[magentaqin]

Modifications / 改动点

Add Google News search support through SerpApi so agents can retrieve current news articles with structured metadata and source links.

• Migrated shared SerpApi requests to the official Python SDK.
• Added the news_search_serpapi tool backed by the Google News API.
• Added article title, publisher, authors, publication time, snippet, thumbnail URL, and source URL to the tool output.
• Added support for country, language, and result-limit parameters.
• Registered the tool in agent and chat workflows.
• Updated configuration metadata, translations, changelog, and documentation.
• Added unit tests for result mapping, grouped stories, deduplication, validation, SDK responses, and API key rotation.

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

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

1）automated tests：

2）End-to-end verification
Configured an OpenAI chat model and a SerpApi API key in AstrBot, then sent the following request through the WebUI:

• Google Search API

- Google News API - Google Image Light API - Google Finance API - Google Scholar API -SerpApi Dashboard Searches Records

---

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 checked the affected WebUI instructions and screenshots in docs/zh and docs/en against the changed navigation, page structure, and labels, and updated them in this PR (or explained why no documentation update is needed). For renamed, moved, or merged entry points, I included an old entry → new entry mapping in the documentation and changelog.
  / 我已对照变化后的 WebUI 入口、页面结构和术语，核对并在本 PR 中更新 docs/zh 和 docs/en 的相关操作说明与截图（或说明无需更新文档的原因）。入口改名、移动或合并时，已在文档和 changelog 中补充 旧入口 → 新入口 对照。

• 🤓 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

Enable agents to retrieve current, citation-ready news articles through SerpApi Google News.

New Features:

• Add a SerpApi-backed Google News search tool that returns structured article metadata and source links.
• Expose Google News search in agent, chat, and citation workflows with country, language, and result-limit options.

Enhancements:

• Adopt the official SerpApi Python SDK for shared SerpApi requests.

Documentation:

• Update English and Chinese configuration and web-search documentation to describe SerpApi Google News support.

Tests:

• Add coverage for Google News result mapping, grouped stories, deduplication, validation, credential handling, retries, and tool registration.

Chores:

• Update configuration labels, translations, and the unreleased changelog for the new capability.

[sourcery-ai]

Hey - I've found 2 issues

Prompt for AI Agents

Please address the comments from this code review:

## Individual Comments

### Comment 1
<location path="astrbot/core/tools/web_search_tools.py" line_range="9" />
<code_context>
 from urllib.parse import quote, urlsplit

 import aiohttp
+import serpapi
 from pydantic import Field
 from pydantic.dataclasses import dataclass as pydantic_dataclass
</code_context>
<issue_to_address>
**Installations fail at startup**

When astrBot is installed from requirements.txt rather than resolving dependencies from pyproject.toml, `web_search_tools.py` imports `serpapi` unconditionally, but `requirements.txt` omits it, so startup and smoke-test imports raise `ModuleNotFoundError`.

Add the SerpApi dependency to `requirements.txt` so installations using that manifest can import the search tools.

Also at `pyproject.toml:77`.
</issue_to_address>

### Comment 2
<location path="astrbot/core/tools/web_search_tools.py" line_range="697" />
<code_context>
+                    {
+                        "title": article.get("title") or "",
+                        "url": source_url,
+                        "snippet": article.get("snippet") or "",
+                        "source": source.get("name") or source.get("title") or "",
+                        "authors": source.get("authors") or [],
</code_context>
<issue_to_address>
**News links can hijack the dashboard tab**

When an attacker-controlled publisher URL appears in Google News results and a user clicks its citation, the publisher URL is returned as a citation and the dashboard opens it with `window.open(url, "_blank")` without disabling `window.opener`; a clicked attacker-controlled article can navigate the original AstrBot tab to a phishing page.

Open citation links with `noopener` (and preferably `noreferrer`) or use an anchor with a safe `rel` attribute.
</issue_to_address>

Sourcery assessment

Approval pending. 2 findings to address first.

Blocking findings: astrbot/core/tools/web_search_tools.py:9, astrbot/core/tools/web_search_tools.py:697

---

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

• X
• Mastodon
• LinkedIn
• Facebook

[Soulter]

Hi, Thanks for your contribution! Is it possible to make requests to SerpApi directly via the HTTP API? This would avoid the need to include a SerpApi python package, helping to keep the main codebase clean.

[magentaqin]

No problem! I just updated the code!