7 +267,7 @@ func (m *AmpModule) registerProviderAliases(engine *gin.Engine, baseHandler *han
 	v1betaAmp := provider.Group("/v1beta")
 	{
 		v1betaAmp.GET("/models", geminiHandlers.GeminiModels)
-		v1betaAmp.POST("/models/:action", fallbackHandler.WrapHandler(geminiHandlers.GeminiHandler))
-		v1betaAmp.GET("/models/:action", geminiHandlers.GeminiGetHandler)
+		v1betaAmp.POST("/models/*action", fallbackHandler.WrapHandler(geminiHandlers.GeminiHandler))
+		v1betaAmp.GET("/models/*action", geminiHandlers.GeminiGetHandler)
 	}
 }

internal/api/modules/amp/routes_test.go

@@ -32,7 +32,9 @@ func TestRegisterManagementRoutes(t *testing.T) {
 	m.setProxy(proxy)
 
 	base := &handlers.BaseAPIHandler{}
-	m.registerManagementRoutes(r, base)
+	m.registerManagementRoutes(r, base, nil)
+	srv := httptest.NewServer(r)
+	defer srv.Close()
 
 	managementPaths := []struct {
 		path   string
@@ -63,11 +65,17 @@ func TestRegisterManagementRoutes(t *testing.T) {
 	for _, path := range managementPaths {
 		t.Run(path.path, func(t *testing.T) {
 			proxyCalled = false
-			req := httptest.NewRequest(path.method, path.path, nil)
-			w := httptest.NewRecorder()
-			r.ServeHTTP(w, req)
+			req, err := http.NewRequest(path.method, srv.URL+path.path, nil)
+			if err != nil {
+				t.Fatalf("failed to build request: %v", err)
+			}
+			resp, err := http.DefaultClient.Do(req)
+			if err != nil {
+				t.Fatalf("request failed: %v", err)
+			}
+			defer resp.Body.Close()
 
-			if w.Code == http.StatusNotFound {
+			if resp.StatusCode == http.StatusNotFound {
 				t.Fatalf("route %s not registered", path.path)
 			}
 			if !proxyCalled {

internal/api/server.go

@@ -230,13 +230,9 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
 	envManagementSecret := envAdminPasswordSet && envAdminPassword != ""
 
 	// Create server instance
-	providerNames := make([]string, 0, len(cfg.OpenAICompatibility))
-	for _, p := range cfg.OpenAICompatibility {
-		providerNames = append(providerNames, p.Name)
-	}
 	s := &Server{
 		engine:              engine,
-		handlers:            handlers.NewBaseAPIHandlers(&cfg.SDKConfig, authManager, providerNames),
+		handlers:            handlers.NewBaseAPIHandlers(&cfg.SDKConfig, authManager),
 		cfg:                 cfg,
 		accessManager:       accessManager,
 		requestLogger:       requestLogger,
@@ -334,8 +330,8 @@ func (s *Server) setupRoutes() {
 	v1beta.Use(AuthMiddleware(s.accessManager))
 	{
 		v1beta.GET("/models", geminiHandlers.GeminiModels)
-		v1beta.POST("/models/:action", geminiHandlers.GeminiHandler)
-		v1beta.GET("/models/:action", geminiHandlers.GeminiGetHandler)
+		v1beta.POST("/models/*action", geminiHandlers.GeminiHandler)
+		v1beta.GET("/models/*action", geminiHandlers.GeminiGetHandler)
 	}
 
 	// Root endpoint
@@ -919,12 +915,6 @@ func (s *Server) UpdateClients(cfg *config.Config) {
 	// Save YAML snapshot for next comparison
 	s.oldConfigYaml, _ = yaml.Marshal(cfg)
 
-	providerNames := make([]string, 0, len(cfg.OpenAICompatibility))
-	for _, p := range cfg.OpenAICompatibility {
-		providerNames = append(providerNames, p.Name)
-	}
-	s.handlers.OpenAICompatProviders = providerNames
-
 	s.handlers.UpdateClients(&cfg.SDKConfig)
 
 	if !cfg.RemoteManagement.DisableControlPanel {

internal/config/config.go

@@ -187,6 +187,9 @@ type ClaudeKey struct {
 	// APIKey is the authentication key for accessing Claude API services.
 	APIKey string `yaml:"api-key" json:"api-key"`
 
+	// Prefix optionally namespaces models for this credential (e.g., "teamA/claude-sonnet-4").
+	Prefix string `yaml:"prefix,omitempty" json:"prefix,omitempty"`
+
 	// BaseURL is the base URL for the Claude API endpoint.
 	// If empty, the default Claude API URL will be used.
 	BaseURL string `yaml:"base-url" json:"base-url"`
@@ -219,6 +222,9 @@ type CodexKey struct {
 	// APIKey is the authentication key for accessing Codex API services.
 	APIKey string `yaml:"api-key" json:"api-key"`
 
+	// Prefix optionally namespaces models for this credential (e.g., "teamA/gpt-5-codex").
+	Prefix string `yaml:"prefix,omitempty" json:"prefix,omitempty"`
+
 	// BaseURL is the base URL for the Codex API endpoint.
 	// If empty, the default Codex API URL will be used.
 	BaseURL string `yaml:"base-url" json:"base-url"`
@@ -239,6 +245,9 @@ type GeminiKey struct {
 	// APIKey is the authentication key for accessing Gemini API services.
 	APIKey string `yaml:"api-key" json:"api-key"`
 
+	// Prefix optionally namespaces models for this credential (e.g., "teamA/gemini-3-pro-preview").
+	Prefix string `yaml:"prefix,omitempty" json:"prefix,omitempty"`
+
 	// BaseURL optionally overrides the Gemini API endpoint.
 	BaseURL string `yaml:"base-url,omitempty" json:"base-url,omitempty"`
 
@@ -258,6 +267,9 @@ type OpenAICompatibility struct {
 	// Name is the identifier for this OpenAI compatibility configuration.
 	Name string `yaml:"name" json:"name"`
 
+	// Prefix optionally namespaces model aliases for this provider (e.g., "teamA/kimi-k2").
+	Prefix string `yaml:"prefix,omitempty" json:"prefix,omitempty"`
+
 	// BaseURL is the base URL for the external OpenAI-compatible API endpoint.
 	BaseURL string `yaml:"base-url" json:"base-url"`
 
@@ -422,6 +434,7 @@ func (cfg *Config) SanitizeOpenAICompatibility() {
 	for i := range cfg.OpenAICompatibility {
 		e := cfg.OpenAICompatibility[i]
 		e.Name = strings.TrimSpace(e.Name)
+		e.Prefix = normalizeModelPrefix(e.Prefix)
 		e.BaseURL = strings.TrimSpace(e.BaseURL)
 		e.Headers = NormalizeHeaders(e.Headers)
 		if e.BaseURL == "" {
@@ -442,6 +455,7 @@ func (cfg *Config) SanitizeCodexKeys() {
 	out := make([]CodexKey, 0, len(cfg.CodexKey))
 	for i := range cfg.CodexKey {
 		e := cfg.CodexKey[i]
+		e.Prefix = normalizeModelPrefix(e.Prefix)
 		e.BaseURL = strings.TrimSpace(e.BaseURL)
 		e.Headers = NormalizeHeaders(e.Headers)
 		e.ExcludedModels = NormalizeExcludedModels(e.ExcludedModels)
@@ -460,6 +474,7 @@ func (cfg *Config) SanitizeClaudeKeys() {
 	}
 	for i := range cfg.ClaudeKey {
 		entry := &cfg.ClaudeKey[i]
+		entry.Prefix = normalizeModelPrefix(entry.Prefix)
 		entry.Headers = NormalizeHeaders(entry.Headers)
 		entry.ExcludedModels = NormalizeExcludedModels(entry.ExcludedModels)
 	}
@@ -479,6 +494,7 @@ func (cfg *Config) SanitizeGeminiKeys() {
 		if entry.APIKey == "" {
 			continue
 		}
+		entry.Prefix = normalizeModelPrefix(entry.Prefix)
 		entry.BaseURL = strings.TrimSpace(entry.BaseURL)
 		entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
 		entry.Headers = NormalizeHeaders(entry.Headers)
@@ -492,6 +508,18 @@ func (cfg *Config) SanitizeGeminiKeys() {
 	cfg.GeminiKey = out
 }
 
+func normalizeModelPrefix(prefix string) string {
+	trimmed := strings.TrimSpace(prefix)
+	trimmed = strings.Trim(trimmed, "/")
+	if trimmed == "" {
+		return ""
+	}
+	if strings.Contains(trimmed, "/") {
+		return ""
+	}
+	return trimmed
+}
+
 func syncInlineAccessProvider(cfg *Config) {
 	if cfg == nil {
 		return

internal/config/vertex_compat.go

@@ -13,6 +13,9 @@ type VertexCompatKey struct {
 	// Maps to the x-goog-api-key header.
 	APIKey string `yaml:"api-key" json:"api-key"`
 
+	// Prefix optionally namespaces model aliases for this credential (e.g., "teamA/vertex-pro").
+	Prefix string `yaml:"prefix,omitempty" json:"prefix,omitempty"`
+
 	// BaseURL is the base URL for the Vertex-compatible API endpoint.
 	// The executor will append "/v1/publishers/google/models/{model}:action" to this.
 	// Example: "https://zenmux.ai/api" becomes "https://zenmux.ai/api/v1/publishers/google/models/..."
@@ -53,6 +56,7 @@ func (cfg *Config) SanitizeVertexCompatKeys() {
 		if entry.APIKey == "" {
 			continue
 		}
+		entry.Prefix = normalizeModelPrefix(entry.Prefix)
 		entry.BaseURL = strings.TrimSpace(entry.BaseURL)
 		if entry.BaseURL == "" {
 			// BaseURL is required for Vertex API key entries

internal/registry/model_definitions.go

@@ -630,6 +630,13 @@ func GetQwenModels() []*ModelInfo {
 	}
 }
 
+// iFlowThinkingSupport is a shared ThinkingSupport configuration for iFlow models
+// that support thinking mode via chat_template_kwargs.enable_thinking (boolean toggle).
+// Uses level-based configuration so standard normalization flows apply before conversion.
+var iFlowThinkingSupport = &ThinkingSupport{
+	Levels: []string{"none", "auto", "minimal", "low", "medium", "high", "xhigh"},
+}
+
 // GetIFlowModels returns supported models for iFlow OAuth accounts.
 func GetIFlowModels() []*ModelInfo {
 	entries := []struct {
@@ -645,9 +652,9 @@ func GetIFlowModels() []*ModelInfo {
 		{ID: "qwen3-vl-plus", DisplayName: "Qwen3-VL-Plus", Description: "Qwen3 multimodal vision-language", Created: 1758672000},
 		{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build", Created: 1757030400},
 		{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905", Created: 1757030400},
-		{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400},
+		{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400, Thinking: iFlowThinkingSupport},
 		{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: "kimi-k2-thinking", DisplayName: "Kimi-K2-Thinking", Description: "Moonshot Kimi K2 thinking model", Created: 1762387200},
 		{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},
@@ -655,10 +662,10 @@ func GetIFlowModels() []*ModelInfo {
 		{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"}}},
+		{ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600},
 		{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
 		{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
-		{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
+		{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000},
 	}
 	models := make([]*ModelInfo, 0, len(entries))
 	for _, entry := range entries {

internal/runtime/executor/iflow_executor.go

@@ -66,6 +66,7 @@ func (e *IFlowExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return resp, errValidate
 	}
+	body = applyIFlowThinkingConfig(body)
 	body = applyPayloadConfig(e.cfg, req.Model, body)
 
 	endpoint := strings.TrimSuffix(baseURL, "/") + iflowDefaultEndpoint
@@ -157,6 +158,7 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
 		return nil, errValidate
 	}
+	body = applyIFlowThinkingConfig(body)
 	// Ensure tools array exists to avoid provider quirks similar to Qwen's behaviour.
 	toolsResult := gjson.GetBytes(body, "tools")
 	if toolsResult.Exists() && toolsResult.IsArray() && len(toolsResult.Array()) == 0 {
@@ -442,3 +444,21 @@ func ensureToolsArray(body []byte) []byte {
 	}
 	return updated
 }
+
+// applyIFlowThinkingConfig converts normalized reasoning_effort to iFlow chat_template_kwargs.enable_thinking.
+// This should be called after NormalizeThinkingConfig has processed the payload.
+// iFlow only supports boolean enable_thinking, so any non-"none" effort enables thinking.
+func applyIFlowThinkingConfig(body []byte) []byte {
+	effort := gjson.GetBytes(body, "reasoning_effort")
+	if !effort.Exists() {
+		return body
+	}
+
+	val := strings.ToLower(strings.TrimSpace(effort.String()))
+	enableThinking := val != "none" && val != ""
+
+	body, _ = sjson.DeleteBytes(body, "reasoning_effort")
+	body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
+
+	return body
+}

internal/runtime/executor/payload_helpers.go

@@ -72,13 +72,7 @@ func ApplyReasoningEffortMetadata(payload []byte, metadata map[string]any, model
 	// 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 effort, ok := util.ThinkingBudgetToEffort(baseModel, *budget); ok && effort != "" {
 				if updated, err := sjson.SetBytes(payload, field, effort); err == nil {
 					return updated
 				}
@@ -273,7 +267,7 @@ func StripThinkingFields(payload []byte, effortOnly bool) []byte {
 		"reasoning.effort",
 	}
 	if !effortOnly {
-		fieldsToRemove = append([]string{"reasoning"}, fieldsToRemove...)
+		fieldsToRemove = append([]string{"reasoning", "thinking"}, fieldsToRemove...)
 	}
 	out := payload
 	for _, field := range fieldsToRemove {

internal/translator/codex/claude/codex_claude_request.go

@@ -219,15 +219,20 @@ func ConvertClaudeRequestToCodex(modelName string, inputRawJSON []byte, _ bool)
 	// 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" {
+		switch thinking.Get("type").String() {
+		case "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 != "" {
+					if effort, ok := util.ThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
 						reasoningEffort = effort
 					}
 				}
 			}
+		case "disabled":
+			if effort, ok := util.ThinkingBudgetToEffort(modelName, 0); ok && effort != "" {
+				reasoningEffort = effort
+			}
 		}
 	}
 	template, _ = sjson.Set(template, "reasoning.effort", reasoningEffort)

internal/translator/codex/gemini/codex_gemini_request.go

@@ -253,7 +253,7 @@ func ConvertGeminiRequestToCodex(modelName string, inputRawJSON []byte, _ bool)
 			if util.ModelUsesThinkingLevels(modelName) {
 				if thinkingBudget := thinkingConfig.Get("thinkingBudget"); thinkingBudget.Exists() {
 					budget := int(thinkingBudget.Int())
-					if effort, ok := util.OpenAIThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
+					if effort, ok := util.ThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
 						reasoningEffort = effort
 					}
 				}

internal/translator/openai/claude/openai_claude_request.go

@@ -63,10 +63,22 @@ func ConvertClaudeRequestToOpenAI(modelName string, inputRawJSON []byte, 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 != "" {
+		if thinkingType := thinking.Get("type"); thinkingType.Exists() {
+			switch thinkingType.String() {
+			case "enabled":
+				if budgetTokens := thinking.Get("budget_tokens"); budgetTokens.Exists() {
+					budget := int(budgetTokens.Int())
+					if effort, ok := util.ThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
+						out, _ = sjson.Set(out, "reasoning_effort", effort)
+					}
+				} else {
+					// No budget_tokens specified, default to "auto" for enabled thinking
+					if effort, ok := util.ThinkingBudgetToEffort(modelName, -1); ok && effort != "" {
+						out, _ = sjson.Set(out, "reasoning_effort", effort)
+					}
+				}
+			case "disabled":
+				if effort, ok := util.ThinkingBudgetToEffort(modelName, 0); ok && effort != "" {
 					out, _ = sjson.Set(out, "reasoning_effort", effort)
 				}
 			}

internal/translator/openai/gemini/openai_gemini_request.go

@@ -83,7 +83,7 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 		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 != "" {
+				if effort, ok := util.ThinkingBudgetToEffort(modelName, budget); ok && effort != "" {
 					out, _ = sjson.Set(out, "reasoning_effort", effort)
 				}
 			}

internal/util/openai_thinking.go

@@ -1,37 +0,0 @@
-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

@@ -118,3 +118,83 @@ func IsOpenAICompatibilityModel(model string) bool {
 	}
 	return strings.EqualFold(strings.TrimSpace(info.Type), "openai-compatibility")
 }
+
+// ThinkingEffortToBudget maps a reasoning effort level to a numeric thinking budget (tokens),
+// clamping the result to the model's supported range.
+//
+// Mappings (values are normalized to model's supported range):
+//   - "none"    -> 0
+//   - "auto"    -> -1
+//   - "minimal" -> 512
+//   - "low"     -> 1024
+//   - "medium"  -> 8192
+//   - "high"    -> 24576
+//   - "xhigh"   -> 32768
+//
+// Returns false when the effort level is empty or unsupported.
+func ThinkingEffortToBudget(model, effort string) (int, bool) {
+	if effort == "" {
+		return 0, false
+	}
+	normalized, ok := NormalizeReasoningEffortLevel(model, effort)
+	if !ok {
+		normalized = strings.ToLower(strings.TrimSpace(effort))
+	}
+	switch normalized {
+	case "none":
+		return 0, true
+	case "auto":
+		return NormalizeThinkingBudget(model, -1), true
+	case "minimal":
+		return NormalizeThinkingBudget(model, 512), true
+	case "low":
+		return NormalizeThinkingBudget(model, 1024), true
+	case "medium":
+		return NormalizeThinkingBudget(model, 8192), true
+	case "high":
+		return NormalizeThinkingBudget(model, 24576), true
+	case "xhigh":
+		return NormalizeThinkingBudget(model, 32768), true
+	default:
+		return 0, false
+	}
+}
+
+// ThinkingBudgetToEffort maps a numeric thinking budget (tokens)
+// to a reasoning effort level for level-based models.
+//
+// Mappings:
+//   - 0            -> "none" (or lowest supported level if model doesn't support "none")
+//   - -1           -> "auto"
+//   - 1..1024      -> "low"
+//   - 1025..8192   -> "medium"
+//   - 8193..24576  -> "high"
+//   - 24577..      -> highest supported level for the model (defaults to "xhigh")
+//
+// Returns false when the budget is unsupported (negative values other than -1).
+func ThinkingBudgetToEffort(model string, budget int) (string, bool) {
+	switch {
+	case budget == -1:
+		return "auto", true
+	case budget < -1:
+		return "", false
+	case budget == 0:
+		if levels := GetModelThinkingLevels(model); len(levels) > 0 {
+			return levels[0], true
+		}
+		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_suffix.go

@@ -201,36 +201,6 @@ func ReasoningEffortFromMetadata(metadata map[string]any) (string, bool) {
 	return "", true
 }
 
-// ThinkingEffortToBudget maps reasoning effort levels to approximate budgets,
-// clamping the result to the model's supported range.
-func ThinkingEffortToBudget(model, effort string) (int, bool) {
-	if effort == "" {
-		return 0, false
-	}
-	normalized, ok := NormalizeReasoningEffortLevel(model, effort)
-	if !ok {
-		normalized = strings.ToLower(strings.TrimSpace(effort))
-	}
-	switch normalized {
-	case "none":
-		return 0, true
-	case "auto":
-		return NormalizeThinkingBudget(model, -1), true
-	case "minimal":
-		return NormalizeThinkingBudget(model, 512), true
-	case "low":
-		return NormalizeThinkingBudget(model, 1024), true
-	case "medium":
-		return NormalizeThinkingBudget(model, 8192), true
-	case "high":
-		return NormalizeThinkingBudget(model, 24576), true
-	case "xhigh":
-		return NormalizeThinkingBudget(model, 32768), true
-	default:
-		return 0, false
-	}
-}
-
 // ResolveOriginalModel returns the original model name stored in metadata (if present),
 // otherwise falls back to the provided model.
 func ResolveOriginalModel(model string, metadata map[string]any) string {

internal/watcher/diff/config_diff.go

@@ -51,6 +51,9 @@ func BuildConfigChangeDetails(oldCfg, newCfg *config.Config) []string {
 	if oldCfg.WebsocketAuth != newCfg.WebsocketAuth {
 		changes = append(changes, fmt.Sprintf("ws-auth: %t -> %t", oldCfg.WebsocketAuth, newCfg.WebsocketAuth))
 	}
+	if oldCfg.ForceModelPrefix != newCfg.ForceModelPrefix {
+		changes = append(changes, fmt.Sprintf("force-model-prefix: %t -> %t", oldCfg.ForceModelPrefix, newCfg.ForceModelPrefix))
+	}
 
 	// Quota-exceeded behavior
 	if oldCfg.QuotaExceeded.SwitchProject != newCfg.QuotaExceeded.SwitchProject {

internal/watcher/watcher.go

@@ -184,7 +184,7 @@ func (w *Watcher) Start(ctx context.Context) error {
 	go w.processEvents(ctx)
 
 	// Perform an initial full reload based on current config and auth dir
-	w.reloadClients(true, nil)
+	w.reloadClients(true, nil, false)
 	return nil
 }
 
@@ -277,7 +277,7 @@ func (w *Watcher) DispatchRuntimeAuthUpdate(update AuthUpdate) bool {
 	return true
 }
 
-func (w *Watcher) refreshAuthState() {
+func (w *Watcher) refreshAuthState(force bool) {
 	auths := w.SnapshotCoreAuths()
 	w.clientsMutex.Lock()
 	if len(w.runtimeAuths) > 0 {
@@ -287,12 +287,12 @@ func (w *Watcher) refreshAuthState() {
 			}
 		}
 	}
-	updates := w.prepareAuthUpdatesLocked(auths)
+	updates := w.prepareAuthUpdatesLocked(auths, force)
 	w.clientsMutex.Unlock()
 	w.dispatchAuthUpdates(updates)
 }
 
-func (w *Watcher) prepareAuthUpdatesLocked(auths []*coreauth.Auth) []AuthUpdate {
+func (w *Watcher) prepareAuthUpdatesLocked(auths []*coreauth.Auth, force bool) []AuthUpdate {
 	newState := make(map[string]*coreauth.Auth, len(auths))
 	for _, auth := range auths {
 		if auth == nil || auth.ID == "" {
@@ -319,7 +319,7 @@ func (w *Watcher) prepareAuthUpdatesLocked(auths []*coreauth.Auth) []AuthUpdate
 	for id, auth := range newState {
 		if existing, ok := w.currentAuths[id]; !ok {
 			updates = append(updates, AuthUpdate{Action: AuthUpdateActionAdd, ID: id, Auth: auth.Clone()})
-		} else if !authEqual(existing, auth) {
+		} else if force || !authEqual(existing, auth) {
 			updates = append(updates, AuthUpdate{Action: AuthUpdateActionModify, ID: id, Auth: auth.Clone()})
 		}
 	}
@@ -786,15 +786,16 @@ func (w *Watcher) reloadConfig() bool {
 	}
 
 	authDirChanged := oldConfig == nil || oldConfig.AuthDir != newConfig.AuthDir
+	forceAuthRefresh := oldConfig != nil && oldConfig.ForceModelPrefix != newConfig.ForceModelPrefix
 
 	log.Infof("config successfully reloaded, triggering client reload")
 	// Reload clients with new config
-	w.reloadClients(authDirChanged, affectedOAuthProviders)
+	w.reloadClients(authDirChanged, affectedOAuthProviders, forceAuthRefresh)
 	return true
 }
 
 // reloadClients performs a full scan and reload of all clients.
-func (w *Watcher) reloadClients(rescanAuth bool, affectedOAuthProviders []string) {
+func (w *Watcher) reloadClients(rescanAuth bool, affectedOAuthProviders []string, forceAuthRefresh bool) {
 	log.Debugf("starting full client load process")
 
 	w.clientsMutex.RLock()
@@ -885,7 +886,7 @@ func (w *Watcher) reloadClients(rescanAuth bool, affectedOAuthProviders []string
 		w.reloadCallback(cfg)
 	}
 
-	w.refreshAuthState()
+	w.refreshAuthState(forceAuthRefresh)
 
 	log.Infof("full client load complete - %d clients (%d auth files + %d Gemini API keys + %d Vertex API keys + %d Claude API keys + %d Codex keys + %d OpenAI-compat)",
 		totalNewClients,
@@ -936,7 +937,7 @@ func (w *Watcher) addOrUpdateClient(path string) {
 
 	w.clientsMutex.Unlock() // Unlock before the callback
 
-	w.refreshAuthState()
+	w.refreshAuthState(false)
 
 	if w.reloadCallback != nil {
 		log.Debugf("triggering server update callback after add/update")
@@ -955,7 +956,7 @@ func (w *Watcher) removeClient(path string) {
 
 	w.clientsMutex.Unlock() // Release the lock before the callback
 
-	w.refreshAuthState()
+	w.refreshAuthState(false)
 
 	if w.reloadCallback != nil {
 		log.Debugf("triggering server update callback after removal")
@@ -984,6 +985,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 			if key == "" {
 				continue
 			}
+			prefix := strings.TrimSpace(entry.Prefix)
 			base := strings.TrimSpace(entry.BaseURL)
 			proxyURL := strings.TrimSpace(entry.ProxyURL)
 			id, token := idGen.next("gemini:apikey", key, base)
@@ -999,6 +1001,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 				ID:         id,
 				Provider:   "gemini",
 				Label:      "gemini-apikey",
+				Prefix:     prefix,
 				Status:     coreauth.StatusActive,
 				ProxyURL:   proxyURL,
 				Attributes: attrs,
@@ -1016,6 +1019,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 			if key == "" {
 				continue
 			}
+			prefix := strings.TrimSpace(ck.Prefix)
 			base := strings.TrimSpace(ck.BaseURL)
 			id, token := idGen.next("claude:apikey", key, base)
 			attrs := map[string]string{
@@ -1034,6 +1038,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 				ID:         id,
 				Provider:   "claude",
 				Label:      "claude-apikey",
+				Prefix:     prefix,
 				Status:     coreauth.StatusActive,
 				ProxyURL:   proxyURL,
 				Attributes: attrs,
@@ -1050,6 +1055,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 			if key == "" {
 				continue
 			}
+			prefix := strings.TrimSpace(ck.Prefix)
 			id, token := idGen.next("codex:apikey", key, ck.BaseURL)
 			attrs := map[string]string{
 				"source":  fmt.Sprintf("config:codex[%s]", token),
@@ -1064,6 +1070,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 				ID:         id,
 				Provider:   "codex",
 				Label:      "codex-apikey",
+				Prefix:     prefix,
 				Status:     coreauth.StatusActive,
 				ProxyURL:   proxyURL,
 				Attributes: attrs,
@@ -1075,6 +1082,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 		}
 		for i := range cfg.OpenAICompatibility {
 			compat := &cfg.OpenAICompatibility[i]
+			prefix := strings.TrimSpace(compat.Prefix)
 			providerName := strings.ToLower(strings.TrimSpace(compat.Name))
 			if providerName == "" {
 				providerName = "openai-compatibility"
@@ -1106,6 +1114,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 					ID:         id,
 					Provider:   providerName,
 					Label:      compat.Name,
+					Prefix:     prefix,
 					Status:     coreauth.StatusActive,
 					ProxyURL:   proxyURL,
 					Attributes: attrs,
@@ -1132,6 +1141,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 					ID:         id,
 					Provider:   providerName,
 					Label:      compat.Name,
+					Prefix:     prefix,
 					Status:     coreauth.StatusActive,
 					Attributes: attrs,
 					CreatedAt:  now,
@@ -1149,6 +1159,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 		base := strings.TrimSpace(compat.BaseURL)
 
 		key := strings.TrimSpace(compat.APIKey)
+		prefix := strings.TrimSpace(compat.Prefix)
 		proxyURL := strings.TrimSpace(compat.ProxyURL)
 		idKind := "vertex:apikey"
 		id, token := idGen.next(idKind, key, base, proxyURL)
@@ -1168,6 +1179,7 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 			ID:         id,
 			Provider:   providerName,
 			Label:      "vertex-apikey",
+			Prefix:     prefix,
 			Status:     coreauth.StatusActive,
 			ProxyURL:   proxyURL,
 			Attributes: attrs,
@@ -1220,10 +1232,20 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 			proxyURL = p
 		}
 
+		prefix := ""
+		if rawPrefix, ok := metadata["prefix"].(string); ok {
+			trimmed := strings.TrimSpace(rawPrefix)
+			trimmed = strings.Trim(trimmed, "/")
+			if trimmed != "" && !strings.Contains(trimmed, "/") {
+				prefix = trimmed
+			}
+		}
+
 		a := &coreauth.Auth{
 			ID:       id,
 			Provider: provider,
 			Label:    label,
+			Prefix:   prefix,
 			Status:   coreauth.StatusActive,
 			Attributes: map[string]string{
 				"source": full,
@@ -1310,6 +1332,7 @@ func synthesizeGeminiVirtualAuths(primary *coreauth.Auth, metadata map[string]an
 			Attributes: attrs,
 			Metadata:   metadataCopy,
 			ProxyURL:   primary.ProxyURL,
+			Prefix:     primary.Prefix,
 			CreatedAt:  now,
 			UpdatedAt:  now,
 			Runtime:    geminicli.NewVirtualCredential(projectID, shared),

internal/watcher/watcher_test.go

@@ -497,7 +497,7 @@ func TestReloadClientsCachesAuthHashes(t *testing.T) {
 		config:  &config.Config{AuthDir: tmpDir},
 	}
 
-	w.reloadClients(true, nil)
+	w.reloadClients(true, nil, false)
 
 	w.clientsMutex.RLock()
 	defer w.clientsMutex.RUnlock()
@@ -522,7 +522,7 @@ func TestReloadClientsLogsConfigDiffs(t *testing.T) {
 	w.config = newCfg
 	w.clientsMutex.Unlock()
 
-	w.reloadClients(false, nil)
+	w.reloadClients(false, nil, false)
 }
 
 func TestSetAuthUpdateQueueNilResetsDispatch(t *testing.T) {