-
Notifications
You must be signed in to change notification settings - Fork 6
docs(security+automation+settings): P0 optimization #43
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -33,6 +33,8 @@ OAuth、CLI 或订阅登录可能由对应的外部工具或操作系统机制 | |
|
|
||
| ## 第三方 API 的数据流向 | ||
|
|
||
|  | ||
|
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
The newly embedded diagram says all data stays on the local device and the cloud does not access local data, but this same section immediately explains that conversation messages, relevant context such as file-content fragments, and system prompts are sent to the configured AI provider. On pages explaining third-party API data flow, that visual overstates the privacy boundary for any online provider and can lead users to believe no prompt/context leaves the device; please update or remove it, or show the selected request payload leaving the device. Useful? React with 👍 / 👎. |
||
|
|
||
| 当智能体调用 AI 模型时,数据会发送到你配置的 AI 供应商。以下是你需要了解的: | ||
|
|
||
| ``` | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The image claims low/medium/high/critical risks require 1/2/3/4+ confirmation steps with supervisor/manager/multiple approvals, while the surrounding page documents DesireCore's actual behavior as automatic execution for low risk and a single confirmation dialog with more detail or prominence for higher risks. Since the repo docs do not define these multi-person approval workflows, adding this visual misdocuments the product and can make readers expect approval features that do not exist.
Useful? React with 👍 / 👎.