Merge remote-tracking branch 'upstream/main' into upstream-sync/20260503-0612

Author: ccs-upstream-sync[bot]

README.md

@@ -212,6 +212,10 @@ Never stop coding. Smart routing to FREE & low-cost AI models with automatic fal
 
 OmniRoute is an AI gateway for multi-provider LLMs: an OpenAI-compatible endpoint with smart routing, load balancing, retries, and fallbacks. Add policies, rate limits, caching, and observability for reliable, cost-aware inference.
 
+### [Playful Proxy API Panel (PPAP)](https://github.com/daishuge/playful-proxy-api-panel)
+
+A public CLIProxyAPI-compatible fork and bundled management panel. It keeps upstream-style usage while restoring built-in usage statistics, adding cache hit rate, first-byte latency, TPS tracking, and Docker-oriented self-hosted installation docs.
+
 > [!NOTE]  
 > If you have developed a port of CLIProxyAPI or a project inspired by it, please open a PR to add it to this list.
 

README_CN.md

@@ -208,6 +208,10 @@ Shadow AI 是一款专为受限环境设计的 AI 辅助工具。提供无窗口
 
 OmniRoute 是一个面向多供应商大语言模型的 AI 网关：它提供兼容 OpenAI 的端点，具备智能路由、负载均衡、重试及回退机制。通过添加策略、速率限制、缓存和可观测性，确保推理过程既可靠又具备成本意识。
 
+### [Playful Proxy API Panel (PPAP)](https://github.com/daishuge/playful-proxy-api-panel)
+
+一个公开的 CLIProxyAPI 兼容二开版本和配套管理面板，尽量保持与上游一致的使用方式，同时恢复内置使用量统计，并补充缓存命中率、首字响应时间、TPS 记录和面向 Docker 自托管的安装说明。
+
 > [!NOTE]  
 > 如果你开发了 CLIProxyAPI 的移植或衍生项目，请提交 PR 将其添加到此列表中。
 

README_JA.md

@@ -207,6 +207,10 @@ CLIProxyAPIに触発されたNext.js実装。インストールと使用が簡
 
 OmniRouteはマルチプロバイダーLLM向けのAIゲートウェイです：スマートルーティング、負荷分散、リトライ、フォールバックを備えたOpenAI互換エンドポイント。ポリシー、レート制限、キャッシュ、可観測性を追加して、信頼性が高くコストを意識した推論を実現します。
 
+### [Playful Proxy API Panel (PPAP)](https://github.com/daishuge/playful-proxy-api-panel)
+
+上流に近い使い方を維持する公開CLIProxyAPI互換フォーク兼管理パネルです。内蔵の使用量統計を復元し、キャッシュヒット率、初回バイト待ち時間、TPSの記録、Docker向けのセルフホスト手順を追加しています。
+
 > [!NOTE]
 > CLIProxyAPIの移植版またはそれに触発されたプロジェクトを開発した場合は、PRを送ってこのリストに追加してください。
 

cmd/server/main.go

@@ -470,6 +470,7 @@ func main() {
 		}
 	}
 	redisqueue.SetUsageStatisticsEnabled(cfg.UsageStatisticsEnabled)
+	redisqueue.SetRetentionSeconds(cfg.RedisUsageQueueRetentionSeconds)
 	coreauth.SetQuotaCooldownDisabled(cfg.DisableCooling)
 
 	if err = logging.ConfigureLogOutput(cfg); err != nil {

config.example.yaml

@@ -71,6 +71,10 @@ error-logs-max-files: 10
 # When false, disable in-memory usage statistics aggregation
 usage-statistics-enabled: false
 
+# How long (in seconds) Redis usage queue items are retained in memory for the RESP interface (LPOP/RPOP).
+# Default: 60. Max: 3600.
+redis-usage-queue-retention-seconds: 60
+
 # Proxy URL. Supports socks5/http/https protocols. Example: socks5://user:pass@192.168.1.1:1080/
 # Per-entry proxy-url also supports "direct" or "none" to bypass both the global proxy-url and environment proxies explicitly.
 proxy-url: ""

internal/api/server.go

@@ -1050,6 +1050,10 @@ func (s *Server) UpdateClients(cfg *config.Config) {
 		redisqueue.SetUsageStatisticsEnabled(cfg.UsageStatisticsEnabled)
 	}
 
+	if oldCfg == nil || oldCfg.RedisUsageQueueRetentionSeconds != cfg.RedisUsageQueueRetentionSeconds {
+		redisqueue.SetRetentionSeconds(cfg.RedisUsageQueueRetentionSeconds)
+	}
+
 	if s.requestLogger != nil && (oldCfg == nil || oldCfg.ErrorLogsMaxFiles != cfg.ErrorLogsMaxFiles) {
 		if setter, ok := s.requestLogger.(interface{ SetErrorLogsMaxFiles(int) }); ok {
 			setter.SetErrorLogsMaxFiles(cfg.ErrorLogsMaxFiles)

internal/config/config.go

@@ -65,6 +65,11 @@ 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"`
 
+	// RedisUsageQueueRetentionSeconds controls how long (in seconds) usage queue items
+	// are retained in memory for the Redis RESP interface (LPOP/RPOP).
+	// Default: 60. Max: 3600.
+	RedisUsageQueueRetentionSeconds int `yaml:"redis-usage-queue-retention-seconds" json:"redis-usage-queue-retention-seconds"`
+
 	// DisableCooling disables quota cooldown scheduling when true.
 	DisableCooling bool `yaml:"disable-cooling" json:"disable-cooling"`
 
@@ -672,6 +677,7 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	cfg.LogsMaxTotalSizeMB = 0
 	cfg.ErrorLogsMaxFiles = 10
 	cfg.UsageStatisticsEnabled = false
+	cfg.RedisUsageQueueRetentionSeconds = 60
 	cfg.DisableCooling = false
 	cfg.DisableImageGeneration = DisableImageGenerationOff
 	cfg.Pprof.Enable = false
@@ -735,6 +741,13 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 		cfg.ErrorLogsMaxFiles = 10
 	}
 
+	if cfg.RedisUsageQueueRetentionSeconds <= 0 {
+		cfg.RedisUsageQueueRetentionSeconds = 60
+	} else if cfg.RedisUsageQueueRetentionSeconds > 3600 {
+		log.WithField("value", cfg.RedisUsageQueueRetentionSeconds).Warn("redis-usage-queue-retention-seconds too large; clamping to 3600")
+		cfg.RedisUsageQueueRetentionSeconds = 3600
+	}
+
 	if cfg.MaxRetryCredentials < 0 {
 		cfg.MaxRetryCredentials = 0
 	}

internal/redisqueue/queue.go

@@ -6,7 +6,10 @@ import (
 	"time"
 )
 
-const retentionWindow = time.Minute
+const (
+	defaultRetentionSeconds int64 = 60
+	maxRetentionSeconds     int64 = 3600
+)
 
 type queueItem struct {
 	enqueuedAt time.Time
@@ -20,10 +23,15 @@ type queue struct {
 }
 
 var (
-	enabled atomic.Bool
-	global  queue
+	enabled          atomic.Bool
+	retentionSeconds atomic.Int64
+	global           queue
 )
 
+func init() {
+	retentionSeconds.Store(defaultRetentionSeconds)
+}
+
 func SetEnabled(value bool) {
 	enabled.Store(value)
 	if !value {
@@ -35,6 +43,16 @@ func Enabled() bool {
 	return enabled.Load()
 }
 
+func SetRetentionSeconds(value int) {
+	normalized := int64(value)
+	if normalized <= 0 {
+		normalized = defaultRetentionSeconds
+	} else if normalized > maxRetentionSeconds {
+		normalized = maxRetentionSeconds
+	}
+	retentionSeconds.Store(normalized)
+}
+
 func Enqueue(payload []byte) {
 	if !Enabled() {
 		return
@@ -110,7 +128,11 @@ func (q *queue) pruneLocked(now time.Time) {
 		return
 	}
 
-	cutoff := now.Add(-retentionWindow)
+	windowSeconds := retentionSeconds.Load()
+	if windowSeconds <= 0 {
+		windowSeconds = defaultRetentionSeconds
+	}
+	cutoff := now.Add(-time.Duration(windowSeconds) * time.Second)
 	for q.head < len(q.items) && q.items[q.head].enqueuedAt.Before(cutoff) {
 		q.head++
 	}

internal/watcher/diff/config_diff.go

@@ -39,6 +39,9 @@ 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.RedisUsageQueueRetentionSeconds != newCfg.RedisUsageQueueRetentionSeconds {
+		changes = append(changes, fmt.Sprintf("redis-usage-queue-retention-seconds: %d -> %d", oldCfg.RedisUsageQueueRetentionSeconds, newCfg.RedisUsageQueueRetentionSeconds))
+	}
 	if oldCfg.DisableCooling != newCfg.DisableCooling {
 		changes = append(changes, fmt.Sprintf("disable-cooling: %t -> %t", oldCfg.DisableCooling, newCfg.DisableCooling))
 	}