fix(core): handle missing web search query params

[whatevertogo]

Fixes #7499.

This PR prevents built-in web search tools from crashing when the LLM emits an empty or invalid query argument. The original issue showed web_search_tavily being called with {}, which raised KeyError: 'query' and fed an error back into the tool loop repeatedly.

Modifications / 改动点

• This is NOT a breaking change. / 这不是一个破坏性变更。

• Validate query before building provider payloads for Tavily, BoCha, Brave, Firecrawl, and Baidu AI Search.

• Return a clear tool error when query is missing, null, or blank instead of raising KeyError/AttributeError.

• Keep normal non-empty queries flowing into each provider payload unchanged, aside from trimming surrounding whitespace.

• Add a regression test covering the affected built-in web search tools.

Screenshots or Test Results / 运行截图或测试结果

uv run pytest tests/unit/test_web_search_tools.py -q

...............                                                          [100%]
15 passed in 2.35s

uv run ruff check astrbot/core/tools/web_search_tools.py tests/unit/test_web_search_tools.py

All checks passed!

Checklist / 检查清单

• 😊 If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
  / 如果 PR 中有新加入的功能，已经通过 Issue / 邮件等方式和作者讨论过。

• 👀 My changes have been well-tested, and "Verification Steps" and "Screenshots" have been provided above.
  / 我的更改经过了良好的测试，并已在上方提供了“验证步骤”和“运行截图”。

• 🤓 I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in requirements.txt and pyproject.toml.
  / 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到 requirements.txt 和 pyproject.toml 文件相应位置。

• 😮 My changes do not introduce malicious code.
  / 我的更改没有引入恶意代码。

Summary by Sourcery

Handle invalid or missing search queries in built-in web search tools to avoid crashes and return clear error messages.

Bug Fixes:

• Prevent Tavily, BoCha, Brave, Firecrawl, and Baidu web search tools from raising errors when the LLM omits or sends an empty/invalid query parameter.

Tests:

• Add regression tests ensuring each built-in web search tool returns a friendly error string when the query argument is missing, null, or blank.

[gemini-code-assist]

Code Review

This pull request introduces validation for the query parameter across several web search tools, including Tavily, BoCha, Brave, Firecrawl, and Baidu, ensuring that empty or missing queries return a friendly error message instead of causing a crash. Corresponding unit tests were added to verify this behavior. Feedback suggests refactoring the duplicated validation logic into a shared helper function to improve maintainability and removing a redundant str() conversion in the Baidu tool implementation.

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• The query normalization and error handling logic is duplicated across all the web search tools; consider extracting this into a shared helper (e.g., normalize_query(kwargs) returning either a trimmed query or a standardized error) to reduce repetition and keep behavior consistent.
• In the Baidu tool test setup you have to special-case websearch_baidu_app_builder_key because it uses a string while the others use lists; aligning the provider_settings structure across tools would simplify this and avoid hidden assumptions about value types.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The `query` normalization and error handling logic is duplicated across all the web search tools; consider extracting this into a shared helper (e.g., `normalize_query(kwargs)` returning either a trimmed query or a standardized error) to reduce repetition and keep behavior consistent.
- In the Baidu tool test setup you have to special-case `websearch_baidu_app_builder_key` because it uses a string while the others use lists; aligning the provider_settings structure across tools would simplify this and avoid hidden assumptions about value types.

## Individual Comments

### Comment 1
<location path="astrbot/core/tools/web_search_tools.py" line_range="427" />
<code_context>
         if not provider_settings.get("websearch_tavily_key", []):
             return "Error: Tavily API key is not configured in AstrBot."

+        query = str(kwargs.get("query") or "").strip()
+        if not query:
+            return "Error: 'query' parameter is required but was not provided."
</code_context>
<issue_to_address>
**issue (complexity):** Consider extracting the repeated `query` parsing and validation into a shared helper function and calling it from each tool’s `call` method to avoid duplication.

You can reduce duplication and keep behavior identical by centralizing the `query` extraction/validation into a small helper, then using it in each tool.

For example, at module level:

```python
def _extract_query(kwargs: dict) -> str | None:
    query = str(kwargs.get("query") or "").strip()
    if not query:
        return None
    return query
```

Then in each `call` method:

```python
async def call(self, context, **kwargs) -> ToolExecResult:
    _, provider_settings, _ = _get_runtime(context)
    if not provider_settings.get("websearch_tavily_key", []):
        return "Error: Tavily API key is not configured in AstrBot."

    query = _extract_query(kwargs)
    if query is None:
        return "Error: 'query' parameter is required but was not provided."

    # rest of logic unchanged...
    payload = {
        "query": query,
        "max_results": kwargs.get("max_results", 7),
        "include_favicon": True,
        "search_depth": search_depth,
        "topic": topic,
    }
```

For Baidu:

```python
async def call(self, context, **kwargs) -> ToolExecResult:
    _, provider_settings, _ = _get_runtime(context)
    if not provider_settings.get("websearch_baidu_app_builder_key", ""):
        return "Error: Baidu AI Search API key is not configured in AstrBot."

    query = _extract_query(kwargs)
    if query is None:
        return "Error: 'query' parameter is required but was not provided."

    top_k = int(kwargs.get("top_k", 10))
    # ... bounds logic unchanged ...

    payload = {
        "messages": [{"role": "user", "content": query[:72]}],
        "search_source": "baidu_search_v2",
        "resource_type_filter": [{"type": "web", "top_k": top_k}],
    }
```

This keeps all current behavior (string coercion, stripping, error text) but moves the logic to a single place, lowering maintenance and cognitive overhead.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[Copilot]

Pull request overview

Fixes a crash loop in AstrBot’s built-in web search tools when the LLM calls them with a missing/blank query, returning a friendly tool error instead of raising exceptions.

Changes:

• Add query normalization/validation (missing/None/blank) in Tavily, BoCha, Brave, Firecrawl, and Baidu search tools.
• Ensure provider payloads use the normalized query (trimmed) rather than direct kwargs["query"] access.
• Add a regression test covering invalid query inputs across the affected tools.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
astrbot/core/tools/web_search_tools.py	Adds defensive query validation to prevent KeyError/AttributeError and standardizes payload building.
tests/unit/test_web_search_tools.py	Adds a parameterized async regression test to ensure tools return a friendly error string when query is invalid.