feat: 错误提示中文化、GPT Image 余额查询、Nano Banana 自动重试

- gemini_client: 更新 429/504 中文错误文案，与产品文案对齐
- gpt_image_client: 新增 query_balance_sync / format_balance_info 余额查询方法
- gpt_image: 每次执行后打印余额日志（finally 块保证触发）
- nano_banana_pro: 单张生成支持自动重试，遇 429/503/504 最多重试 4 次，指数退避 2-32s，终端显示显眼重试状态
- nano_banana_pro: 关闭调试日志（DEBUG_LOG_ENABLED = False）

Co-Authored-By: Claude Sonnet 4.5 <[email protected]>

clients/gemini_client.py

@@ -115,13 +115,13 @@ class GeminiAPIClient(BaseAPIClient):
         return "/v1beta/models/gemini-3-pro-image-preview:generateContent"
     
     def get_http_error_message(self, status_code: int, error_message: str) -> Optional[str]:
-        """Gemini 请求 429/503 时返回图中约定的多行错误框文案。"""
+        """Gemini 请求 429/503/504 时返回中文错误文案。"""
         if status_code == 429:
-            return "该型号资源已耗尽，但只是暂时的，请稍后重试。"
+            return "此型号资源暂时耗尽，继续重试即可"
         if status_code == 503:
             return "此型号目前需求量较大。需求高峰通常是暂时的。请稍后再试。"
         if status_code == 504:
-            return "服务无法在截止期限内完成处理。请稍后重试。"
+            return "服务无法在截止期限内完成处理。可能原因是：您的提示词过大，无法及时处理。"
         return None
     
     def build_request_body(

clients/gpt_image_client.py

@@ -417,3 +417,35 @@ class GptImageClient:
                 raise RuntimeError(
                     f"o1key GPT Image 请求超时（>{_REQUEST_TIMEOUT}s），请检查网络或稍后重试"
                 )
+
+    # ── 余额查询 ──────────────────────────────────────────────────────────────
+
+    async def _query_balance_async(self) -> dict:
+        url = f"{self.base_url}/api/usage/token"
+        connector = aiohttp.TCPConnector(ssl=False, force_close=True)
+        timeout   = aiohttp.ClientTimeout(total=10)
+        async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session:
+            async with session.get(url, headers=self._auth_headers()) as resp:
+                if resp.status != 200:
+                    raise RuntimeError(f"余额查询失败 HTTP {resp.status}")
+                return await resp.json()
+
+    def query_balance_sync(self) -> dict:
+        def _run():
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+            try:
+                return loop.run_until_complete(self._query_balance_async())
+            finally:
+                loop.close()
+
+        with ThreadPoolExecutor(max_workers=1) as executor:
+            return executor.submit(_run).result(timeout=15)
+
+    @staticmethod
+    def format_balance_info(balance_data: dict) -> str:
+        data             = balance_data.get("data", {})
+        api_name         = data.get("name", "未知")
+        total_available  = data.get("total_available", 0)
+        balance_in_dollars = total_available / 500000
+        return f"当前余额：{balance_in_dollars:.2f} | API：{api_name}"