fix(billing): 默认关闭 OpenAI 长上下文计费

frontend/src/i18n/locales/en/admin/accounts.ts

@@ -404,7 +404,7 @@ export default {
           'When enabled, this OpenAI account uses automatic passthrough: the gateway forwards request/response as-is and only swaps auth, while keeping billing/concurrency/audit and necessary safety filtering.',
         longContextBilling: 'API long-context pricing',
         longContextBillingDesc:
-          'Enabled by default. Disable only when this account\'s upstream does not charge OpenAI API long-context rates above the model threshold.',
+          'Disabled by default. Enable only when this account\'s upstream charges OpenAI API long-context rates above the model threshold.',
         responsesWebsocketsV2: 'Responses WebSocket v2',
         responsesWebsocketsV2Desc:
           'Disabled by default. Enable to allow responses_websockets_v2 capability (still gated by global and account-type switches).',

frontend/src/i18n/locales/zh/admin/accounts.ts

@@ -506,7 +506,7 @@ export default {
         oauthPassthroughDesc:
           '开启后，该 OpenAI 账号将自动透传请求与响应，仅替换认证并保留计费/并发/审计及必要安全过滤；如遇兼容性问题可随时关闭回滚。',
         longContextBilling: 'API 长上下文计费',
-        longContextBillingDesc: '默认开启。仅当该账号的上游不会按模型阈值收取 OpenAI API 长上下文费率时关闭。',
+        longContextBillingDesc: '默认关闭。仅当该账号的上游会按模型阈值收取 OpenAI API 长上下文费率时开启。',
         responsesWebsocketsV2: 'Responses WebSocket v2',
         responsesWebsocketsV2Desc:
           '默认关闭。开启后可启用 responses_websockets_v2 协议能力（受网关全局开关与账号类型开关约束）。',