fix: dedupe preset messages

[Raven95676]

修复预设对话重复注入的问题

Modifications / 改动点

添加_no_save私有字段

• 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

---

Checklist / 检查清单

• 😊 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。/ If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
• 👀 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”。/ My changes have been well-tested, and "Verification Steps" and "Screenshots" have been provided above.
• 🤓 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了 requirements.txt 和 pyproject.toml 文件相应位置。/ 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.
• 😮 我的更改没有引入恶意代码。/ My changes do not introduce malicious code.

Summary by Sourcery

确保预设人物对话消息被视为不持久化的数据，这样它们就不会在会话历史中被反复重新注入。

Bug 修复：

• 通过遵守消息上的非持久化标记，防止预设人物对话消息被保存到会话历史中并从中被反复重新注入。

功能增强：

• 在 Message 上引入私有属性 _no_save，并在请求上下文中进行传递，以控制哪些助手和用户消息需要被持久化。

Original summary in English

Summary by Sourcery

Ensure preset persona dialogue messages are treated as non-persisted so they are not repeatedly re-injected into conversation history.

Bug Fixes:

• Prevent preset persona dialogue messages from being saved to and repeatedly re-injected from conversation history by honoring a non-persisted flag on messages.

Enhancements:

• Introduce a private _no_save attribute on Message and propagate it through request contexts to control which assistant and user messages are persisted.

Bug 修复：

• 确保预设人格（persona）对话消息被标记为不持久化（non-persisted），从而不会被反复重新注入到对话历史中。

增强功能：

• 在 Message 上引入私有的 _no_save 标志，并通过请求上下文进行传递，以控制哪些消息需要被持久化。

Original summary in English

Summary by Sourcery

确保预设人物对话消息被视为不持久化的数据，这样它们就不会在会话历史中被反复重新注入。

Bug 修复：

• 通过遵守消息上的非持久化标记，防止预设人物对话消息被保存到会话历史中并从中被反复重新注入。

功能增强：

• 在 Message 上引入私有属性 _no_save，并在请求上下文中进行传递，以控制哪些助手和用户消息需要被持久化。

Original summary in English

Summary by Sourcery

Ensure preset persona dialogue messages are treated as non-persisted so they are not repeatedly re-injected into conversation history.

Bug Fixes:

• Prevent preset persona dialogue messages from being saved to and repeatedly re-injected from conversation history by honoring a non-persisted flag on messages.

Enhancements:

• Introduce a private _no_save attribute on Message and propagate it through request contexts to control which assistant and user messages are persisted.

[dosubot]

Related Documentation

Checked 1 published document(s) in 1 knowledge base(s). No updates required.

^{How did I do? Any feedback?}  

[sourcery-ai]

Hey - 我在这里给出了一些总体反馈：

• 在 tool_loop_agent_runner.reset 中，只有当 request.contexts 的元素是 dict 时，_no_save 才会被向下传递；建议在上下文元素已经是 Message 实例时同样保留 _no_save（例如通过 hasattr(msg, "_no_save") 检查），这样在这些场景下该标志就不会丢失。
• 由于 _no_save 被声明为 PrivateAttr，直接从外部的 dict 数据写入该字段会在一定程度上破坏封装；你可能希望将这类映射逻辑集中处理（例如通过一个 helper 或 factory），这样如果以后私有属性的处理方式有变化，相关行为会更容易审查和调整。

给 AI Agents 的提示

Please address the comments from this code review:

## Overall Comments
- In `tool_loop_agent_runner.reset`, `_no_save` is only propagated when `request.contexts` items are dicts; consider also preserving `_no_save` when the context item is already a `Message` instance (e.g., via `hasattr(msg, "_no_save")`) so the flag isn't lost in those cases.
- Since `_no_save` is declared as a `PrivateAttr`, directly setting it from external dict data slightly breaks the encapsulation; you might want to centralize this mapping (e.g., via a helper or factory) so the behavior is easier to audit and adjust if the private attribute handling changes.

---

Sourcery 对开源项目永久免费——如果你觉得我们的评审有帮助，欢迎分享给更多人 ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{帮我变得更有用！请在每条评论上点击 👍 或 👎，我会根据你的反馈改进后续的评审质量。}

Original comment in English

Hey - I've left some high level feedback:

• In tool_loop_agent_runner.reset, _no_save is only propagated when request.contexts items are dicts; consider also preserving _no_save when the context item is already a Message instance (e.g., via hasattr(msg, "_no_save")) so the flag isn't lost in those cases.
• Since _no_save is declared as a PrivateAttr, directly setting it from external dict data slightly breaks the encapsulation; you might want to centralize this mapping (e.g., via a helper or factory) so the behavior is easier to audit and adjust if the private attribute handling changes.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In `tool_loop_agent_runner.reset`, `_no_save` is only propagated when `request.contexts` items are dicts; consider also preserving `_no_save` when the context item is already a `Message` instance (e.g., via `hasattr(msg, "_no_save")`) so the flag isn't lost in those cases.
- Since `_no_save` is declared as a `PrivateAttr`, directly setting it from external dict data slightly breaks the encapsulation; you might want to centralize this mapping (e.g., via a helper or factory) so the behavior is easier to audit and adjust if the private attribute handling changes.

---

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.}