[Bug] gemini开启高级配置中的“启用原生搜索功能”“启用URL上下文功能”等功能时，疑似构造了错误的请求参数，导致请求出错。

[tusky94]

What happened / 发生了什么

LLM响应错误：
All chat models failed: ClientError: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'Function calling config is set without function_declarations.', 'status': 'INVALID_ARGUMENT'}}

Reproduce / 如何复现？

配置一个官网 https://generativelanguage.googleapis.com 的google_gemini/gemini-2.5-flash模型，启用启高级配置中的“启用原生搜索功能”“启用URL上下文功能”选项，保存后配置为默认模型进行对话。

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

AstrBot v4.22.3 使用linux源码部署，使用Google官方api，QQ平台

OS

Windows

Logs / 报错日志

[2026-04-07 14:54:36.114] [Core] [INFO] [core.event_bus:61]: [default] [astrbot(aiocqhttp)] 逸木/872778579: [At:2578272592] 你哪个初中的 
[2026-04-07 14:54:36.115] [Core] [DBUG] [waking_check.stage:157]: enabled_plugins_name: ['*']
[2026-04-07 14:54:36.497] [Core] [DBUG] [method.star_request:44]: plugin -> session_controller - handle_session_control_agent
[2026-04-07 14:54:36.498] [Core] [DBUG] [method.star_request:44]: plugin -> session_controller - handle_empty_mention
[2026-04-07 14:54:36.498] [Core] [DBUG] [method.star_request:44]: plugin -> astrbot_plugin_wakepro - on_group_msg
[2026-04-07 14:54:36.498] [Plug] [DBUG] [astrbot_plugin_wakepro.main:261]: 已添加event到缓存：1
[2026-04-07 14:54:36.499] [Plug] [INFO] [astrbot_plugin_wakepro.main:267]: [wakepro] 群(71901396)at_or_cmd：你哪个初中的
[2026-04-07 14:54:36.499] [Plug] [DBUG] [astrbot_plugin_wakepro.sentiment:219]: [wakepro] ['哪个', '初中']
[2026-04-07 14:54:36.499] [Core] [DBUG] [method.star_request:44]: plugin -> astrbot - on_message
[2026-04-07 14:54:36.500] [Plug] [DBUG] [astrbot.long_term_memory:146]: ltm | astrbot:GroupMessage:71901396 | [逸木/14:54:36]:  [At: 猫猫头] 你哪个初中的
[2026-04-07 14:54:36.504] [Core] [DBUG] [agent_sub_stages.internal:167]: ready to request llm provider
[2026-04-07 14:54:36.504] [Core] [DBUG] [agent_sub_stages.internal:190]: acquired session lock for llm request
[2026-04-07 14:54:36.795] [Core] [DBUG] [core.astr_main_agent_resources:463]: [知识库] 使用全局配置，知识库数量: 0
[2026-04-07 14:54:36.796] [Core] [DBUG] [pipeline.context_utils:95]: hook(OnLLMRequestEvent) -> astrbot - decorate_llm_req
[2026-04-07 14:54:36.796] [Core] [DBUG] [pipeline.context_utils:95]: hook(OnLLMRequestEvent) -> astrbot-web-searcher - edit_web_search_tools
[2026-04-07 14:54:36.796] [Core] [DBUG] [runners.base:64]: Agent state transition: AgentState.IDLE -> AgentState.RUNNING
[2026-04-07 14:54:36.797] [Core] [DBUG] [runners.tool_loop_agent_runner:379]: [BefCompact] RunCtx.messages -> [8] system,user,assistant,user,assistant,user,assistant,user
[2026-04-07 14:54:36.797] [Core] [DBUG] [runners.tool_loop_agent_runner:379]: [AftCompact] RunCtx.messages -> [8] system,user,assistant,user,assistant,user,assistant,user
[2026-04-07 14:54:36.798] [Core] [WARN] [v4.22.3] [sources.gemini_source:206]: 已启用原生工具，函数工具将被忽略
[2026-04-07 14:54:37.783] [Core] [WARN] [v4.22.3] [runners.tool_loop_agent_runner:350]: Chat Model google_gemini/gemini-2.5-flash request error: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'Function calling config is set without function_declarations.', 'status': 'INVALID_ARGUMENT'}}
Traceback (most recent call last):
  File "/home/qqbot/AstrBot/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 305, in _iter_llm_responses_with_fallback
    async for attempt in retrying:
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/asyncio/__init__.py", line 166, in __anext__
    do = await self.iter(retry_state=self._retry_state)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/asyncio/__init__.py", line 153, in iter
    result = await action(retry_state)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/_utils.py", line 99, in inner
    return call(*args, **kwargs)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/__init__.py", line 400, in <lambda>
    self._add_action_func(lambda rs: rs.outcome.result())
  File "/home/qqbot/.pyenv/versions/3.10.12/lib/python3.10/concurrent/futures/_base.py", line 451, in result
    return self.__get_result()
  File "/home/qqbot/.pyenv/versions/3.10.12/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
    raise self._exception
  File "/home/qqbot/AstrBot/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 309, in _iter_llm_responses_with_fallback
    async for resp in self._iter_llm_responses(
  File "/home/qqbot/AstrBot/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 272, in _iter_llm_responses
    yield await self.provider.text_chat(**payload)
  File "/home/qqbot/AstrBot/astrbot/core/provider/sources/gemini_source.py", line 821, in text_chat
    if await self._handle_api_error(e, keys):
  File "/home/qqbot/AstrBot/astrbot/core/provider/sources/gemini_source.py", line 129, in _handle_api_error
    raise e
  File "/home/qqbot/AstrBot/astrbot/core/provider/sources/gemini_source.py", line 819, in text_chat
    return await self._query(payloads, func_tool)
  File "/home/qqbot/AstrBot/astrbot/core/provider/sources/gemini_source.py", line 587, in _query
    result = await self.client.models.generate_content(
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/models.py", line 7009, in generate_content
    return await self._generate_content(
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/models.py", line 5848, in _generate_content
    response = await self._api_client.async_request(
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/_api_client.py", line 1432, in async_request
    result = await self._async_request(
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/_api_client.py", line 1365, in _async_request
    return await self._async_retry(  # type: ignore[no-any-return]
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/asyncio/__init__.py", line 111, in __call__
    do = await self.iter(retry_state=retry_state)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/asyncio/__init__.py", line 153, in iter
    result = await action(retry_state)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/_utils.py", line 99, in inner
    return call(*args, **kwargs)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/__init__.py", line 420, in exc_check
    raise retry_exc.reraise()
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/__init__.py", line 187, in reraise
    raise self.last_attempt.result()
  File "/home/qqbot/.pyenv/versions/3.10.12/lib/python3.10/concurrent/futures/_base.py", line 451, in result
    return self.__get_result()
  File "/home/qqbot/.pyenv/versions/3.10.12/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
    raise self._exception
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/tenacity/asyncio/__init__.py", line 114, in __call__
    result = await fn(*args, **kwargs)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/_api_client.py", line 1310, in _async_request_once
    await errors.APIError.raise_for_async_response(response)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/errors.py", line 203, in raise_for_async_response
    await cls.raise_error_async(status_code, response_json, response)
  File "/home/qqbot/AstrBot/venv/lib/python3.10/site-packages/google/genai/errors.py", line 225, in raise_error_async
    raise ClientError(status_code, response_json, response)
google.genai.errors.ClientError: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'Function calling config is set without function_declarations.', 'status': 'INVALID_ARGUMENT'}}
[2026-04-07 14:54:37.792] [Core] [DBUG] [runners.base:64]: Agent state transition: AgentState.RUNNING -> AgentState.ERROR
[2026-04-07 14:54:37.793] [Core] [DBUG] [result_decorate.stage:165]: hook(on_decorating_result) -> astrbot_plugin_wakepro - on_message
[2026-04-07 14:54:37.793] [Core] [DBUG] [result_decorate.stage:165]: hook(on_decorating_result) -> astrbot_plugin_outputpro - on_message
[2026-04-07 14:54:37.796] [Core] [INFO] [respond.stage:184]: Prepare to send - 逸木/872778579: LLM 响应错误: All chat models failed: ClientError: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'Function calling config is set without function_declarations.', 'status': 'INVALID_ARGUMENT'}} 
[2026-04-07 14:54:38.048] [Core] [DBUG] [pipeline.context_utils:95]: hook(OnAfterMessageSentEvent) -> astrbot - after_message_sent
[2026-04-07 14:54:38.049] [Core] [DBUG] [pipeline.scheduler:93]: pipeline 执行完毕。

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。

[dosubot]

Hi @tusky94! I'm Dosu and I’m helping the AstrBot team.

这是一个已确认的 bug，根因在 gemini_source.py 的 _prepare_query_config 方法中 [1]。

问题原因： 当启用原生工具（google_search / url_context）时，tool_list 中只包含原生工具而没有 function_declarations。但代码在构建 ToolConfig 时，判断条件 if tools and tool_list: 仍然为 True（因为 tools 参数从调用方传入不为空，tool_list 中有原生工具），于是错误地设置了 FunctionCallingConfig。Gemini API 要求 FunctionCallingConfig 必须搭配 function_declarations 使用，否则就会返回 400 INVALID_ARGUMENT [2]。

修复方向： 在设置 FunctionCallingConfig 之前，应检查 tool_list 中是否实际包含 function_declarations，而不是仅判断 tool_list 是否非空。如果只有原生工具（google_search、url_context、code_execution），则不应创建 FunctionCallingConfig。大致修改如下：

# 检查 tool_list 中是否存在 function_declarations
has_func_declarations = any(
    getattr(t, 'function_declarations', None) for t in tool_list
) if tool_list else False

tool_config = None
if tools and has_func_declarations:
    tool_config = types.ToolConfig(
        function_calling_config=types.FunctionCallingConfig(
            mode=(
                types.FunctionCallingConfigMode.ANY
                if tool_choice == "required"
                else types.FunctionCallingConfigMode.AUTO
            )
        )
    )

这个 bug 在 PR #7101 引入 tool_choice 支持时产生，影响 _query 和 _query_stream 两个路径（它们共用 _prepare_query_config）。

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}