refactor(rate_limit): refactor API Key rate limiting and remove tenant-level QPS check

- Streamline rate limit check flow by removing redundant tenant-level QPS checks.
- Restrict checks to API Key QPS and plan degradation protection only.
- Update constant naming and error message handling for consistency.

api/app/core/api_key_auth.py

@@ -108,8 +108,7 @@ def require_api_key(
                 # 根据错误消息判断限流类型
                 if "Daily" in error_msg:
                     code = BizCode.API_KEY_DAILY_LIMIT_EXCEEDED
-                elif "QPS" in error_msg or "ops rate limit" in error_msg:
-                    # "QPS limit exceeded" 和 "API ops rate limit exceeded" 同属 QPS 类
+                elif "QPS" in error_msg:
                     code = BizCode.API_KEY_QPS_LIMIT_EXCEEDED
                 else:
                     code = BizCode.API_KEY_QUOTA_EXCEEDED

api/app/core/quota_stub.py

@@ -18,7 +18,7 @@ from app.core.quota_manager import (
     get_quota_usage,
     _check_quota,
     QuotaUsageRepository,
-    TENANT_QPS_REDIS_KEY,
+    API_KEY_QPS_REDIS_KEY,
 )
 
 __all__ = [
@@ -34,5 +34,5 @@ __all__ = [
     "get_quota_usage",
     "_check_quota",
     "QuotaUsageRepository",
-    "TENANT_QPS_REDIS_KEY",
+    "API_KEY_QPS_REDIS_KEY",
 ]