[BUG]在使用OpenRouter的api调用Gemini3-pro模型时不能连续使用工具

[BluedeDove]

---

Bug 描述
在使用OpenRouter的api调用google/gemini-3-pro-preview模型时 Google AI Studio不接受返回的信息
{ "error": { "message": "Provider returned error", "code": 400, "metadata": { "raw": "Gemini models require OpenRouter reasoning details to be preserved in each request. Please refer to our docs: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. Upstream error: {\n \"error\": {\n \"code\": 400,\n \"message\": \"Function call is missing a thought_signature in functionCall parts. This is required for tools to work correctly, and missing thought_signature may lead to degraded model performance. Additional data, function call default_api:mcp__playwright__browser_navigate , position 2. please refer to https://ai.google.dev/gemini-api/docs/thought-signatures for more details.\",\n \"status\": \"INVALID_ARGUMENT\"\n }\n}\n", "provider_name": "Google AI Studio" } }, "user_id": "user_34q6l6LSd2PxvhizR29Xg0Kcncl" }

并且对于一般的对话 结尾总会附加一个[REDACTED]

对于Gemini 2.5pro等模型不会出现这种情况

重现步骤

1. 使用OpenRouter的api调用google/gemini-3-pro-preview
2. 让模型使用工具

期望结果

实际结果

桌面端（请填写以下信息）：

• 操作系统：[Windows]
• 应用程序版本：[1.17.1]