[Bug]更新新版4.21后用大模型一直会报'int' and 'NoneType'，导致无法正常使用 #6772

What happened / 发生了什么

更新后和机器人聊天就会报'int' and 'NoneType'，然后报400，导致无法正常使用

Reproduce / 如何复现？

1.更新4.21
2.和任意机器人聊天

AstrBot version, deployment method (e.g., Windows Docker Desktop deployment), provider used, and messaging platform used. / AstrBot 版本、部署方式（如 Windows Docker Desktop 部署）、使用的提供商、使用的消息平台适配器

4.21
window.exe

OS

Windows

Logs / 报错日志

[2026-03-22 10:17:54.105] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:283]: Chat Model 自建api/qwen3.5-plus request error: unsupported operand type(s) for -: 'int' and 'NoneType'
Traceback (most recent call last):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 258, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(include_model=idx == 0):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 235, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 790, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 741, in _handle_api_error
raise e
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 778, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 285, in _query
llm_response = await self._parse_openai_completion(completion, tools)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 571, in _parse_openai_completion
llm_response.usage = self._extract_usage(completion.usage)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 396, in _extract_usage
input_other=prompt_tokens - cached,
~~~~~~~~~~~~~~^~~~~~~~
TypeError: unsupported operand type(s) for -: 'int' and 'NoneType'
[2026-03-22 10:17:54.166] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:250]: Switched from 自建api/qwen3.5-plus to fallback chat provider: 自建api/doubao-seed-2-0-pro-260215
[2026-03-22 10:17:56.170] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:283]: Chat Model 自建api/doubao-seed-2-0-pro-260215 request error: Error code: 400 - {'error': {'message': 'Total tokens of image and text exceed max message tokens. Request id: 021774145881399e3c0010419774ef230e4bef6206f9366989f55', 'type': 'BadRequest', 'param': '', 'code': 'InvalidParameter'}}
Traceback (most recent call last):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 258, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(include_model=idx == 0):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 235, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 790, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 741, in _handle_api_error
raise e
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 778, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 272, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai\resources\chat\completions\completions.py", line 2714, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1884, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1669, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Total tokens of image and text exceed max message tokens. Request id: 021774145881399e3c0010419774ef230e4bef6206f9366989f55', 'type': 'BadRequest', 'param': '', 'code': 'InvalidParameter'}}
[2026-03-22 10:17:56.246] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:250]: Switched from 自建api/doubao-seed-2-0-pro-260215 to fallback chat provider: 自建api/腾讯kimi-k2.5
[2026-03-22 10:17:57.906] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:283]: Chat Model 自建api/腾讯kimi-k2.5 request error: Error code: 400 - {'error': {'message': 'Request parameters are invalid. Please check the required parameters.', 'type': 'runtime_error', 'param': '', 'code': '20024'}}
Traceback (most recent call last):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 258, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(include_model=idx == 0):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 235, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 790, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 741, in _handle_api_error
raise e
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 778, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 272, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai\resources\chat\completions\completions.py", line 2714, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1884, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1669, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Request parameters are invalid. Please check the required parameters.', 'type': 'runtime_error', 'param': '', 'code': '20024'}}
[2026-03-22 10:17:57.978] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:250]: Switched from 自建api/腾讯kimi-k2.5 to fallback chat provider: 自建api/qianfan-code-latest
[2026-03-22 10:17:59.495] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:283]: Chat Model 自建api/qianfan-code-latest request error: Error code: 400 - {'error': {'message': "Error code: 400 - {'error': {'code': 'invalid_argument', 'message': 'Message format error, index[2] tool_calls[3] id is duplicate', 'type': 'invalid_request_error'}, 'id': 'as-ztpi8cz5g8'}", 'type': 'api_error', 'param': '', 'code': None}}
Traceback (most recent call last):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 258, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(include_model=idx == 0):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 235, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 790, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 741, in _handle_api_error
raise e
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 778, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 272, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai\resources\chat\completions\completions.py", line 2714, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1884, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1669, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Error code: 400 - {'error': {'code': 'invalid_argument', 'message': 'Message format error, index[2] tool_calls[3] id is duplicate', 'type': 'invalid_request_error'}, 'id': 'as-ztpi8cz5g8'}", 'type': 'api_error', 'param': '', 'code': None}}
[2026-03-22 10:17:59.569] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:250]: Switched from 自建api/qianfan-code-latest to fallback chat provider: 自建api/grok-4.20-beta
[2026-03-22 10:17:59.945] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:283]: Chat Model 自建api/grok-4.20-beta request error: Error code: 403 - {'error': {'code': '', 'message': 'This token has no access to model grok-4.20-beta (request id: 20260322021806532583044vrL7h0r8)', 'type': 'new_api_error'}}
Traceback (most recent call last):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 258, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(include_model=idx == 0):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 235, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 790, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 741, in _handle_api_error
raise e
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 778, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 272, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai\resources\chat\completions\completions.py", line 2714, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1884, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\venv\Lib\site-packages\openai_base_client.py", line 1669, in request
raise self._make_status_error_from_response(err.response) from None
openai.PermissionDeniedError: Error code: 403 - {'error': {'code': '', 'message': 'This token has no access to model grok-4.20-beta (request id: 20260322021806532583044vrL7h0r8)', 'type': 'new_api_error'}}
[2026-03-22 10:18:00.014] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:250]: Switched from 自建api/grok-4.20-beta to fallback chat provider: 魔塔社区API/ZhipuAI/GLM-5
[2026-03-22 10:18:02.440] [Core] [WARN] [v4.21.0] [runners.tool_loop_agent_runner:283]: Chat Model 魔塔社区API/ZhipuAI/GLM-5 request error: API 返回的 completion 为空。
Traceback (most recent call last):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 258, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(include_model=idx == 0):
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 235, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 790, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 741, in _handle_api_error
raise e
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 778, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 285, in _query
llm_response = await self._parse_openai_completion(completion, tools)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator.astrbot_launcher\instances\5807117e-1c9a-4f6e-bedd-59c5ff4a4e81\core\astrbot\core\provider\sources\openai_source.py", line 498, in _parse_openai_completion
raise Exception("API 返回的 completion 为空。")
Exception: API 返回的 completion 为空。

Are you willing to submit a PR? / 你愿意提交 PR 吗？

• Yes!

Code of Conduct

• I have read and agree to abide by the project's Code of Conduct。