feat: add DisableCooling configuration to manage quota cooldown behavior

cmd/server/main.go

@@ -27,6 +27,7 @@ import (
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/usage"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	sdkAuth "github.com/router-for-me/CLIProxyAPI/v6/sdk/auth"
+	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	log "github.com/sirupsen/logrus"
 )
 
@@ -377,6 +378,7 @@ func main() {
 		}
 	}
 	usage.SetStatisticsEnabled(cfg.UsageStatisticsEnabled)
+	coreauth.SetQuotaCooldownDisabled(cfg.DisableCooling)
 
 	if err = logging.ConfigureLogOutput(cfg.LoggingToFile); err != nil {
 		log.Fatalf("failed to configure log output: %v", err)

internal/api/server.go

@@ -233,6 +233,7 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
 	s.oldConfigYaml, _ = yaml.Marshal(cfg)
 	s.applyAccessConfig(nil, cfg)
 	managementasset.SetCurrentConfig(cfg)
+	auth.SetQuotaCooldownDisabled(cfg.DisableCooling)
 	// Initialize management handler
 	s.mgmt = managementHandlers.NewHandler(cfg, configFilePath, authManager)
 	if optionState.localPassword != "" {
@@ -716,6 +717,15 @@ func (s *Server) UpdateClients(cfg *config.Config) {
 		}
 	}
 
+	if oldCfg == nil || oldCfg.DisableCooling != cfg.DisableCooling {
+		auth.SetQuotaCooldownDisabled(cfg.DisableCooling)
+		if oldCfg != nil {
+			log.Debugf("disable_cooling updated from %t to %t", oldCfg.DisableCooling, cfg.DisableCooling)
+		} else {
+			log.Debugf("disable_cooling toggled to %t", cfg.DisableCooling)
+		}
+	}
+
 	// Update log level dynamically when debug flag changes
 	if oldCfg == nil || oldCfg.Debug != cfg.Debug {
 		util.SetLogLevel(cfg)

internal/config/config.go

@@ -34,6 +34,9 @@ type Config struct {
 	// UsageStatisticsEnabled toggles in-memory usage aggregation; when false, usage data is discarded.
 	UsageStatisticsEnabled bool `yaml:"usage-statistics-enabled" json:"usage-statistics-enabled"`
 
+	// DisableCooling disables quota cooldown scheduling when true.
+	DisableCooling bool `yaml:"disable-cooling" json:"disable-cooling"`
+
 	// QuotaExceeded defines the behavior when a quota is exceeded.
 	QuotaExceeded QuotaExceeded `yaml:"quota-exceeded" json:"quota-exceeded"`
 
@@ -183,6 +186,7 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	// Set defaults before unmarshal so that absent keys keep defaults.
 	cfg.LoggingToFile = false
 	cfg.UsageStatisticsEnabled = false
+	cfg.DisableCooling = false
 	if err = yaml.Unmarshal(data, &cfg); err != nil {
 		if optional {
 			// In cloud deploy mode, if YAML parsing fails, return empty config instead of error.

internal/watcher/watcher.go

@@ -1192,6 +1192,9 @@ func buildConfigChangeDetails(oldCfg, newCfg *config.Config) []string {
 	if oldCfg.UsageStatisticsEnabled != newCfg.UsageStatisticsEnabled {
 		changes = append(changes, fmt.Sprintf("usage-statistics-enabled: %t -> %t", oldCfg.UsageStatisticsEnabled, newCfg.UsageStatisticsEnabled))
 	}
+	if oldCfg.DisableCooling != newCfg.DisableCooling {
+		changes = append(changes, fmt.Sprintf("disable-cooling: %t -> %t", oldCfg.DisableCooling, newCfg.DisableCooling))
+	}
 	if oldCfg.RequestLog != newCfg.RequestLog {
 		changes = append(changes, fmt.Sprintf("request-log: %t -> %t", oldCfg.RequestLog, newCfg.RequestLog))
 	}

sdk/cliproxy/auth/manager.go

@@ -8,6 +8,7 @@ import (
 	"strconv"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/google/uuid"
@@ -44,6 +45,13 @@ const (
 	quotaBackoffMax       = 30 * time.Minute
 )
 
+var quotaCooldownDisabled atomic.Bool
+
+// SetQuotaCooldownDisabled toggles quota cooldown scheduling globally.
+func SetQuotaCooldownDisabled(disable bool) {
+	quotaCooldownDisabled.Store(disable)
+}
+
 // Result captures execution outcome used to adjust auth state.
 type Result struct {
 	// AuthID references the auth that produced this result.
@@ -535,7 +543,10 @@ func (m *Manager) MarkResult(ctx context.Context, result Result) {
 					shouldSuspendModel = true
 				case 429:
 					cooldown, nextLevel := nextQuotaCooldown(state.Quota.BackoffLevel)
-					next := now.Add(cooldown)
+					var next time.Time
+					if cooldown > 0 {
+						next = now.Add(cooldown)
+					}
 					state.NextRetryAfter = next
 					state.Quota = QuotaState{
 						Exceeded:      true,
@@ -750,9 +761,13 @@ func applyAuthFailureState(auth *Auth, resultErr *Error, now time.Time) {
 		auth.Quota.Exceeded = true
 		auth.Quota.Reason = "quota"
 		cooldown, nextLevel := nextQuotaCooldown(auth.Quota.BackoffLevel)
-		auth.Quota.NextRecoverAt = now.Add(cooldown)
+		var next time.Time
+		if cooldown > 0 {
+			next = now.Add(cooldown)
+		}
+		auth.Quota.NextRecoverAt = next
 		auth.Quota.BackoffLevel = nextLevel
-		auth.NextRetryAfter = auth.Quota.NextRecoverAt
+		auth.NextRetryAfter = next
 	case 408, 500, 502, 503, 504:
 		auth.StatusMessage = "transient upstream error"
 		auth.NextRetryAfter = now.Add(1 * time.Minute)
@@ -768,6 +783,9 @@ func nextQuotaCooldown(prevLevel int) (time.Duration, int) {
 	if prevLevel < 0 {
 		prevLevel = 0
 	}
+	if quotaCooldownDisabled.Load() {
+		return 0, prevLevel
+	}
 	cooldown := quotaBackoffBase * time.Duration(1<<prevLevel)
 	if cooldown < quotaBackoffBase {
 		cooldown = quotaBackoffBase