Merge branch 'router-for-me:main' into main

This update enhances the `FileRequestLogger` by introducing support for spooling large request and response bodies to temporary files, reducing memory consumption. It adds atomic requestLogID generation for sequential log naming and new methods for non-streaming/streaming log assembly. Also includes better error handling during logging and temp file cleanups.

cmd/server/main.go

@@ -434,7 +434,7 @@ func main() {
 	usage.SetStatisticsEnabled(cfg.UsageStatisticsEnabled)
 	coreauth.SetQuotaCooldownDisabled(cfg.DisableCooling)
 
-	if err = logging.ConfigureLogOutput(cfg.LoggingToFile); err != nil {
+	if err = logging.ConfigureLogOutput(cfg.LoggingToFile, cfg.LogsMaxTotalSizeMB); err != nil {
 		log.Errorf("failed to configure log output: %v", err)
 		return
 	}

config.example.yaml

@@ -47,6 +47,10 @@ incognito-browser: true
 # When true, write application logs to rotating files instead of stdout
 logging-to-file: false
 
+# Maximum total size (MB) of log files under the logs directory. When exceeded, the oldest log
+# files are deleted until within the limit. Set to 0 to disable.
+logs-max-total-size-mb: 0
+
 # When false, disable in-memory usage statistics aggregation
 usage-statistics-enabled: false
 

examples/custom-provider/main.go

@@ -23,13 +23,13 @@ import (
 	"time"
 
 	"github.com/gin-gonic/gin"
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/api"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/api"
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
 	sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
 	"github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy"
 	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	clipexec "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/logging"
 	sdktr "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
 )
 

internal/api/modules/amp/fallback_handlers.go

@@ -134,7 +134,43 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 		}
 
 		// Normalize model (handles dynamic thinking suffixes)
-		normalizedModel, _ := util.NormalizeThinkingModel(modelName)
+		normalizedModel, thinkingMetadata := util.NormalizeThinkingModel(modelName)
+		thinkingSuffix := ""
+		if thinkingMetadata != nil && strings.HasPrefix(modelName, normalizedModel) {
+			thinkingSuffix = modelName[len(normalizedModel):]
+		}
+
+		resolveMappedModel := func() (string, []string) {
+			if fh.modelMapper == nil {
+				return "", nil
+			}
+
+			mappedModel := fh.modelMapper.MapModel(modelName)
+			if mappedModel == "" {
+				mappedModel = fh.modelMapper.MapModel(normalizedModel)
+			}
+			mappedModel = strings.TrimSpace(mappedModel)
+			if mappedModel == "" {
+				return "", nil
+			}
+
+			// Preserve dynamic thinking suffix (e.g. "(xhigh)") when mapping applies, unless the target
+			// already specifies its own thinking suffix.
+			if thinkingSuffix != "" {
+				_, mappedThinkingMetadata := util.NormalizeThinkingModel(mappedModel)
+				if mappedThinkingMetadata == nil {
+					mappedModel += thinkingSuffix
+				}
+			}
+
+			mappedBaseModel, _ := util.NormalizeThinkingModel(mappedModel)
+			mappedProviders := util.GetProviderName(mappedBaseModel)
+			if len(mappedProviders) == 0 {
+				return "", nil
+			}
+
+			return mappedModel, mappedProviders
+		}
 
 		// Track resolved model for logging (may change if mapping is applied)
 		resolvedModel := normalizedModel
@@ -147,21 +183,15 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 		if forceMappings {
 			// FORCE MODE: Check model mappings FIRST (takes precedence over local API keys)
 			// This allows users to route Amp requests to their preferred OAuth providers
-			if fh.modelMapper != nil {
+			if mappedModel, mappedProviders := resolveMappedModel(); mappedModel != "" {
-				if mappedModel := fh.modelMapper.MapModel(normalizedModel); mappedModel != "" {
+				// Mapping found and provider available - rewrite the model in request body
-					// Mapping found - check if we have a provider for the mapped model
+				bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
-					mappedProviders := util.GetProviderName(mappedModel)
+				c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
-					if len(mappedProviders) > 0 {
+				// Store mapped model in context for handlers that check it (like gemini bridge)
-						// Mapping found and provider available - rewrite the model in request body
+				c.Set(MappedModelContextKey, mappedModel)
-						bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
+				resolvedModel = mappedModel
-						c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+				usedMapping = true
-						// Store mapped model in context for handlers that check it (like gemini bridge)
+				providers = mappedProviders
-						c.Set(MappedModelContextKey, mappedModel)
-						resolvedModel = mappedModel
-						usedMapping = true
-						providers = mappedProviders
-					}
-				}
 			}
 
 			// If no mapping applied, check for local providers
@@ -174,21 +204,15 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 
 			if len(providers) == 0 {
 				// No providers configured - check if we have a model mapping
-				if fh.modelMapper != nil {
+				if mappedModel, mappedProviders := resolveMappedModel(); mappedModel != "" {
-					if mappedModel := fh.modelMapper.MapModel(normalizedModel); mappedModel != "" {
+					// Mapping found and provider available - rewrite the model in request body
-						// Mapping found - check if we have a provider for the mapped model
+					bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
-						mappedProviders := util.GetProviderName(mappedModel)
+					c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
-						if len(mappedProviders) > 0 {
+					// Store mapped model in context for handlers that check it (like gemini bridge)
-							// Mapping found and provider available - rewrite the model in request body
+					c.Set(MappedModelContextKey, mappedModel)
-							bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
+					resolvedModel = mappedModel
-							c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+					usedMapping = true
-							// Store mapped model in context for handlers that check it (like gemini bridge)
+					providers = mappedProviders
-							c.Set(MappedModelContextKey, mappedModel)
-							resolvedModel = mappedModel
-							usedMapping = true
-							providers = mappedProviders
-						}
-					}
 				}
 			}
 		}
@@ -222,14 +246,14 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 			// Log: Model was mapped to another model
 			log.Debugf("amp model mapping: request %s -> %s", normalizedModel, resolvedModel)
 			logAmpRouting(RouteTypeModelMapping, modelName, resolvedModel, providerName, requestPath)
-			rewriter := NewResponseRewriter(c.Writer, normalizedModel)
+			rewriter := NewResponseRewriter(c.Writer, modelName)
 			c.Writer = rewriter
 			// Filter Anthropic-Beta header only for local handling paths
 			filterAntropicBetaHeader(c)
 			c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
 			handler(c)
 			rewriter.Flush()
-			log.Debugf("amp model mapping: response %s -> %s", resolvedModel, normalizedModel)
+			log.Debugf("amp model mapping: response %s -> %s", resolvedModel, modelName)
 		} else if len(providers) > 0 {
 			// Log: Using local provider (free)
 			logAmpRouting(RouteTypeLocalProvider, modelName, resolvedModel, providerName, requestPath)

internal/api/modules/amp/fallback_handlers_test.go

@@ -0,0 +1,73 @@
+package amp
+
+import (
+	"bytes"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"net/http/httputil"
+	"testing"
+
+	"github.com/gin-gonic/gin"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+)
+
+func TestFallbackHandler_ModelMapping_PreservesThinkingSuffixAndRewritesResponse(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-amp-fallback", "codex", []*registry.ModelInfo{
+		{ID: "test/gpt-5.2", OwnedBy: "openai", Type: "codex"},
+	})
+	defer reg.UnregisterClient("test-client-amp-fallback")
+
+	mapper := NewModelMapper([]config.AmpModelMapping{
+		{From: "gpt-5.2", To: "test/gpt-5.2"},
+	})
+
+	fallback := NewFallbackHandlerWithMapper(func() *httputil.ReverseProxy { return nil }, mapper, nil)
+
+	handler := func(c *gin.Context) {
+		var req struct {
+			Model string `json:"model"`
+		}
+		if err := c.ShouldBindJSON(&req); err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+			return
+		}
+
+		c.JSON(http.StatusOK, gin.H{
+			"model":      req.Model,
+			"seen_model": req.Model,
+		})
+	}
+
+	r := gin.New()
+	r.POST("/chat/completions", fallback.WrapHandler(handler))
+
+	reqBody := []byte(`{"model":"gpt-5.2(xhigh)"}`)
+	req := httptest.NewRequest(http.MethodPost, "/chat/completions", bytes.NewReader(reqBody))
+	req.Header.Set("Content-Type", "application/json")
+	w := httptest.NewRecorder()
+	r.ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("Expected status 200, got %d", w.Code)
+	}
+
+	var resp struct {
+		Model     string `json:"model"`
+		SeenModel string `json:"seen_model"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+		t.Fatalf("Failed to parse response JSON: %v", err)
+	}
+
+	if resp.Model != "gpt-5.2(xhigh)" {
+		t.Errorf("Expected response model gpt-5.2(xhigh), got %s", resp.Model)
+	}
+	if resp.SeenModel != "test/gpt-5.2(xhigh)" {
+		t.Errorf("Expected handler to see test/gpt-5.2(xhigh), got %s", resp.SeenModel)
+	}
+}

internal/api/modules/amp/model_mapping.go

@@ -59,7 +59,8 @@ func (m *DefaultModelMapper) MapModel(requestedModel string) string {
 	}
 
 	// Verify target model has available providers
-	providers := util.GetProviderName(targetModel)
+	normalizedTarget, _ := util.NormalizeThinkingModel(targetModel)
+	providers := util.GetProviderName(normalizedTarget)
 	if len(providers) == 0 {
 		log.Debugf("amp model mapping: target model %s has no available providers, skipping mapping", targetModel)
 		return ""

internal/api/modules/amp/model_mapping_test.go

@@ -71,6 +71,25 @@ func TestModelMapper_MapModel_WithProvider(t *testing.T) {
 	}
 }
 
+func TestModelMapper_MapModel_TargetWithThinkingSuffix(t *testing.T) {
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-thinking", "codex", []*registry.ModelInfo{
+		{ID: "gpt-5.2", OwnedBy: "openai", Type: "codex"},
+	})
+	defer reg.UnregisterClient("test-client-thinking")
+
+	mappings := []config.AmpModelMapping{
+		{From: "gpt-5.2-alias", To: "gpt-5.2(xhigh)"},
+	}
+
+	mapper := NewModelMapper(mappings)
+
+	result := mapper.MapModel("gpt-5.2-alias")
+	if result != "gpt-5.2(xhigh)" {
+		t.Errorf("Expected gpt-5.2(xhigh), got %s", result)
+	}
+}
+
 func TestModelMapper_MapModel_CaseInsensitive(t *testing.T) {
 	reg := registry.GetGlobalRegistry()
 	reg.RegisterClient("test-client2", "claude", []*registry.ModelInfo{

internal/api/modules/amp/routes.go

@@ -126,7 +126,7 @@ func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *ha
 	var authWithBypass gin.HandlerFunc
 	if auth != nil {
 		ampAPI.Use(auth)
-		authWithBypass = wrapManagementAuth(auth, "/threads", "/auth")
+		authWithBypass = wrapManagementAuth(auth, "/threads", "/auth", "/docs", "/settings")
 	}
 
 	// Dynamic proxy handler that uses m.getProxy() for hot-reload support
@@ -175,7 +175,13 @@ func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *ha
 	if authWithBypass != nil {
 		rootMiddleware = append(rootMiddleware, authWithBypass)
 	}
+	engine.GET("/threads", append(rootMiddleware, proxyHandler)...)
 	engine.GET("/threads/*path", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/docs", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/docs/*path", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/settings", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/settings/*path", append(rootMiddleware, proxyHandler)...)
+
 	engine.GET("/threads.rss", append(rootMiddleware, proxyHandler)...)
 	engine.GET("/news.rss", append(rootMiddleware, proxyHandler)...)
 

internal/api/server.go

@@ -865,11 +865,20 @@ func (s *Server) UpdateClients(cfg *config.Config) {
 		}
 	}
 
-	if oldCfg != nil && oldCfg.LoggingToFile != cfg.LoggingToFile {
+	if oldCfg == nil || oldCfg.LoggingToFile != cfg.LoggingToFile || oldCfg.LogsMaxTotalSizeMB != cfg.LogsMaxTotalSizeMB {
-		if err := logging.ConfigureLogOutput(cfg.LoggingToFile); err != nil {
+		if err := logging.ConfigureLogOutput(cfg.LoggingToFile, cfg.LogsMaxTotalSizeMB); err != nil {
 			log.Errorf("failed to reconfigure log output: %v", err)
 		} else {
-			log.Debugf("logging_to_file updated from %t to %t", oldCfg.LoggingToFile, cfg.LoggingToFile)
+			if oldCfg == nil {
+				log.Debug("log output configuration refreshed")
+			} else {
+				if oldCfg.LoggingToFile != cfg.LoggingToFile {
+					log.Debugf("logging_to_file updated from %t to %t", oldCfg.LoggingToFile, cfg.LoggingToFile)
+				}
+				if oldCfg.LogsMaxTotalSizeMB != cfg.LogsMaxTotalSizeMB {
+					log.Debugf("logs_max_total_size_mb updated from %d to %d", oldCfg.LogsMaxTotalSizeMB, cfg.LogsMaxTotalSizeMB)
+				}
+			}
 		}
 	}
 

internal/config/config.go

@@ -12,7 +12,6 @@ import (
 	"strings"
 	"syscall"
 
-	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
 	"golang.org/x/crypto/bcrypt"
 	"gopkg.in/yaml.v3"
 )
@@ -21,7 +20,7 @@ const DefaultPanelGitHubRepository = "https://github.com/router-for-me/Cli-Proxy
 
 // Config represents the application's configuration, loaded from a YAML file.
 type Config struct {
-	config.SDKConfig `yaml:",inline"`
+	SDKConfig `yaml:",inline"`
 	// Host is the network host/interface on which the API server will bind.
 	// Default is empty ("") to bind all interfaces (IPv4 + IPv6). Use "127.0.0.1" or "localhost" for local-only access.
 	Host string `yaml:"host" json:"-"`
@@ -43,6 +42,10 @@ type Config struct {
 	// LoggingToFile controls whether application logs are written to rotating files or stdout.
 	LoggingToFile bool `yaml:"logging-to-file" json:"logging-to-file"`
 
+	// LogsMaxTotalSizeMB limits the total size (in MB) of log files under the logs directory.
+	// When exceeded, the oldest log files are deleted until within the limit. Set to 0 to disable.
+	LogsMaxTotalSizeMB int `yaml:"logs-max-total-size-mb" json:"logs-max-total-size-mb"`
+
 	// UsageStatisticsEnabled toggles in-memory usage aggregation; when false, usage data is discarded.
 	UsageStatisticsEnabled bool `yaml:"usage-statistics-enabled" json:"usage-statistics-enabled"`
 
@@ -383,6 +386,7 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	// Set defaults before unmarshal so that absent keys keep defaults.
 	cfg.Host = "" // Default empty: binds to all interfaces (IPv4 + IPv6)
 	cfg.LoggingToFile = false
+	cfg.LogsMaxTotalSizeMB = 0
 	cfg.UsageStatisticsEnabled = false
 	cfg.DisableCooling = false
 	cfg.AmpCode.RestrictManagementToLocalhost = false // Default to false: API key auth is sufficient
@@ -428,6 +432,10 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 		cfg.RemoteManagement.PanelGitHubRepository = DefaultPanelGitHubRepository
 	}
 
+	if cfg.LogsMaxTotalSizeMB < 0 {
+		cfg.LogsMaxTotalSizeMB = 0
+	}
+
 	// Sync request authentication providers with inline API keys for backwards compatibility.
 	syncInlineAccessProvider(&cfg)
 
@@ -754,7 +762,7 @@ func sanitizeConfigForPersist(cfg *Config) *Config {
 	}
 	clone := *cfg
 	clone.SDKConfig = cfg.SDKConfig
-	clone.SDKConfig.Access = config.AccessConfig{}
+	clone.SDKConfig.Access = AccessConfig{}
 	return &clone
 }
 

internal/config/sdk_config.go

@@ -0,0 +1,87 @@
+// Package config provides configuration management for the CLI Proxy API server.
+// It handles loading and parsing YAML configuration files, and provides structured
+// access to application settings including server port, authentication directory,
+// debug settings, proxy configuration, and API keys.
+package config
+
+// SDKConfig represents the application's configuration, loaded from a YAML file.
+type SDKConfig struct {
+	// ProxyURL is the URL of an optional proxy server to use for outbound requests.
+	ProxyURL string `yaml:"proxy-url" json:"proxy-url"`
+
+	// ForceModelPrefix requires explicit model prefixes (e.g., "teamA/gemini-3-pro-preview")
+	// to target prefixed credentials. When false, unprefixed model requests may use prefixed
+	// credentials as well.
+	ForceModelPrefix bool `yaml:"force-model-prefix" json:"force-model-prefix"`
+
+	// RequestLog enables or disables detailed request logging functionality.
+	RequestLog bool `yaml:"request-log" json:"request-log"`
+
+	// APIKeys is a list of keys for authenticating clients to this proxy server.
+	APIKeys []string `yaml:"api-keys" json:"api-keys"`
+
+	// Access holds request authentication provider configuration.
+	Access AccessConfig `yaml:"auth,omitempty" json:"auth,omitempty"`
+}
+
+// AccessConfig groups request authentication providers.
+type AccessConfig struct {
+	// Providers lists configured authentication providers.
+	Providers []AccessProvider `yaml:"providers,omitempty" json:"providers,omitempty"`
+}
+
+// AccessProvider describes a request authentication provider entry.
+type AccessProvider struct {
+	// Name is the instance identifier for the provider.
+	Name string `yaml:"name" json:"name"`
+
+	// Type selects the provider implementation registered via the SDK.
+	Type string `yaml:"type" json:"type"`
+
+	// SDK optionally names a third-party SDK module providing this provider.
+	SDK string `yaml:"sdk,omitempty" json:"sdk,omitempty"`
+
+	// APIKeys lists inline keys for providers that require them.
+	APIKeys []string `yaml:"api-keys,omitempty" json:"api-keys,omitempty"`
+
+	// Config passes provider-specific options to the implementation.
+	Config map[string]any `yaml:"config,omitempty" json:"config,omitempty"`
+}
+
+const (
+	// AccessProviderTypeConfigAPIKey is the built-in provider validating inline API keys.
+	AccessProviderTypeConfigAPIKey = "config-api-key"
+
+	// DefaultAccessProviderName is applied when no provider name is supplied.
+	DefaultAccessProviderName = "config-inline"
+)
+
+// ConfigAPIKeyProvider returns the first inline API key provider if present.
+func (c *SDKConfig) ConfigAPIKeyProvider() *AccessProvider {
+	if c == nil {
+		return nil
+	}
+	for i := range c.Access.Providers {
+		if c.Access.Providers[i].Type == AccessProviderTypeConfigAPIKey {
+			if c.Access.Providers[i].Name == "" {
+				c.Access.Providers[i].Name = DefaultAccessProviderName
+			}
+			return &c.Access.Providers[i]
+		}
+	}
+	return nil
+}
+
+// MakeInlineAPIKeyProvider constructs an inline API key provider configuration.
+// It returns nil when no keys are supplied.
+func MakeInlineAPIKeyProvider(keys []string) *AccessProvider {
+	if len(keys) == 0 {
+		return nil
+	}
+	provider := &AccessProvider{
+		Name:    DefaultAccessProviderName,
+		Type:    AccessProviderTypeConfigAPIKey,
+		APIKeys: append([]string(nil), keys...),
+	}
+	return provider
+}

internal/logging/global_logger.go

@@ -76,39 +76,45 @@ func SetupBaseLogger() {
 }
 
 // ConfigureLogOutput switches the global log destination between rotating files and stdout.
-func ConfigureLogOutput(loggingToFile bool) error {
+// When logsMaxTotalSizeMB > 0, a background cleaner removes the oldest log files in the logs directory
+// until the total size is within the limit.
+func ConfigureLogOutput(loggingToFile bool, logsMaxTotalSizeMB int) error {
 	SetupBaseLogger()
 
 	writerMu.Lock()
 	defer writerMu.Unlock()
 
+	logDir := "logs"
+	if base := util.WritablePath(); base != "" {
+		logDir = filepath.Join(base, "logs")
+	}
+
+	protectedPath := ""
 	if loggingToFile {
-		logDir := "logs"
-		if base := util.WritablePath(); base != "" {
-			logDir = filepath.Join(base, "logs")
-		}
 		if err := os.MkdirAll(logDir, 0o755); err != nil {
 			return fmt.Errorf("logging: failed to create log directory: %w", err)
 		}
 		if logWriter != nil {
 			_ = logWriter.Close()
 		}
+		protectedPath = filepath.Join(logDir, "main.log")
 		logWriter = &lumberjack.Logger{
-			Filename:   filepath.Join(logDir, "main.log"),
+			Filename:   protectedPath,
 			MaxSize:    10,
 			MaxBackups: 0,
 			MaxAge:     0,
 			Compress:   false,
 		}
 		log.SetOutput(logWriter)
-		return nil
+	} else {
+		if logWriter != nil {
+			_ = logWriter.Close()
+			logWriter = nil
+		}
+		log.SetOutput(os.Stdout)
 	}
 
-	if logWriter != nil {
+	configureLogDirCleanerLocked(logDir, logsMaxTotalSizeMB, protectedPath)
-		_ = logWriter.Close()
-		logWriter = nil
-	}
-	log.SetOutput(os.Stdout)
 	return nil
 }
 
@@ -116,6 +122,8 @@ func closeLogOutputs() {
 	writerMu.Lock()
 	defer writerMu.Unlock()
 
+	stopLogDirCleanerLocked()
+
 	if logWriter != nil {
 		_ = logWriter.Close()
 		logWriter = nil

internal/logging/log_dir_cleaner.go

@@ -0,0 +1,166 @@
+package logging
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+)
+
+const logDirCleanerInterval = time.Minute
+
+var logDirCleanerCancel context.CancelFunc
+
+func configureLogDirCleanerLocked(logDir string, maxTotalSizeMB int, protectedPath string) {
+	stopLogDirCleanerLocked()
+
+	if maxTotalSizeMB <= 0 {
+		return
+	}
+
+	maxBytes := int64(maxTotalSizeMB) * 1024 * 1024
+	if maxBytes <= 0 {
+		return
+	}
+
+	dir := strings.TrimSpace(logDir)
+	if dir == "" {
+		return
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	logDirCleanerCancel = cancel
+	go runLogDirCleaner(ctx, filepath.Clean(dir), maxBytes, strings.TrimSpace(protectedPath))
+}
+
+func stopLogDirCleanerLocked() {
+	if logDirCleanerCancel == nil {
+		return
+	}
+	logDirCleanerCancel()
+	logDirCleanerCancel = nil
+}
+
+func runLogDirCleaner(ctx context.Context, logDir string, maxBytes int64, protectedPath string) {
+	ticker := time.NewTicker(logDirCleanerInterval)
+	defer ticker.Stop()
+
+	cleanOnce := func() {
+		deleted, errClean := enforceLogDirSizeLimit(logDir, maxBytes, protectedPath)
+		if errClean != nil {
+			log.WithError(errClean).Warn("logging: failed to enforce log directory size limit")
+			return
+		}
+		if deleted > 0 {
+			log.Debugf("logging: removed %d old log file(s) to enforce log directory size limit", deleted)
+		}
+	}
+
+	cleanOnce()
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			cleanOnce()
+		}
+	}
+}
+
+func enforceLogDirSizeLimit(logDir string, maxBytes int64, protectedPath string) (int, error) {
+	if maxBytes <= 0 {
+		return 0, nil
+	}
+
+	dir := strings.TrimSpace(logDir)
+	if dir == "" {
+		return 0, nil
+	}
+	dir = filepath.Clean(dir)
+
+	entries, errRead := os.ReadDir(dir)
+	if errRead != nil {
+		if os.IsNotExist(errRead) {
+			return 0, nil
+		}
+		return 0, errRead
+	}
+
+	protected := strings.TrimSpace(protectedPath)
+	if protected != "" {
+		protected = filepath.Clean(protected)
+	}
+
+	type logFile struct {
+		path    string
+		size    int64
+		modTime time.Time
+	}
+
+	var (
+		files []logFile
+		total int64
+	)
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		name := entry.Name()
+		if !isLogFileName(name) {
+			continue
+		}
+		info, errInfo := entry.Info()
+		if errInfo != nil {
+			continue
+		}
+		if !info.Mode().IsRegular() {
+			continue
+		}
+		path := filepath.Join(dir, name)
+		files = append(files, logFile{
+			path:    path,
+			size:    info.Size(),
+			modTime: info.ModTime(),
+		})
+		total += info.Size()
+	}
+
+	if total <= maxBytes {
+		return 0, nil
+	}
+
+	sort.Slice(files, func(i, j int) bool {
+		return files[i].modTime.Before(files[j].modTime)
+	})
+
+	deleted := 0
+	for _, file := range files {
+		if total <= maxBytes {
+			break
+		}
+		if protected != "" && filepath.Clean(file.path) == protected {
+			continue
+		}
+		if errRemove := os.Remove(file.path); errRemove != nil {
+			log.WithError(errRemove).Warnf("logging: failed to remove old log file: %s", filepath.Base(file.path))
+			continue
+		}
+		total -= file.size
+		deleted++
+	}
+
+	return deleted, nil
+}
+
+func isLogFileName(name string) bool {
+	trimmed := strings.TrimSpace(name)
+	if trimmed == "" {
+		return false
+	}
+	lower := strings.ToLower(trimmed)
+	return strings.HasSuffix(lower, ".log") || strings.HasSuffix(lower, ".log.gz")
+}

internal/logging/log_dir_cleaner_test.go

@@ -0,0 +1,70 @@
+package logging
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+)
+
+func TestEnforceLogDirSizeLimitDeletesOldest(t *testing.T) {
+	dir := t.TempDir()
+
+	writeLogFile(t, filepath.Join(dir, "old.log"), 60, time.Unix(1, 0))
+	writeLogFile(t, filepath.Join(dir, "mid.log"), 60, time.Unix(2, 0))
+	protected := filepath.Join(dir, "main.log")
+	writeLogFile(t, protected, 60, time.Unix(3, 0))
+
+	deleted, err := enforceLogDirSizeLimit(dir, 120, protected)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("expected 1 deleted file, got %d", deleted)
+	}
+
+	if _, err := os.Stat(filepath.Join(dir, "old.log")); !os.IsNotExist(err) {
+		t.Fatalf("expected old.log to be removed, stat error: %v", err)
+	}
+	if _, err := os.Stat(filepath.Join(dir, "mid.log")); err != nil {
+		t.Fatalf("expected mid.log to remain, stat error: %v", err)
+	}
+	if _, err := os.Stat(protected); err != nil {
+		t.Fatalf("expected protected main.log to remain, stat error: %v", err)
+	}
+}
+
+func TestEnforceLogDirSizeLimitSkipsProtected(t *testing.T) {
+	dir := t.TempDir()
+
+	protected := filepath.Join(dir, "main.log")
+	writeLogFile(t, protected, 200, time.Unix(1, 0))
+	writeLogFile(t, filepath.Join(dir, "other.log"), 50, time.Unix(2, 0))
+
+	deleted, err := enforceLogDirSizeLimit(dir, 100, protected)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("expected 1 deleted file, got %d", deleted)
+	}
+
+	if _, err := os.Stat(protected); err != nil {
+		t.Fatalf("expected protected main.log to remain, stat error: %v", err)
+	}
+	if _, err := os.Stat(filepath.Join(dir, "other.log")); !os.IsNotExist(err) {
+		t.Fatalf("expected other.log to be removed, stat error: %v", err)
+	}
+}
+
+func writeLogFile(t *testing.T, path string, size int, modTime time.Time) {
+	t.Helper()
+
+	data := make([]byte, size)
+	if err := os.WriteFile(path, data, 0o644); err != nil {
+		t.Fatalf("write file: %v", err)
+	}
+	if err := os.Chtimes(path, modTime, modTime); err != nil {
+		t.Fatalf("set times: %v", err)
+	}
+}

internal/logging/request_logger.go

@@ -14,6 +14,7 @@ import (
 	"regexp"
 	"sort"
 	"strings"
+	"sync/atomic"
 	"time"
 
 	"github.com/andybalholm/brotli"
@@ -25,6 +26,8 @@ import (
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 )
 
+var requestLogID atomic.Uint64
+
 // RequestLogger defines the interface for logging HTTP requests and responses.
 // It provides methods for logging both regular and streaming HTTP request/response cycles.
 type RequestLogger interface {
@@ -204,19 +207,52 @@ func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[st
 	}
 	filePath := filepath.Join(l.logsDir, filename)
 
-	// Decompress response if needed
+	requestBodyPath, errTemp := l.writeRequestBodyTempFile(body)
-	decompressedResponse, err := l.decompressResponse(responseHeaders, response)
+	if errTemp != nil {
-	if err != nil {
+		log.WithError(errTemp).Warn("failed to create request body temp file, falling back to direct write")
-		// If decompression fails, log the error but continue with original response
+	}
-		decompressedResponse = append(response, []byte(fmt.Sprintf("\n[DECOMPRESSION ERROR: %v]", err))...)
+	if requestBodyPath != "" {
+		defer func() {
+			if errRemove := os.Remove(requestBodyPath); errRemove != nil {
+				log.WithError(errRemove).Warn("failed to remove request body temp file")
+			}
+		}()
 	}
 
-	// Create log content
+	responseToWrite, decompressErr := l.decompressResponse(responseHeaders, response)
-	content := l.formatLogContent(url, method, requestHeaders, body, apiRequest, apiResponse, decompressedResponse, statusCode, responseHeaders, apiResponseErrors)
+	if decompressErr != nil {
+		// If decompression fails, continue with original response and annotate the log output.
+		responseToWrite = response
+	}
 
-	// Write to file
+	logFile, errOpen := os.OpenFile(filePath, os.O_CREATE|os.O_WRONLY|os.O_TRUNC, 0644)
-	if err = os.WriteFile(filePath, []byte(content), 0644); err != nil {
+	if errOpen != nil {
-		return fmt.Errorf("failed to write log file: %w", err)
+		return fmt.Errorf("failed to create log file: %w", errOpen)
+	}
+
+	writeErr := l.writeNonStreamingLog(
+		logFile,
+		url,
+		method,
+		requestHeaders,
+		body,
+		requestBodyPath,
+		apiRequest,
+		apiResponse,
+		apiResponseErrors,
+		statusCode,
+		responseHeaders,
+		responseToWrite,
+		decompressErr,
+	)
+	if errClose := logFile.Close(); errClose != nil {
+		log.WithError(errClose).Warn("failed to close request log file")
+		if writeErr == nil {
+			return errClose
+		}
+	}
+	if writeErr != nil {
+		return fmt.Errorf("failed to write log file: %w", writeErr)
 	}
 
 	if force && !l.enabled {
@@ -253,26 +289,38 @@ func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[
 	filename := l.generateFilename(url)
 	filePath := filepath.Join(l.logsDir, filename)
 
-	// Create and open file
+	requestHeaders := make(map[string][]string, len(headers))
-	file, err := os.Create(filePath)
+	for key, values := range headers {
-	if err != nil {
+		headerValues := make([]string, len(values))
-		return nil, fmt.Errorf("failed to create log file: %w", err)
+		copy(headerValues, values)
+		requestHeaders[key] = headerValues
 	}
 
-	// Write initial request information
+	requestBodyPath, errTemp := l.writeRequestBodyTempFile(body)
-	requestInfo := l.formatRequestInfo(url, method, headers, body)
+	if errTemp != nil {
-	if _, err = file.WriteString(requestInfo); err != nil {
+		return nil, fmt.Errorf("failed to create request body temp file: %w", errTemp)
-		_ = file.Close()
-		return nil, fmt.Errorf("failed to write request info: %w", err)
 	}
 
+	responseBodyFile, errCreate := os.CreateTemp(l.logsDir, "response-body-*.tmp")
+	if errCreate != nil {
+		_ = os.Remove(requestBodyPath)
+		return nil, fmt.Errorf("failed to create response body temp file: %w", errCreate)
+	}
+	responseBodyPath := responseBodyFile.Name()
+
 	// Create streaming writer
 	writer := &FileStreamingLogWriter{
-		file:           file,
+		logFilePath:      filePath,
-		chunkChan:      make(chan []byte, 100), // Buffered channel for async writes
+		url:              url,
-		closeChan:      make(chan struct{}),
+		method:           method,
-		errorChan:      make(chan error, 1),
+		timestamp:        time.Now(),
-		bufferedChunks: &bytes.Buffer{},
+		requestHeaders:   requestHeaders,
+		requestBodyPath:  requestBodyPath,
+		responseBodyPath: responseBodyPath,
+		responseBodyFile: responseBodyFile,
+		chunkChan:        make(chan []byte, 100), // Buffered channel for async writes
+		closeChan:        make(chan struct{}),
+		errorChan:        make(chan error, 1),
 	}
 
 	// Start async writer goroutine
@@ -323,7 +371,9 @@ func (l *FileRequestLogger) generateFilename(url string) string {
 	timestamp := time.Now().Format("2006-01-02T150405-.000000000")
 	timestamp = strings.Replace(timestamp, ".", "", -1)
 
-	return fmt.Sprintf("%s-%s.log", sanitized, timestamp)
+	id := requestLogID.Add(1)
+
+	return fmt.Sprintf("%s-%s-%d.log", sanitized, timestamp, id)
 }
 
 // sanitizeForFilename replaces characters that are not safe for filenames.
@@ -405,6 +455,220 @@ func (l *FileRequestLogger) cleanupOldErrorLogs() error {
 	return nil
 }
 
+func (l *FileRequestLogger) writeRequestBodyTempFile(body []byte) (string, error) {
+	tmpFile, errCreate := os.CreateTemp(l.logsDir, "request-body-*.tmp")
+	if errCreate != nil {
+		return "", errCreate
+	}
+	tmpPath := tmpFile.Name()
+
+	if _, errCopy := io.Copy(tmpFile, bytes.NewReader(body)); errCopy != nil {
+		_ = tmpFile.Close()
+		_ = os.Remove(tmpPath)
+		return "", errCopy
+	}
+	if errClose := tmpFile.Close(); errClose != nil {
+		_ = os.Remove(tmpPath)
+		return "", errClose
+	}
+	return tmpPath, nil
+}
+
+func (l *FileRequestLogger) writeNonStreamingLog(
+	w io.Writer,
+	url, method string,
+	requestHeaders map[string][]string,
+	requestBody []byte,
+	requestBodyPath string,
+	apiRequest []byte,
+	apiResponse []byte,
+	apiResponseErrors []*interfaces.ErrorMessage,
+	statusCode int,
+	responseHeaders map[string][]string,
+	response []byte,
+	decompressErr error,
+) error {
+	if errWrite := writeRequestInfoWithBody(w, url, method, requestHeaders, requestBody, requestBodyPath, time.Now()); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(w, "=== API REQUEST ===\n", "=== API REQUEST", apiRequest); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPIErrorResponses(w, apiResponseErrors); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(w, "=== API RESPONSE ===\n", "=== API RESPONSE", apiResponse); errWrite != nil {
+		return errWrite
+	}
+	return writeResponseSection(w, statusCode, true, responseHeaders, bytes.NewReader(response), decompressErr, true)
+}
+
+func writeRequestInfoWithBody(
+	w io.Writer,
+	url, method string,
+	headers map[string][]string,
+	body []byte,
+	bodyPath string,
+	timestamp time.Time,
+) error {
+	if _, errWrite := io.WriteString(w, "=== REQUEST INFO ===\n"); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("Version: %s\n", buildinfo.Version)); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("URL: %s\n", url)); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("Method: %s\n", method)); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("Timestamp: %s\n", timestamp.Format(time.RFC3339Nano))); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if _, errWrite := io.WriteString(w, "=== HEADERS ===\n"); errWrite != nil {
+		return errWrite
+	}
+	for key, values := range headers {
+		for _, value := range values {
+			masked := util.MaskSensitiveHeaderValue(key, value)
+			if _, errWrite := io.WriteString(w, fmt.Sprintf("%s: %s\n", key, masked)); errWrite != nil {
+				return errWrite
+			}
+		}
+	}
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if _, errWrite := io.WriteString(w, "=== REQUEST BODY ===\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if bodyPath != "" {
+		bodyFile, errOpen := os.Open(bodyPath)
+		if errOpen != nil {
+			return errOpen
+		}
+		if _, errCopy := io.Copy(w, bodyFile); errCopy != nil {
+			_ = bodyFile.Close()
+			return errCopy
+		}
+		if errClose := bodyFile.Close(); errClose != nil {
+			log.WithError(errClose).Warn("failed to close request body temp file")
+		}
+	} else if _, errWrite := w.Write(body); errWrite != nil {
+		return errWrite
+	}
+
+	if _, errWrite := io.WriteString(w, "\n\n"); errWrite != nil {
+		return errWrite
+	}
+	return nil
+}
+
+func writeAPISection(w io.Writer, sectionHeader string, sectionPrefix string, payload []byte) error {
+	if len(payload) == 0 {
+		return nil
+	}
+
+	if bytes.HasPrefix(payload, []byte(sectionPrefix)) {
+		if _, errWrite := w.Write(payload); errWrite != nil {
+			return errWrite
+		}
+		if !bytes.HasSuffix(payload, []byte("\n")) {
+			if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+				return errWrite
+			}
+		}
+	} else {
+		if _, errWrite := io.WriteString(w, sectionHeader); errWrite != nil {
+			return errWrite
+		}
+		if _, errWrite := w.Write(payload); errWrite != nil {
+			return errWrite
+		}
+		if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+			return errWrite
+		}
+	}
+
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+	return nil
+}
+
+func writeAPIErrorResponses(w io.Writer, apiResponseErrors []*interfaces.ErrorMessage) error {
+	for i := 0; i < len(apiResponseErrors); i++ {
+		if apiResponseErrors[i] == nil {
+			continue
+		}
+		if _, errWrite := io.WriteString(w, "=== API ERROR RESPONSE ===\n"); errWrite != nil {
+			return errWrite
+		}
+		if _, errWrite := io.WriteString(w, fmt.Sprintf("HTTP Status: %d\n", apiResponseErrors[i].StatusCode)); errWrite != nil {
+			return errWrite
+		}
+		if apiResponseErrors[i].Error != nil {
+			if _, errWrite := io.WriteString(w, apiResponseErrors[i].Error.Error()); errWrite != nil {
+				return errWrite
+			}
+		}
+		if _, errWrite := io.WriteString(w, "\n\n"); errWrite != nil {
+			return errWrite
+		}
+	}
+	return nil
+}
+
+func writeResponseSection(w io.Writer, statusCode int, statusWritten bool, responseHeaders map[string][]string, responseReader io.Reader, decompressErr error, trailingNewline bool) error {
+	if _, errWrite := io.WriteString(w, "=== RESPONSE ===\n"); errWrite != nil {
+		return errWrite
+	}
+	if statusWritten {
+		if _, errWrite := io.WriteString(w, fmt.Sprintf("Status: %d\n", statusCode)); errWrite != nil {
+			return errWrite
+		}
+	}
+
+	if responseHeaders != nil {
+		for key, values := range responseHeaders {
+			for _, value := range values {
+				if _, errWrite := io.WriteString(w, fmt.Sprintf("%s: %s\n", key, value)); errWrite != nil {
+					return errWrite
+				}
+			}
+		}
+	}
+
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if responseReader != nil {
+		if _, errCopy := io.Copy(w, responseReader); errCopy != nil {
+			return errCopy
+		}
+	}
+	if decompressErr != nil {
+		if _, errWrite := io.WriteString(w, fmt.Sprintf("\n[DECOMPRESSION ERROR: %v]", decompressErr)); errWrite != nil {
+			return errWrite
+		}
+	}
+
+	if trailingNewline {
+		if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+			return errWrite
+		}
+	}
+	return nil
+}
+
 // formatLogContent creates the complete log content for non-streaming requests.
 //
 // Parameters:
@@ -648,13 +912,34 @@ func (l *FileRequestLogger) formatRequestInfo(url, method string, headers map[st
 }
 
 // FileStreamingLogWriter implements StreamingLogWriter for file-based streaming logs.
-// It handles asynchronous writing of streaming response chunks to a file.
+// It spools streaming response chunks to a temporary file to avoid retaining large responses in memory.
-// All data is buffered and written in the correct order when Close is called.
+// The final log file is assembled when Close is called.
 type FileStreamingLogWriter struct {
-	// file is the file where log data is written.
+	// logFilePath is the final log file path.
-	file *os.File
+	logFilePath string
 
-	// chunkChan is a channel for receiving response chunks to buffer.
+	// url is the request URL (masked upstream in middleware).
+	url string
+
+	// method is the HTTP method.
+	method string
+
+	// timestamp is captured when the streaming log is initialized.
+	timestamp time.Time
+
+	// requestHeaders stores the request headers.
+	requestHeaders map[string][]string
+
+	// requestBodyPath is a temporary file path holding the request body.
+	requestBodyPath string
+
+	// responseBodyPath is a temporary file path holding the streaming response body.
+	responseBodyPath string
+
+	// responseBodyFile is the temp file where chunks are appended by the async writer.
+	responseBodyFile *os.File
+
+	// chunkChan is a channel for receiving response chunks to spool.
 	chunkChan chan []byte
 
 	// closeChan is a channel for signaling when the writer is closed.
@@ -663,9 +948,6 @@ type FileStreamingLogWriter struct {
 	// errorChan is a channel for reporting errors during writing.
 	errorChan chan error
 
-	// bufferedChunks stores the response chunks in order.
-	bufferedChunks *bytes.Buffer
-
 	// responseStatus stores the HTTP status code.
 	responseStatus int
 
@@ -770,85 +1052,115 @@ func (w *FileStreamingLogWriter) Close() error {
 		close(w.chunkChan)
 	}
 
-	// Wait for async writer to finish buffering chunks
+	// Wait for async writer to finish spooling chunks
 	if w.closeChan != nil {
 		<-w.closeChan
 		w.chunkChan = nil
 	}
 
-	if w.file == nil {
+	select {
+	case errWrite := <-w.errorChan:
+		w.cleanupTempFiles()
+		return errWrite
+	default:
+	}
+
+	if w.logFilePath == "" {
+		w.cleanupTempFiles()
 		return nil
 	}
 
-	// Write all content in the correct order
+	logFile, errOpen := os.OpenFile(w.logFilePath, os.O_CREATE|os.O_WRONLY|os.O_TRUNC, 0644)
-	var content strings.Builder
+	if errOpen != nil {
-
+		w.cleanupTempFiles()
-	// 1. Write API REQUEST section
+		return fmt.Errorf("failed to create log file: %w", errOpen)
-	if len(w.apiRequest) > 0 {
-		if bytes.HasPrefix(w.apiRequest, []byte("=== API REQUEST")) {
-			content.Write(w.apiRequest)
-			if !bytes.HasSuffix(w.apiRequest, []byte("\n")) {
-				content.WriteString("\n")
-			}
-		} else {
-			content.WriteString("=== API REQUEST ===\n")
-			content.Write(w.apiRequest)
-			content.WriteString("\n")
-		}
-		content.WriteString("\n")
 	}
 
-	// 2. Write API RESPONSE section
+	writeErr := w.writeFinalLog(logFile)
-	if len(w.apiResponse) > 0 {
+	if errClose := logFile.Close(); errClose != nil {
-		if bytes.HasPrefix(w.apiResponse, []byte("=== API RESPONSE")) {
+		log.WithError(errClose).Warn("failed to close request log file")
-			content.Write(w.apiResponse)
+		if writeErr == nil {
-			if !bytes.HasSuffix(w.apiResponse, []byte("\n")) {
+			writeErr = errClose
-				content.WriteString("\n")
-			}
-		} else {
-			content.WriteString("=== API RESPONSE ===\n")
-			content.Write(w.apiResponse)
-			content.WriteString("\n")
-		}
-		content.WriteString("\n")
-	}
-
-	// 3. Write RESPONSE section (status, headers, buffered chunks)
-	content.WriteString("=== RESPONSE ===\n")
-	if w.statusWritten {
-		content.WriteString(fmt.Sprintf("Status: %d\n", w.responseStatus))
-	}
-
-	for key, values := range w.responseHeaders {
-		for _, value := range values {
-			content.WriteString(fmt.Sprintf("%s: %s\n", key, value))
 		}
 	}
-	content.WriteString("\n")
 
-	// Write buffered response body chunks
+	w.cleanupTempFiles()
-	if w.bufferedChunks != nil && w.bufferedChunks.Len() > 0 {
+	return writeErr
-		content.Write(w.bufferedChunks.Bytes())
-	}
-
-	// Write the complete content to file
-	if _, err := w.file.WriteString(content.String()); err != nil {
-		_ = w.file.Close()
-		return err
-	}
-
-	return w.file.Close()
 }
 
 // asyncWriter runs in a goroutine to buffer chunks from the channel.
-// It continuously reads chunks from the channel and buffers them for later writing.
+// It continuously reads chunks from the channel and appends them to a temp file for later assembly.
 func (w *FileStreamingLogWriter) asyncWriter() {
 	defer close(w.closeChan)
 
 	for chunk := range w.chunkChan {
-		if w.bufferedChunks != nil {
+		if w.responseBodyFile == nil {
-			w.bufferedChunks.Write(chunk)
+			continue
 		}
+		if _, errWrite := w.responseBodyFile.Write(chunk); errWrite != nil {
+			select {
+			case w.errorChan <- errWrite:
+			default:
+			}
+			if errClose := w.responseBodyFile.Close(); errClose != nil {
+				select {
+				case w.errorChan <- errClose:
+				default:
+				}
+			}
+			w.responseBodyFile = nil
+		}
+	}
+
+	if w.responseBodyFile == nil {
+		return
+	}
+	if errClose := w.responseBodyFile.Close(); errClose != nil {
+		select {
+		case w.errorChan <- errClose:
+		default:
+		}
+	}
+	w.responseBodyFile = nil
+}
+
+func (w *FileStreamingLogWriter) writeFinalLog(logFile *os.File) error {
+	if errWrite := writeRequestInfoWithBody(logFile, w.url, w.method, w.requestHeaders, nil, w.requestBodyPath, w.timestamp); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(logFile, "=== API REQUEST ===\n", "=== API REQUEST", w.apiRequest); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(logFile, "=== API RESPONSE ===\n", "=== API RESPONSE", w.apiResponse); errWrite != nil {
+		return errWrite
+	}
+
+	responseBodyFile, errOpen := os.Open(w.responseBodyPath)
+	if errOpen != nil {
+		return errOpen
+	}
+	defer func() {
+		if errClose := responseBodyFile.Close(); errClose != nil {
+			log.WithError(errClose).Warn("failed to close response body temp file")
+		}
+	}()
+
+	return writeResponseSection(logFile, w.responseStatus, w.statusWritten, w.responseHeaders, responseBodyFile, nil, false)
+}
+
+func (w *FileStreamingLogWriter) cleanupTempFiles() {
+	if w.requestBodyPath != "" {
+		if errRemove := os.Remove(w.requestBodyPath); errRemove != nil {
+			log.WithError(errRemove).Warn("failed to remove request body temp file")
+		}
+		w.requestBodyPath = ""
+	}
+
+	if w.responseBodyPath != "" {
+		if errRemove := os.Remove(w.responseBodyPath); errRemove != nil {
+			log.WithError(errRemove).Warn("failed to remove response body temp file")
+		}
+		w.responseBodyPath = ""
 	}
 }
 

internal/registry/model_definitions.go

@@ -162,6 +162,21 @@ func GetGeminiModels() []*ModelInfo {
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
 			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
 		},
+		{
+			ID:                         "gemini-3-flash-preview",
+			Object:                     "model",
+			Created:                    1765929600,
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-3-flash-preview",
+			Version:                    "3.0",
+			DisplayName:                "Gemini 3 Flash Preview",
+			Description:                "Gemini 3 Flash Preview",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           65536,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}},
+		},
 		{
 			ID:                         "gemini-3-pro-image-preview",
 			Object:                     "model",

internal/runtime/executor/aistudio_executor.go

@@ -325,8 +325,8 @@ func (e *AIStudioExecutor) translateRequest(req cliproxyexecutor.Request, opts c
 	payload = ApplyThinkingMetadata(payload, req.Metadata, req.Model)
 	payload = util.ApplyGemini3ThinkingLevelFromMetadata(req.Model, req.Metadata, payload)
 	payload = util.ApplyDefaultThinkingIfNeeded(req.Model, payload)
-	payload = util.ConvertThinkingLevelToBudget(payload, req.Model)
+	payload = util.ConvertThinkingLevelToBudget(payload, req.Model, true)
-	payload = util.NormalizeGeminiThinkingBudget(req.Model, payload)
+	payload = util.NormalizeGeminiThinkingBudget(req.Model, payload, true)
 	payload = util.StripThinkingConfigIfUnsupported(req.Model, payload)
 	payload = fixGeminiImageAspectRatio(req.Model, payload)
 	payload = applyPayloadConfig(e.cfg, req.Model, payload)

internal/runtime/executor/antigravity_executor.go

@@ -97,6 +97,7 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
 	translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
 	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
 	translated = normalizeAntigravityThinking(req.Model, translated)
+	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
 
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
@@ -191,6 +192,7 @@ func (e *AntigravityExecutor) executeClaudeNonStream(ctx context.Context, auth *
 	translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
 	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
 	translated = normalizeAntigravityThinking(req.Model, translated)
+	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
 
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
@@ -524,6 +526,7 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
 	translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
 	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
 	translated = normalizeAntigravityThinking(req.Model, translated)
+	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
 
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)

internal/translator/antigravity/claude/antigravity_claude_request.go

@@ -211,6 +211,8 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 				tool, _ = sjson.SetRaw(tool, "parametersJsonSchema", inputSchema)
 				tool, _ = sjson.Delete(tool, "strict")
 				tool, _ = sjson.Delete(tool, "input_examples")
+				tool, _ = sjson.Delete(tool, "type")
+				tool, _ = sjson.Delete(tool, "cache_control")
 				toolsJSON, _ = sjson.SetRaw(toolsJSON, "0.functionDeclarations.-1", tool)
 				toolDeclCount++
 			}

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

@@ -39,8 +39,23 @@ 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) && !util.ModelUsesThinkingLevels(modelName) {
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
-		out = util.ApplyReasoningEffortToGeminiCLI(out, re.String())
+		effort := strings.ToLower(strings.TrimSpace(re.String()))
+		if util.IsGemini3Model(modelName) {
+			switch effort {
+			case "none":
+				out, _ = sjson.DeleteBytes(out, "request.generationConfig.thinkingConfig")
+			case "auto":
+				includeThoughts := true
+				out = util.ApplyGeminiCLIThinkingLevel(out, "", &includeThoughts)
+			default:
+				if level, ok := util.ValidateGemini3ThinkingLevel(modelName, effort); ok {
+					out = util.ApplyGeminiCLIThinkingLevel(out, level, nil)
+				}
+			}
+		} else if !util.ModelUsesThinkingLevels(modelName) {
+			out = util.ApplyReasoningEffortToGeminiCLI(out, effort)
+		}
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)

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

@@ -95,7 +95,7 @@ func ConvertClaudeResponseToOpenAIResponses(ctx context.Context, modelName strin
 				}
 			}
 			// response.created
-			created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"instructions":""}}`
+			created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"output":[]}}`
 			created, _ = sjson.Set(created, "sequence_number", nextSeq())
 			created, _ = sjson.Set(created, "response.id", st.ResponseID)
 			created, _ = sjson.Set(created, "response.created_at", st.CreatedAt)
@@ -197,11 +197,11 @@ func ConvertClaudeResponseToOpenAIResponses(ctx context.Context, modelName strin
 			if st.ReasoningActive {
 				if t := d.Get("thinking"); t.Exists() {
 					st.ReasoningBuf.WriteString(t.String())
-					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"text":""}`
+					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"delta":""}`
 					msg, _ = sjson.Set(msg, "sequence_number", nextSeq())
 					msg, _ = sjson.Set(msg, "item_id", st.ReasoningItemID)
 					msg, _ = sjson.Set(msg, "output_index", st.ReasoningIndex)
-					msg, _ = sjson.Set(msg, "text", t.String())
+					msg, _ = sjson.Set(msg, "delta", t.String())
 					out = append(out, emitEvent("response.reasoning_summary_text.delta", msg))
 				}
 			}

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

@@ -134,6 +134,8 @@ func ConvertClaudeRequestToCLI(modelName string, inputRawJSON []byte, _ bool) []
 				tool, _ = sjson.SetRaw(tool, "parametersJsonSchema", inputSchema)
 				tool, _ = sjson.Delete(tool, "strict")
 				tool, _ = sjson.Delete(tool, "input_examples")
+				tool, _ = sjson.Delete(tool, "type")
+				tool, _ = sjson.Delete(tool, "cache_control")
 				var toolDeclaration any
 				if err := json.Unmarshal([]byte(tool), &toolDeclaration); err == nil {
 					tools[0].FunctionDeclarations = append(tools[0].FunctionDeclarations, toolDeclaration)

internal/translator/gemini/claude/gemini_claude_request.go

@@ -127,6 +127,8 @@ func ConvertClaudeRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 				tool, _ = sjson.SetRaw(tool, "parametersJsonSchema", inputSchema)
 				tool, _ = sjson.Delete(tool, "strict")
 				tool, _ = sjson.Delete(tool, "input_examples")
+				tool, _ = sjson.Delete(tool, "type")
+				tool, _ = sjson.Delete(tool, "cache_control")
 				var toolDeclaration any
 				if err := json.Unmarshal([]byte(tool), &toolDeclaration); err == nil {
 					tools[0].FunctionDeclarations = append(tools[0].FunctionDeclarations, toolDeclaration)

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

@@ -37,12 +37,28 @@ 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
+	// Only apply numeric budgets for models that use budgets (not discrete levels) to avoid
-	// incorrectly applying thinkingBudget for level-based models like gpt-5.
+	// incorrectly applying thinkingBudget for level-based models like gpt-5. Gemini 3 models
+	// use thinkingLevel/includeThoughts instead.
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
 	hasOfficialThinking := re.Exists()
-	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
-		out = util.ApplyReasoningEffortToGemini(out, re.String())
+		effort := strings.ToLower(strings.TrimSpace(re.String()))
+		if util.IsGemini3Model(modelName) {
+			switch effort {
+			case "none":
+				out, _ = sjson.DeleteBytes(out, "generationConfig.thinkingConfig")
+			case "auto":
+				includeThoughts := true
+				out = util.ApplyGeminiThinkingLevel(out, "", &includeThoughts)
+			default:
+				if level, ok := util.ValidateGemini3ThinkingLevel(modelName, effort); ok {
+					out = util.ApplyGeminiThinkingLevel(out, level, nil)
+				}
+			}
+		} else if !util.ModelUsesThinkingLevels(modelName) {
+			out = util.ApplyReasoningEffortToGemini(out, effort)
+		}
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)

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

@@ -117,7 +117,7 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 			st.CreatedAt = time.Now().Unix()
 		}
 
-		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null}}`
+		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"output":[]}}`
 		created, _ = sjson.Set(created, "sequence_number", nextSeq())
 		created, _ = sjson.Set(created, "response.id", st.ResponseID)
 		created, _ = sjson.Set(created, "response.created_at", st.CreatedAt)
@@ -160,11 +160,11 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 				}
 				if t := part.Get("text"); t.Exists() && t.String() != "" {
 					st.ReasoningBuf.WriteString(t.String())
-					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"text":""}`
+					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"delta":""}`
 					msg, _ = sjson.Set(msg, "sequence_number", nextSeq())
 					msg, _ = sjson.Set(msg, "item_id", st.ReasoningItemID)
 					msg, _ = sjson.Set(msg, "output_index", st.ReasoningIndex)
-					msg, _ = sjson.Set(msg, "text", t.String())
+					msg, _ = sjson.Set(msg, "delta", t.String())
 					out = append(out, emitEvent("response.reasoning_summary_text.delta", msg))
 				}
 				return true

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

@@ -143,7 +143,7 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 		st.ReasoningTokens = 0
 		st.UsageSeen = false
 		// response.created
-		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null}}`
+		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"output":[]}}`
 		created, _ = sjson.Set(created, "sequence_number", nextSeq())
 		created, _ = sjson.Set(created, "response.id", st.ResponseID)
 		created, _ = sjson.Set(created, "response.created_at", st.Created)
@@ -216,11 +216,11 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 					}
 					// Append incremental text to reasoning buffer
 					st.ReasoningBuf.WriteString(rc.String())
-					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"text":""}`
+					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"delta":""}`
 					msg, _ = sjson.Set(msg, "sequence_number", nextSeq())
 					msg, _ = sjson.Set(msg, "item_id", st.ReasoningID)
 					msg, _ = sjson.Set(msg, "output_index", st.ReasoningIndex)
-					msg, _ = sjson.Set(msg, "text", rc.String())
+					msg, _ = sjson.Set(msg, "delta", rc.String())
 					out = append(out, emitRespEvent("response.reasoning_summary_text.delta", msg))
 				}
 

internal/util/gemini_schema.go

@@ -296,6 +296,7 @@ func flattenTypeArrays(jsonStr string) string {
 func removeUnsupportedKeywords(jsonStr string) string {
 	keywords := append(unsupportedConstraints,
 		"$schema", "$defs", "definitions", "const", "$ref", "additionalProperties",
+		"propertyNames", // Gemini doesn't support property name validation
 	)
 	for _, key := range keywords {
 		for _, p := range findPaths(jsonStr, key) {

internal/util/gemini_schema_test.go

@@ -596,6 +596,71 @@ func TestCleanJSONSchemaForGemini_MultipleNonNullTypes(t *testing.T) {
 	}
 }
 
+func TestCleanJSONSchemaForGemini_PropertyNamesRemoval(t *testing.T) {
+	// propertyNames is used to validate object property names (e.g., must match a pattern)
+	// Gemini doesn't support this keyword and will reject requests containing it
+	input := `{
+		"type": "object",
+		"properties": {
+			"metadata": {
+				"type": "object",
+				"propertyNames": {
+					"pattern": "^[a-zA-Z_][a-zA-Z0-9_]*$"
+				},
+				"additionalProperties": {
+					"type": "string"
+				}
+			}
+		}
+	}`
+
+	expected := `{
+		"type": "object",
+		"properties": {
+			"metadata": {
+				"type": "object"
+			}
+		}
+	}`
+
+	result := CleanJSONSchemaForGemini(input)
+	compareJSON(t, expected, result)
+
+	// Verify propertyNames is completely removed
+	if strings.Contains(result, "propertyNames") {
+		t.Errorf("propertyNames keyword should be removed, got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForGemini_PropertyNamesRemoval_Nested(t *testing.T) {
+	// Test deeply nested propertyNames (as seen in real Claude tool schemas)
+	input := `{
+		"type": "object",
+		"properties": {
+			"items": {
+				"type": "array",
+				"items": {
+					"type": "object",
+					"properties": {
+						"config": {
+							"type": "object",
+							"propertyNames": {
+								"type": "string"
+							}
+						}
+					}
+				}
+			}
+		}
+	}`
+
+	result := CleanJSONSchemaForGemini(input)
+
+	if strings.Contains(result, "propertyNames") {
+		t.Errorf("Nested propertyNames should be removed, got: %s", result)
+	}
+}
+
 func compareJSON(t *testing.T, expectedJSON, actualJSON string) {
 	var expMap, actMap map[string]interface{}
 	errExp := json.Unmarshal([]byte(expectedJSON), &expMap)

internal/util/gemini_thinking.go

@@ -136,6 +136,12 @@ func ApplyGeminiThinkingLevel(body []byte, level string, includeThoughts *bool)
 			updated = rewritten
 		}
 	}
+	if it := gjson.GetBytes(body, "generationConfig.thinkingConfig.include_thoughts"); it.Exists() {
+		updated, _ = sjson.DeleteBytes(updated, "generationConfig.thinkingConfig.include_thoughts")
+	}
+	if tb := gjson.GetBytes(body, "generationConfig.thinkingConfig.thinkingBudget"); tb.Exists() {
+		updated, _ = sjson.DeleteBytes(updated, "generationConfig.thinkingConfig.thinkingBudget")
+	}
 	return updated
 }
 
@@ -167,6 +173,12 @@ func ApplyGeminiCLIThinkingLevel(body []byte, level string, includeThoughts *boo
 			updated = rewritten
 		}
 	}
+	if it := gjson.GetBytes(body, "request.generationConfig.thinkingConfig.include_thoughts"); it.Exists() {
+		updated, _ = sjson.DeleteBytes(updated, "request.generationConfig.thinkingConfig.include_thoughts")
+	}
+	if tb := gjson.GetBytes(body, "request.generationConfig.thinkingConfig.thinkingBudget"); tb.Exists() {
+		updated, _ = sjson.DeleteBytes(updated, "request.generationConfig.thinkingConfig.thinkingBudget")
+	}
 	return updated
 }
 
@@ -352,8 +364,9 @@ func StripThinkingConfigIfUnsupported(model string, body []byte) []byte {
 
 // NormalizeGeminiThinkingBudget normalizes the thinkingBudget value in a standard Gemini
 // request body (generationConfig.thinkingConfig.thinkingBudget path).
-// For Gemini 3 models, converts thinkingBudget to thinkingLevel per Google's documentation.
+// For Gemini 3 models, converts thinkingBudget to thinkingLevel per Google's documentation,
-func NormalizeGeminiThinkingBudget(model string, body []byte) []byte {
+// unless skipGemini3Check is provided and true.
+func NormalizeGeminiThinkingBudget(model string, body []byte, skipGemini3Check ...bool) []byte {
 	const budgetPath = "generationConfig.thinkingConfig.thinkingBudget"
 	const levelPath = "generationConfig.thinkingConfig.thinkingLevel"
 
@@ -363,7 +376,8 @@ func NormalizeGeminiThinkingBudget(model string, body []byte) []byte {
 	}
 
 	// For Gemini 3 models, convert thinkingBudget to thinkingLevel
-	if IsGemini3Model(model) {
+	skipGemini3 := len(skipGemini3Check) > 0 && skipGemini3Check[0]
+	if IsGemini3Model(model) && !skipGemini3 {
 		if level, ok := ThinkingBudgetToGemini3Level(model, int(budget.Int())); ok {
 			updated, _ := sjson.SetBytes(body, levelPath, level)
 			updated, _ = sjson.DeleteBytes(updated, budgetPath)
@@ -382,8 +396,9 @@ func NormalizeGeminiThinkingBudget(model string, body []byte) []byte {
 
 // NormalizeGeminiCLIThinkingBudget normalizes the thinkingBudget value in a Gemini CLI
 // request body (request.generationConfig.thinkingConfig.thinkingBudget path).
-// For Gemini 3 models, converts thinkingBudget to thinkingLevel per Google's documentation.
+// For Gemini 3 models, converts thinkingBudget to thinkingLevel per Google's documentation,
-func NormalizeGeminiCLIThinkingBudget(model string, body []byte) []byte {
+// unless skipGemini3Check is provided and true.
+func NormalizeGeminiCLIThinkingBudget(model string, body []byte, skipGemini3Check ...bool) []byte {
 	const budgetPath = "request.generationConfig.thinkingConfig.thinkingBudget"
 	const levelPath = "request.generationConfig.thinkingConfig.thinkingLevel"
 
@@ -393,7 +408,8 @@ func NormalizeGeminiCLIThinkingBudget(model string, body []byte) []byte {
 	}
 
 	// For Gemini 3 models, convert thinkingBudget to thinkingLevel
-	if IsGemini3Model(model) {
+	skipGemini3 := len(skipGemini3Check) > 0 && skipGemini3Check[0]
+	if IsGemini3Model(model) && !skipGemini3 {
 		if level, ok := ThinkingBudgetToGemini3Level(model, int(budget.Int())); ok {
 			updated, _ := sjson.SetBytes(body, levelPath, level)
 			updated, _ = sjson.DeleteBytes(updated, budgetPath)
@@ -477,7 +493,7 @@ func ApplyReasoningEffortToGeminiCLI(body []byte, effort string) []byte {
 
 // ConvertThinkingLevelToBudget checks for "generationConfig.thinkingConfig.thinkingLevel"
 // and converts it to "thinkingBudget" for Gemini 2.5 models.
-// For Gemini 3 models, preserves thinkingLevel as-is (does not convert).
+// For Gemini 3 models, preserves thinkingLevel unless skipGemini3Check is provided and true.
 // Mappings for Gemini 2.5:
 //   - "high" -> 32768
 //   - "medium" -> 8192
@@ -485,43 +501,31 @@ func ApplyReasoningEffortToGeminiCLI(body []byte, effort string) []byte {
 //   - "minimal" -> 512
 //
 // It removes "thinkingLevel" after conversion (for Gemini 2.5 only).
-func ConvertThinkingLevelToBudget(body []byte, model string) []byte {
+func ConvertThinkingLevelToBudget(body []byte, model string, skipGemini3Check ...bool) []byte {
 	levelPath := "generationConfig.thinkingConfig.thinkingLevel"
 	res := gjson.GetBytes(body, levelPath)
 	if !res.Exists() {
 		return body
 	}
 
-	// For Gemini 3 models, preserve thinkingLevel - don't convert to budget
+	// For Gemini 3 models, preserve thinkingLevel unless explicitly skipped
-	if IsGemini3Model(model) {
+	skipGemini3 := len(skipGemini3Check) > 0 && skipGemini3Check[0]
+	if IsGemini3Model(model) && !skipGemini3 {
 		return body
 	}
 
-	level := strings.ToLower(res.String())
+	budget, ok := ThinkingLevelToBudget(res.String())
-	var budget int
+	if !ok {
-	switch level {
-	case "high":
-		budget = 32768
-	case "medium":
-		budget = 8192
-	case "low":
-		budget = 1024
-	case "minimal":
-		budget = 512
-	default:
-		// Unknown level - remove it and let the API use defaults
 		updated, _ := sjson.DeleteBytes(body, levelPath)
 		return updated
 	}
 
-	// Set budget
 	budgetPath := "generationConfig.thinkingConfig.thinkingBudget"
 	updated, err := sjson.SetBytes(body, budgetPath, budget)
 	if err != nil {
 		return body
 	}
 
-	// Remove level
 	updated, err = sjson.DeleteBytes(updated, levelPath)
 	if err != nil {
 		return body
@@ -544,31 +548,18 @@ func ConvertThinkingLevelToBudgetCLI(body []byte, model string) []byte {
 		return body
 	}
 
-	level := strings.ToLower(res.String())
+	budget, ok := ThinkingLevelToBudget(res.String())
-	var budget int
+	if !ok {
-	switch level {
-	case "high":
-		budget = 32768
-	case "medium":
-		budget = 8192
-	case "low":
-		budget = 1024
-	case "minimal":
-		budget = 512
-	default:
-		// Unknown level - remove it and let the API use defaults
 		updated, _ := sjson.DeleteBytes(body, levelPath)
 		return updated
 	}
 
-	// Set budget
 	budgetPath := "request.generationConfig.thinkingConfig.thinkingBudget"
 	updated, err := sjson.SetBytes(body, budgetPath, budget)
 	if err != nil {
 		return body
 	}
 
-	// Remove level
 	updated, err = sjson.DeleteBytes(updated, levelPath)
 	if err != nil {
 		return body

internal/util/thinking.go

@@ -160,6 +160,34 @@ func ThinkingEffortToBudget(model, effort string) (int, bool) {
 	}
 }
 
+// ThinkingLevelToBudget maps a Gemini thinkingLevel to a numeric thinking budget (tokens).
+//
+// Mappings:
+//   - "minimal" -> 512
+//   - "low"     -> 1024
+//   - "medium"  -> 8192
+//   - "high"    -> 32768
+//
+// Returns false when the level is empty or unsupported.
+func ThinkingLevelToBudget(level string) (int, bool) {
+	if level == "" {
+		return 0, false
+	}
+	normalized := strings.ToLower(strings.TrimSpace(level))
+	switch normalized {
+	case "minimal":
+		return 512, true
+	case "low":
+		return 1024, true
+	case "medium":
+		return 8192, true
+	case "high":
+		return 32768, true
+	default:
+		return 0, false
+	}
+}
+
 // ThinkingBudgetToEffort maps a numeric thinking budget (tokens)
 // to a reasoning effort level for level-based models.
 //

sdk/api/options.go

@@ -0,0 +1,46 @@
+// Package api exposes server option helpers for embedding CLIProxyAPI.
+//
+// It wraps internal server option types so external projects can configure the embedded
+// HTTP server without importing internal packages.
+package api
+
+import (
+	"time"
+
+	"github.com/gin-gonic/gin"
+	internalapi "github.com/router-for-me/CLIProxyAPI/v6/internal/api"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/api/handlers"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/logging"
+)
+
+// ServerOption customises HTTP server construction.
+type ServerOption = internalapi.ServerOption
+
+// WithMiddleware appends additional Gin middleware during server construction.
+func WithMiddleware(mw ...gin.HandlerFunc) ServerOption { return internalapi.WithMiddleware(mw...) }
+
+// WithEngineConfigurator allows callers to mutate the Gin engine prior to middleware setup.
+func WithEngineConfigurator(fn func(*gin.Engine)) ServerOption {
+	return internalapi.WithEngineConfigurator(fn)
+}
+
+// WithRouterConfigurator appends a callback after default routes are registered.
+func WithRouterConfigurator(fn func(*gin.Engine, *handlers.BaseAPIHandler, *config.Config)) ServerOption {
+	return internalapi.WithRouterConfigurator(fn)
+}
+
+// WithLocalManagementPassword stores a runtime-only management password accepted for localhost requests.
+func WithLocalManagementPassword(password string) ServerOption {
+	return internalapi.WithLocalManagementPassword(password)
+}
+
+// WithKeepAliveEndpoint enables a keep-alive endpoint with the provided timeout and callback.
+func WithKeepAliveEndpoint(timeout time.Duration, onTimeout func()) ServerOption {
+	return internalapi.WithKeepAliveEndpoint(timeout, onTimeout)
+}
+
+// WithRequestLoggerFactory customises request logger creation.
+func WithRequestLoggerFactory(factory func(*config.Config, string) logging.RequestLogger) ServerOption {
+	return internalapi.WithRequestLoggerFactory(factory)
+}

sdk/auth/filestore.go

@@ -72,7 +72,9 @@ func (s *FileTokenStore) Save(ctx context.Context, auth *cliproxyauth.Auth) (str
 			return "", fmt.Errorf("auth filestore: marshal metadata failed: %w", errMarshal)
 		}
 		if existing, errRead := os.ReadFile(path); errRead == nil {
-			if jsonEqual(existing, raw) {
+			// Use metadataEqualIgnoringTimestamps to skip writes when only timestamp fields change.
+			// This prevents the token refresh loop caused by timestamp/expired/expires_in changes.
+			if metadataEqualIgnoringTimestamps(existing, raw) {
 				return path, nil
 			}
 		} else if errRead != nil && !os.IsNotExist(errRead) {
@@ -264,6 +266,8 @@ func (s *FileTokenStore) baseDirSnapshot() string {
 	return s.baseDir
 }
 
+// DEPRECATED: Use metadataEqualIgnoringTimestamps for comparing auth metadata.
+// This function is kept for backward compatibility but can cause refresh loops.
 func jsonEqual(a, b []byte) bool {
 	var objA any
 	var objB any
@@ -276,6 +280,32 @@ func jsonEqual(a, b []byte) bool {
 	return deepEqualJSON(objA, objB)
 }
 
+// metadataEqualIgnoringTimestamps compares two metadata JSON blobs,
+// ignoring fields that change on every refresh but don't affect functionality.
+// This prevents unnecessary file writes that would trigger watcher events and
+// create refresh loops.
+func metadataEqualIgnoringTimestamps(a, b []byte) bool {
+	var objA, objB map[string]any
+	if err := json.Unmarshal(a, &objA); err != nil {
+		return false
+	}
+	if err := json.Unmarshal(b, &objB); err != nil {
+		return false
+	}
+
+	// Fields to ignore: these change on every refresh but don't affect authentication logic.
+	// - timestamp, expired, expires_in, last_refresh: time-related fields that change on refresh
+	// - access_token: Google OAuth returns a new access_token on each refresh, this is expected
+	//   and shouldn't trigger file writes (the new token will be fetched again when needed)
+	ignoredFields := []string{"timestamp", "expired", "expires_in", "last_refresh", "access_token"}
+	for _, field := range ignoredFields {
+		delete(objA, field)
+		delete(objB, field)
+	}
+
+	return deepEqualJSON(objA, objB)
+}
+
 func deepEqualJSON(a, b any) bool {
 	switch valA := a.(type) {
 	case map[string]any:

sdk/cliproxy/builder.go

@@ -7,10 +7,10 @@ import (
 	"fmt"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/api"
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	sdkaccess "github.com/router-for-me/CLIProxyAPI/v6/sdk/access"
 	sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
 	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
 )
 
 // Builder constructs a Service instance with customizable providers.

sdk/cliproxy/providers.go

@@ -3,8 +3,8 @@ package cliproxy
 import (
 	"context"
 
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/watcher"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
 )
 
 // NewFileTokenClientProvider returns the default token-backed client loader.

sdk/cliproxy/service.go

@@ -13,7 +13,6 @@ import (
 	"time"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/api"
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"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/usage"
@@ -23,6 +22,7 @@ import (
 	sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
 	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	"github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/usage"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
 	log "github.com/sirupsen/logrus"
 )
 

sdk/cliproxy/types.go

@@ -6,9 +6,9 @@ package cliproxy
 import (
 	"context"
 
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/watcher"
 	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
 )
 
 // TokenClientProvider loads clients backed by stored authentication tokens.

sdk/cliproxy/watcher.go

@@ -3,9 +3,9 @@ package cliproxy
 import (
 	"context"
 
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/watcher"
 	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
+	"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
 )
 
 func defaultWatcherFactory(configPath, authDir string, reload func(*config.Config)) (*WatcherWrapper, error) {

sdk/config/config.go

@@ -1,87 +1,59 @@
-// Package config provides configuration management for the CLI Proxy API server.
+// Package config provides the public SDK configuration API.
-// It handles loading and parsing YAML configuration files, and provides structured
+//
-// access to application settings including server port, authentication directory,
+// It re-exports the server configuration types and helpers so external projects can
-// debug settings, proxy configuration, and API keys.
+// embed CLIProxyAPI without importing internal packages.
 package config
 
-// SDKConfig represents the application's configuration, loaded from a YAML file.
+import internalconfig "github.com/router-for-me/CLIProxyAPI/v6/internal/config"
-type SDKConfig struct {
-	// ProxyURL is the URL of an optional proxy server to use for outbound requests.
-	ProxyURL string `yaml:"proxy-url" json:"proxy-url"`
 
-	// ForceModelPrefix requires explicit model prefixes (e.g., "teamA/gemini-3-pro-preview")
+type SDKConfig = internalconfig.SDKConfig
-	// to target prefixed credentials. When false, unprefixed model requests may use prefixed
+type AccessConfig = internalconfig.AccessConfig
-	// credentials as well.
+type AccessProvider = internalconfig.AccessProvider
-	ForceModelPrefix bool `yaml:"force-model-prefix" json:"force-model-prefix"`
 
-	// RequestLog enables or disables detailed request logging functionality.
+type Config = internalconfig.Config
-	RequestLog bool `yaml:"request-log" json:"request-log"`
 
-	// APIKeys is a list of keys for authenticating clients to this proxy server.
+type TLSConfig = internalconfig.TLSConfig
-	APIKeys []string `yaml:"api-keys" json:"api-keys"`
+type RemoteManagement = internalconfig.RemoteManagement
+type AmpCode = internalconfig.AmpCode
+type PayloadConfig = internalconfig.PayloadConfig
+type PayloadRule = internalconfig.PayloadRule
+type PayloadModelRule = internalconfig.PayloadModelRule
 
-	// Access holds request authentication provider configuration.
+type GeminiKey = internalconfig.GeminiKey
-	Access AccessConfig `yaml:"auth,omitempty" json:"auth,omitempty"`
+type CodexKey = internalconfig.CodexKey
-}
+type ClaudeKey = internalconfig.ClaudeKey
+type VertexCompatKey = internalconfig.VertexCompatKey
+type VertexCompatModel = internalconfig.VertexCompatModel
+type OpenAICompatibility = internalconfig.OpenAICompatibility
+type OpenAICompatibilityAPIKey = internalconfig.OpenAICompatibilityAPIKey
+type OpenAICompatibilityModel = internalconfig.OpenAICompatibilityModel
 
-// AccessConfig groups request authentication providers.
+type TLS = internalconfig.TLSConfig
-type AccessConfig struct {
-	// Providers lists configured authentication providers.
-	Providers []AccessProvider `yaml:"providers,omitempty" json:"providers,omitempty"`
-}
-
-// AccessProvider describes a request authentication provider entry.
-type AccessProvider struct {
-	// Name is the instance identifier for the provider.
-	Name string `yaml:"name" json:"name"`
-
-	// Type selects the provider implementation registered via the SDK.
-	Type string `yaml:"type" json:"type"`
-
-	// SDK optionally names a third-party SDK module providing this provider.
-	SDK string `yaml:"sdk,omitempty" json:"sdk,omitempty"`
-
-	// APIKeys lists inline keys for providers that require them.
-	APIKeys []string `yaml:"api-keys,omitempty" json:"api-keys,omitempty"`
-
-	// Config passes provider-specific options to the implementation.
-	Config map[string]any `yaml:"config,omitempty" json:"config,omitempty"`
-}
 
 const (
-	// AccessProviderTypeConfigAPIKey is the built-in provider validating inline API keys.
+	AccessProviderTypeConfigAPIKey = internalconfig.AccessProviderTypeConfigAPIKey
-	AccessProviderTypeConfigAPIKey = "config-api-key"
+	DefaultAccessProviderName      = internalconfig.DefaultAccessProviderName
-
+	DefaultPanelGitHubRepository   = internalconfig.DefaultPanelGitHubRepository
-	// DefaultAccessProviderName is applied when no provider name is supplied.
-	DefaultAccessProviderName = "config-inline"
 )
 
-// ConfigAPIKeyProvider returns the first inline API key provider if present.
+func MakeInlineAPIKeyProvider(keys []string) *AccessProvider {
-func (c *SDKConfig) ConfigAPIKeyProvider() *AccessProvider {
+	return internalconfig.MakeInlineAPIKeyProvider(keys)
-	if c == nil {
-		return nil
-	}
-	for i := range c.Access.Providers {
-		if c.Access.Providers[i].Type == AccessProviderTypeConfigAPIKey {
-			if c.Access.Providers[i].Name == "" {
-				c.Access.Providers[i].Name = DefaultAccessProviderName
-			}
-			return &c.Access.Providers[i]
-		}
-	}
-	return nil
 }
 
-// MakeInlineAPIKeyProvider constructs an inline API key provider configuration.
+func LoadConfig(configFile string) (*Config, error) { return internalconfig.LoadConfig(configFile) }
-// It returns nil when no keys are supplied.
+
-func MakeInlineAPIKeyProvider(keys []string) *AccessProvider {
+func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
-	if len(keys) == 0 {
+	return internalconfig.LoadConfigOptional(configFile, optional)
-		return nil
+}
-	}
+
-	provider := &AccessProvider{
+func SaveConfigPreserveComments(configFile string, cfg *Config) error {
-		Name:    DefaultAccessProviderName,
+	return internalconfig.SaveConfigPreserveComments(configFile, cfg)
-		Type:    AccessProviderTypeConfigAPIKey,
+}
-		APIKeys: append([]string(nil), keys...),
+
-	}
+func SaveConfigPreserveCommentsUpdateNestedScalar(configFile string, path []string, value string) error {
-	return provider
+	return internalconfig.SaveConfigPreserveCommentsUpdateNestedScalar(configFile, path, value)
+}
+
+func NormalizeCommentIndentation(data []byte) []byte {
+	return internalconfig.NormalizeCommentIndentation(data)
 }

sdk/logging/request_logger.go

@@ -0,0 +1,18 @@
+// Package logging re-exports request logging primitives for SDK consumers.
+package logging
+
+import internallogging "github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
+
+// RequestLogger defines the interface for logging HTTP requests and responses.
+type RequestLogger = internallogging.RequestLogger
+
+// StreamingLogWriter handles real-time logging of streaming response chunks.
+type StreamingLogWriter = internallogging.StreamingLogWriter
+
+// FileRequestLogger implements RequestLogger using file-based storage.
+type FileRequestLogger = internallogging.FileRequestLogger
+
+// NewFileRequestLogger creates a new file-based request logger.
+func NewFileRequestLogger(enabled bool, logsDir string, configDir string) *FileRequestLogger {
+	return internallogging.NewFileRequestLogger(enabled, logsDir, configDir)
+}