fix(embedding): use removesuffix instead of rstrip to prevent over-trimming URLs

[Izayoi9]

动机

修复 #7025

之前在 #6863 中提交的修复使用了 rstrip() 方法来移除 URL 末尾的 /embeddings 路径，但 rstrip() 是字符集操作而非字符串移除操作，会误删 URL 末尾属于该字符集的任意字符。

问题表现

当 API Base URL 以 /embeddings 字符集中的字符结尾时（如 siliconflow.cn 的 n），该字符会被误删：

• 输入：https://api.siliconflow.cn
• 错误结果：https://api.siliconflow.c/v1（n 被删掉）
• 正确结果：https://api.siliconflow.cn/v1

修复方案

将 rstrip() 改为 removesuffix()，后者只在字符串以指定后缀结尾时才移除，避免误删字符。

Modifications / 改动点

• 将 astrbot/core/provider/sources/openai_embedding_source.py 中的 .rstrip("/") 和 .rstrip("/embeddings") 改为 .removesuffix("/") 和 .removesuffix("/embeddings")

• 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

本地测试日志：

[OpenAI Embedding] openai_embedding Using API Base: https://api.siliconflow.cn/v1

URL 中的 n 不再被误删。

---

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

Bug Fixes:

• Fix incorrect removal of trailing characters from embedding API base URLs by replacing character-based stripping with suffix-based removal.

[sourcery-ai]

Hey - I've left some high level feedback:

• Using str.removesuffix changes the minimum required Python version to 3.9; if this project still supports 3.8 or earlier, consider replacing it with an equivalent helper (e.g., a small remove_suffix utility) to avoid breaking older runtimes.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Using `str.removesuffix` changes the minimum required Python version to 3.9; if this project still supports 3.8 or earlier, consider replacing it with an equivalent helper (e.g., a small `remove_suffix` utility) to avoid breaking older runtimes.

---

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.}

[gemini-code-assist]

Code Review

This pull request updates the URL sanitization logic in the OpenAI embedding source by replacing .rstrip() with .removesuffix() to prevent unintended character stripping. The reviewer suggests using .rstrip("/") instead of .removesuffix("/") to more robustly handle multiple trailing slashes while maintaining the use of .removesuffix("/embeddings") to fix the logic bug.

[gemini-code-assist]

感谢您修复这个 bug！使用 removesuffix 确实是正确的做法。

这里有一个小建议：只将有问题的 .rstrip("/embeddings") 改为 .removesuffix("/embeddings")，并保留 .rstrip("/") 可能更好。

原因是 .rstrip("/") 可以移除末尾所有的斜杠（例如 //），比 .removesuffix("/") 只移除一个斜杠更具鲁棒性。rstrip 的问题仅在于当参数是多字符字符串时，它会将其作为字符集处理；对于单个字符 / 则是安全且符合预期的。

这样修改后，代码既能修复 bug，又能更好地处理用户可能输入的多余斜杠。

Suggested change

	.removesuffix("/")
	.removesuffix("/embeddings")
	.rstrip("/")
	.removesuffix("/embeddings")

[Izayoi9]

自己拉的史自己修（1/1）

.removesuffix()方法只有与后缀结尾精确匹配时才会移除字符，这个方法是python3.9引入的，在astrbot目前版本完全适用。