diff --git a/config.yaml b/config.yaml
deleted file mode 100644
index 5e7513fb..00000000
--- a/config.yaml
+++ /dev/null
@@ -1,527 +0,0 @@
-# Sub2API Configuration File
-# Sub2API 配置文件
-#
-# Copy this file to /etc/sub2api/config.yaml and modify as needed
-# 复制此文件到 /etc/sub2api/config.yaml 并根据需要修改
-#
-# Documentation / 文档: https://github.com/Wei-Shaw/sub2api
-
-# =============================================================================
-# Server Configuration
-# 服务器配置
-# =============================================================================
-server:
-  # Bind address (0.0.0.0 for all interfaces)
-  # 绑定地址（0.0.0.0 表示监听所有网络接口）
-  host: "0.0.0.0"
-  # Port to listen on
-  # 监听端口
-  port: 8080
-  # Mode: "debug" for development, "release" for production
-  # 运行模式："debug" 用于开发，"release" 用于生产环境
-  mode: "release"
-  # Trusted proxies for X-Forwarded-For parsing (CIDR/IP). Empty disables trusted proxies.
-  # 信任的代理地址（CIDR/IP 格式），用于解析 X-Forwarded-For 头。留空则禁用代理信任。
-  trusted_proxies: []
-
-# =============================================================================
-# Run Mode Configuration
-# 运行模式配置
-# =============================================================================
-# Run mode: "standard" (default) or "simple" (for internal use)
-# 运行模式："standard"（默认）或 "simple"（内部使用）
-# - standard: Full SaaS features with billing/balance checks
-# - standard: 完整 SaaS 功能，包含计费和余额校验
-# - simple: Hides SaaS features and skips billing/balance checks
-# - simple: 隐藏 SaaS 功能，跳过计费和余额校验
-run_mode: "standard"
-
-# =============================================================================
-# CORS Configuration
-# 跨域资源共享 (CORS) 配置
-# =============================================================================
-cors:
-  # Allowed origins list. Leave empty to disable cross-origin requests.
-  # 允许的来源列表。留空则禁用跨域请求。
-  allowed_origins: []
-  # Allow credentials (cookies/authorization headers). Cannot be used with "*".
-  # 允许携带凭证（cookies/授权头）。不能与 "*" 通配符同时使用。
-  allow_credentials: true
-
-# =============================================================================
-# Security Configuration
-# 安全配置
-# =============================================================================
-security:
-  url_allowlist:
-    # Enable URL allowlist validation (disable to skip all URL checks)
-    # 启用 URL 白名单验证（禁用则跳过所有 URL 检查）
-    enabled: false
-    # Allowed upstream hosts for API proxying
-    # 允许代理的上游 API 主机列表
-    upstream_hosts:
-      - "api.openai.com"
-      - "api.anthropic.com"
-      - "api.kimi.com"
-      - "open.bigmodel.cn"
-      - "api.minimaxi.com"
-      - "generativelanguage.googleapis.com"
-      - "cloudcode-pa.googleapis.com"
-      - "*.openai.azure.com"
-    # Allowed hosts for pricing data download
-    # 允许下载定价数据的主机列表
-    pricing_hosts:
-      - "raw.githubusercontent.com"
-    # Allowed hosts for CRS sync (required when using CRS sync)
-    # 允许 CRS 同步的主机列表（使用 CRS 同步功能时必须配置）
-    crs_hosts: []
-    # Allow localhost/private IPs for upstream/pricing/CRS (use only in trusted networks)
-    # 允许本地/私有 IP 地址用于上游/定价/CRS（仅在可信网络中使用）
-    allow_private_hosts: true
-    # Allow http:// URLs when allowlist is disabled (default: false, require https)
-    # 白名单禁用时是否允许 http:// URL（默认: false，要求 https）
-    allow_insecure_http: true
-  response_headers:
-    # Enable configurable response header filtering (disable to use default allowlist)
-    # 启用可配置的响应头过滤（禁用则使用默认白名单）
-    enabled: false
-    # Extra allowed response headers from upstream
-    # 额外允许的上游响应头
-    additional_allowed: []
-    # Force-remove response headers from upstream
-    # 强制移除的上游响应头
-    force_remove: []
-  csp:
-    # Enable Content-Security-Policy header
-    # 启用内容安全策略 (CSP) 响应头
-    enabled: true
-    # Default CSP policy (override if you host assets on other domains)
-    # 默认 CSP 策略（如果静态资源托管在其他域名，请自行覆盖）
-    policy: "default-src 'self'; script-src 'self'; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; img-src 'self' data: https:; font-src 'self' data: https://fonts.gstatic.com; connect-src 'self' https:; frame-ancestors 'none'; base-uri 'self'; form-action 'self'"
-  proxy_probe:
-    # Allow skipping TLS verification for proxy probe (debug only)
-    # 允许代理探测时跳过 TLS 证书验证（仅用于调试）
-    insecure_skip_verify: false
-
-# =============================================================================
-# Gateway Configuration
-# 网关配置
-# =============================================================================
-gateway:
-  # Timeout for waiting upstream response headers (seconds)
-  # 等待上游响应头超时时间（秒）
-  response_header_timeout: 600
-  # Max request body size in bytes (default: 100MB)
-  # 请求体最大字节数（默认 100MB）
-  max_body_size: 104857600
-  # Connection pool isolation strategy:
-  # 连接池隔离策略：
-  # - proxy: Isolate by proxy, same proxy shares connection pool (suitable for few proxies, many accounts)
-  # - proxy: 按代理隔离，同一代理共享连接池（适合代理少、账户多）
-  # - account: Isolate by account, same account shares connection pool (suitable for few accounts, strict isolation)
-  # - account: 按账户隔离，同一账户共享连接池（适合账户少、需严格隔离）
-  # - account_proxy: Isolate by account+proxy combination (default, finest granularity)
-  # - account_proxy: 按账户+代理组合隔离（默认，最细粒度）
-  connection_pool_isolation: "account_proxy"
-  # HTTP upstream connection pool settings (HTTP/2 + multi-proxy scenario defaults)
-  # HTTP 上游连接池配置（HTTP/2 + 多代理场景默认值）
-  # Max idle connections across all hosts
-  # 所有主机的最大空闲连接数
-  max_idle_conns: 240
-  # Max idle connections per host
-  # 每个主机的最大空闲连接数
-  max_idle_conns_per_host: 120
-  # Max connections per host
-  # 每个主机的最大连接数
-  max_conns_per_host: 240
-  # Idle connection timeout (seconds)
-  # 空闲连接超时时间（秒）
-  idle_conn_timeout_seconds: 90
-  # Upstream client cache settings
-  # 上游连接池客户端缓存配置
-  # max_upstream_clients: Max cached clients, evicts least recently used when exceeded
-  # max_upstream_clients: 最大缓存客户端数量，超出后淘汰最久未使用的
-  max_upstream_clients: 5000
-  # client_idle_ttl_seconds: Client idle reclaim threshold (seconds), reclaimed when idle and no active requests
-  # client_idle_ttl_seconds: 客户端空闲回收阈值（秒），超时且无活跃请求时回收
-  client_idle_ttl_seconds: 900
-  # Concurrency slot expiration time (minutes)
-  # 并发槽位过期时间（分钟）
-  concurrency_slot_ttl_minutes: 30
-  # Stream data interval timeout (seconds), 0=disable
-  # 流数据间隔超时（秒），0=禁用
-  stream_data_interval_timeout: 180
-  # Stream keepalive interval (seconds), 0=disable
-  # 流式 keepalive 间隔（秒），0=禁用
-  stream_keepalive_interval: 10
-  # SSE max line size in bytes (default: 40MB)
-  # SSE 单行最大字节数（默认 40MB）
-  max_line_size: 41943040
-  # Log upstream error response body summary (safe/truncated; does not log request content)
-  # 记录上游错误响应体摘要（安全/截断；不记录请求内容）
-  log_upstream_error_body: true
-  # Max bytes to log from upstream error body
-  # 记录上游错误响应体的最大字节数
-  log_upstream_error_body_max_bytes: 2048
-  # Auto inject anthropic-beta header for API-key accounts when needed (default: off)
-  # 需要时自动为 API-key 账户注入 anthropic-beta 头（默认：关闭）
-  inject_beta_for_apikey: false
-  # Allow failover on selected 400 errors (default: off)
-  # 允许在特定 400 错误时进行故障转移（默认：关闭）
-  failover_on_400: false
-
-# =============================================================================
-# API Key Auth Cache Configuration
-# API Key 认证缓存配置
-# =============================================================================
-api_key_auth_cache:
-  # L1 cache size (entries), in-process LRU/TTL cache
-  # L1 缓存容量（条目数），进程内 LRU/TTL 缓存
-  l1_size: 65535
-  # L1 cache TTL (seconds)
-  # L1 缓存 TTL（秒）
-  l1_ttl_seconds: 15
-  # L2 cache TTL (seconds), stored in Redis
-  # L2 缓存 TTL（秒），Redis 中存储
-  l2_ttl_seconds: 300
-  # Negative cache TTL (seconds)
-  # 负缓存 TTL（秒）
-  negative_ttl_seconds: 30
-  # TTL jitter percent (0-100)
-  # TTL 抖动百分比（0-100）
-  jitter_percent: 10
-  # Enable singleflight for cache misses
-  # 缓存未命中时启用 singleflight 合并回源
-  singleflight: true
-
-# =============================================================================
-# Dashboard Cache Configuration
-# 仪表盘缓存配置
-# =============================================================================
-dashboard_cache:
-  # Enable dashboard cache
-  # 启用仪表盘缓存
-  enabled: true
-  # Redis key prefix for multi-environment isolation
-  # Redis key 前缀，用于多环境隔离
-  key_prefix: "sub2api:"
-  # Fresh TTL (seconds); within this window cached stats are considered fresh
-  # 新鲜阈值（秒）；命中后处于该窗口视为新鲜数据
-  stats_fresh_ttl_seconds: 15
-  # Cache TTL (seconds) stored in Redis
-  # Redis 缓存 TTL（秒）
-  stats_ttl_seconds: 30
-  # Async refresh timeout (seconds)
-  # 异步刷新超时（秒）
-  stats_refresh_timeout_seconds: 30
-
-# =============================================================================
-# Dashboard Aggregation Configuration
-# 仪表盘预聚合配置（重启生效）
-# =============================================================================
-dashboard_aggregation:
-  # Enable aggregation job
-  # 启用聚合作业
-  enabled: true
-  # Refresh interval (seconds)
-  # 刷新间隔（秒）
-  interval_seconds: 60
-  # Lookback window (seconds) for late-arriving data
-  # 回看窗口（秒），处理迟到数据
-  lookback_seconds: 120
-  # Allow manual backfill
-  # 允许手动回填
-  backfill_enabled: false
-  # Backfill max range (days)
-  # 回填最大跨度（天）
-  backfill_max_days: 31
-  # Recompute recent N days on startup
-  # 启动时重算最近 N 天
-  recompute_days: 2
-  # Retention windows (days)
-  # 保留窗口（天）
-  retention:
-    # Raw usage_logs retention
-    # 原始 usage_logs 保留天数
-    usage_logs_days: 90
-    # Hourly aggregation retention
-    # 小时聚合保留天数
-    hourly_days: 180
-    # Daily aggregation retention
-    # 日聚合保留天数
-    daily_days: 730
-
-# =============================================================================
-# Usage Cleanup Task Configuration
-# 使用记录清理任务配置（重启生效）
-# =============================================================================
-usage_cleanup:
-  # Enable cleanup task worker
-  # 启用清理任务执行器
-  enabled: true
-  # Max date range (days) per task
-  # 单次任务最大时间跨度（天）
-  max_range_days: 31
-  # Batch delete size
-  # 单批删除数量
-  batch_size: 5000
-  # Worker interval (seconds)
-  # 执行器轮询间隔（秒）
-  worker_interval_seconds: 10
-  # Task execution timeout (seconds)
-  # 单次任务最大执行时长（秒）
-  task_timeout_seconds: 1800
-
-# =============================================================================
-# Concurrency Wait Configuration
-# 并发等待配置
-# =============================================================================
-concurrency:
-  # SSE ping interval during concurrency wait (seconds)
-  # 并发等待期间的 SSE ping 间隔（秒）
-  ping_interval: 10
-
-# =============================================================================
-# Database Configuration (PostgreSQL)
-# 数据库配置 (PostgreSQL)
-# =============================================================================
-database:
-  # Database host address
-  # 数据库主机地址
-  host: "localhost"
-  # Database port
-  # 数据库端口
-  port: 5432
-  # Database username
-  # 数据库用户名
-  user: "postgres"
-  # Database password
-  # 数据库密码
-  password: "your_secure_password_here"
-  # Database name
-  # 数据库名称
-  dbname: "sub2api"
-  # SSL mode: disable, require, verify-ca, verify-full
-  # SSL 模式：disable（禁用）, require（要求）, verify-ca（验证CA）, verify-full（完全验证）
-  sslmode: "disable"
-
-# =============================================================================
-# Redis Configuration
-# Redis 配置
-# =============================================================================
-redis:
-  # Redis host address
-  # Redis 主机地址
-  host: "localhost"
-  # Redis port
-  # Redis 端口
-  port: 6379
-  # Redis password (leave empty if no password is set)
-  # Redis 密码（如果未设置密码则留空）
-  password: ""
-  # Database number (0-15)
-  # 数据库编号（0-15）
-  db: 0
-
-# =============================================================================
-# Ops Monitoring (Optional)
-# 运维监控 (可选)
-# =============================================================================
-ops:
-  # Hard switch: disable all ops background jobs and APIs when false
-  # 硬开关：为 false 时禁用所有 Ops 后台任务与接口
-  enabled: true
-
-  # Prefer pre-aggregated tables (ops_metrics_hourly/ops_metrics_daily) for long-window dashboard queries.
-  # 优先使用预聚合表（用于长时间窗口查询性能）
-  use_preaggregated_tables: false
-
-  # Data cleanup configuration
-  # 数据清理配置（vNext 默认统一保留 30 天）
-  cleanup:
-    enabled: true
-    # Cron expression (minute hour dom month dow), e.g. "0 2 * * *" = daily at 2 AM
-    # Cron 表达式（分 时 日 月 周），例如 "0 2 * * *" = 每天凌晨 2 点
-    schedule: "0 2 * * *"
-    error_log_retention_days: 30
-    minute_metrics_retention_days: 30
-    hourly_metrics_retention_days: 30
-
-  # Pre-aggregation configuration
-  # 预聚合任务配置
-  aggregation:
-    enabled: true
-
-  # OpsMetricsCollector Redis cache (reduces duplicate expensive window aggregation in multi-replica deployments)
-  # 指标采集 Redis 缓存（多副本部署时减少重复计算）
-  metrics_collector_cache:
-    enabled: true
-    ttl: 65s
-
-# =============================================================================
-# JWT Configuration
-# JWT 配置
-# =============================================================================
-jwt:
-  # IMPORTANT: Change this to a random string in production!
-  # 重要：生产环境中请更改为随机字符串！
-  # Generate with / 生成命令: openssl rand -hex 32
-  secret: "change-this-to-a-secure-random-string"
-  # Token expiration time in hours (max 24)
-  # 令牌过期时间（小时，最大 24）
-  expire_hour: 24
-
-# =============================================================================
-# Default Settings
-# 默认设置
-# =============================================================================
-default:
-  # Initial admin account (created on first run)
-  # 初始管理员账户（首次运行时创建）
-  admin_email: "admin@example.com"
-  admin_password: "admin123"
-
-  # Default settings for new users
-  # 新用户默认设置
-  # Max concurrent requests per user
-  # 每用户最大并发请求数
-  user_concurrency: 5
-  # Initial balance for new users
-  # 新用户初始余额
-  user_balance: 0
-
-  # API key settings
-  # API 密钥设置
-  # Prefix for generated API keys
-  # 生成的 API 密钥前缀
-  api_key_prefix: "sk-"
-
-  # Rate multiplier (affects billing calculation)
-  # 费率倍数（影响计费计算）
-  rate_multiplier: 1.0
-
-# =============================================================================
-# Rate Limiting
-# 速率限制
-# =============================================================================
-rate_limit:
-  # Cooldown time (in minutes) when upstream returns 529 (overloaded)
-  # 上游返回 529（过载）时的冷却时间（分钟）
-  overload_cooldown_minutes: 10
-
-# =============================================================================
-# Pricing Data Source (Optional)
-# 定价数据源（可选）
-# =============================================================================
-pricing:
-  # URL to fetch model pricing data (default: LiteLLM)
-  # 获取模型定价数据的 URL（默认：LiteLLM）
-  remote_url: "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
-  # Hash verification URL (optional)
-  # 哈希校验 URL（可选）
-  hash_url: ""
-  # Local data directory for caching
-  # 本地数据缓存目录
-  data_dir: "./data"
-  # Fallback pricing file
-  # 备用定价文件
-  fallback_file: "./resources/model-pricing/model_prices_and_context_window.json"
-  # Update interval in hours
-  # 更新间隔（小时）
-  update_interval_hours: 24
-  # Hash check interval in minutes
-  # 哈希检查间隔（分钟）
-  hash_check_interval_minutes: 10
-
-# =============================================================================
-# Billing Configuration
-# 计费配置
-# =============================================================================
-billing:
-  circuit_breaker:
-    # Enable circuit breaker for billing service
-    # 启用计费服务熔断器
-    enabled: true
-    # Number of failures before opening circuit
-    # 触发熔断的失败次数阈值
-    failure_threshold: 5
-    # Time to wait before attempting reset (seconds)
-    # 熔断后重试等待时间（秒）
-    reset_timeout_seconds: 30
-    # Number of requests to allow in half-open state
-    # 半开状态允许通过的请求数
-    half_open_requests: 3
-
-# =============================================================================
-# Turnstile Configuration
-# Turnstile 人机验证配置
-# =============================================================================
-turnstile:
-  # Require Turnstile in release mode (when enabled, login/register will fail if not configured)
-  # 在 release 模式下要求 Turnstile 验证（启用后，若未配置则登录/注册会失败）
-  required: false
-
-# =============================================================================
-# Gemini OAuth (Required for Gemini accounts)
-# Gemini OAuth 配置（Gemini 账户必需）
-# =============================================================================
-# Sub2API supports TWO Gemini OAuth modes:
-# Sub2API 支持两种 Gemini OAuth 模式：
-#
-# 1. Code Assist OAuth (requires GCP project_id)
-# 1. Code Assist OAuth（需要 GCP project_id）
-#    - Uses: cloudcode-pa.googleapis.com (Code Assist API)
-#    - 使用：cloudcode-pa.googleapis.com（Code Assist API）
-#
-# 2. AI Studio OAuth (no project_id needed)
-# 2. AI Studio OAuth（不需要 project_id）
-#    - Uses: generativelanguage.googleapis.com (AI Studio API)
-#    - 使用：generativelanguage.googleapis.com（AI Studio API）
-#
-# Default: Uses Gemini CLI's public OAuth credentials (same as Google's official CLI tool)
-# 默认：使用 Gemini CLI 的公开 OAuth 凭证（与 Google 官方 CLI 工具相同）
-gemini:
-  oauth:
-    # Gemini CLI public OAuth credentials (works for both Code Assist and AI Studio)
-    # Gemini CLI 公开 OAuth 凭证（适用于 Code Assist 和 AI Studio）
-    client_id: "681255809395-oo8ft2oprdrnp9e3aqf6av3hmdib135j.apps.googleusercontent.com"
-    client_secret: "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"
-    # Optional scopes (space-separated). Leave empty to auto-select based on oauth_type.
-    # 可选的权限范围（空格分隔）。留空则根据 oauth_type 自动选择。
-    scopes: ""
-  quota:
-    # Optional: local quota simulation for Gemini Code Assist (local billing).
-    # 可选：Gemini Code Assist 本地配额模拟（本地计费）。
-    # These values are used for UI progress + precheck scheduling, not official Google quotas.
-    # 这些值用于 UI 进度显示和预检调度，并非 Google 官方配额。
-    tiers:
-      LEGACY:
-        # Pro model requests per day
-        # Pro 模型每日请求数
-        pro_rpd: 50
-        # Flash model requests per day
-        # Flash 模型每日请求数
-        flash_rpd: 1500
-        # Cooldown time (minutes) after hitting quota
-        # 达到配额后的冷却时间（分钟）
-        cooldown_minutes: 30
-      PRO:
-        # Pro model requests per day
-        # Pro 模型每日请求数
-        pro_rpd: 1500
-        # Flash model requests per day
-        # Flash 模型每日请求数
-        flash_rpd: 4000
-        # Cooldown time (minutes) after hitting quota
-        # 达到配额后的冷却时间（分钟）
-        cooldown_minutes: 5
-      ULTRA:
-        # Pro model requests per day
-        # Pro 模型每日请求数
-        pro_rpd: 2000
-        # Flash model requests per day (0 = unlimited)
-        # Flash 模型每日请求数（0 = 无限制）
-        flash_rpd: 0
-        # Cooldown time (minutes) after hitting quota
-        # 达到配额后的冷却时间（分钟）
-        cooldown_minutes: 5
diff --git a/deploy/docker-compose-test.yml b/deploy/docker-compose-test.yml
index bcda3141..19903f6f 100644
--- a/deploy/docker-compose-test.yml
+++ b/deploy/docker-compose-test.yml
@@ -33,7 +33,7 @@ services:
       # Data persistence (config.yaml will be auto-generated here)
       - sub2api_data:/app/data
       # Mount custom config.yaml (optional, overrides auto-generated config)
-      - ./config.yaml:/app/data/config.yaml:ro
+      # - ./config.yaml:/app/data/config.yaml:ro
     environment:
       # =======================================================================
       # Auto Setup (REQUIRED for Docker deployment)
@@ -150,7 +150,7 @@ services:
   # Redis Cache
   # ===========================================================================
   redis:
-    image: redis:7-alpine
+    image: redis:8-alpine
     container_name: sub2api-redis
     restart: unless-stopped
     ulimits: