docs: fix human_input oversight claims in security guide - #7096
Draft
theCyberTech wants to merge 1 commit into
Draft
docs: fix human_input oversight claims in security guide#7096theCyberTech wants to merge 1 commit into
theCyberTech wants to merge 1 commit into
Conversation
Section 5 of the Security Best Practices guide incorrectly framed human_input=True as pre-execution approval for irreversible tools. Clarify that it gates final answer review after tools have run, and point readers to tool hooks, execution hooks, and @human_feedback for true pre-execution gates. Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: trueThanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes Defect 2 in the Security Best Practices guide (§5): the original draft incorrectly framed
human_input=Trueas "explicit human approval before execution" for irreversible tools and external side effects.Per the Task contract in
task.py,human_inputgates review of the final answer before it is accepted/finalized — not tool execution. An agent on a task withhuman_input=Truecan still run destructive tools before any human sees the run.Changes
docs/edge/en/guides/advanced/security-best-practices.mdxwith corrected §5:human_input=Trueactually does (post-run output review)@human_feedbackfor true pre-execution approval gatesar,ko, andpt-BRdocs/docs.jsonfor all edge localesRelated
human_inputfield description: "Whether the task should have a human review the final answer of the agent"