fix: resolve the destructive action bug - #1103
Merged
Roopan-Microsoft merged 1 commit intoJul 20, 2026
Merged
Conversation
Dhruvkumar-Microsoft
requested review from
Avijit-Microsoft,
Fr4nc3,
Roopan-Microsoft,
aniaroramsft,
dgp10801,
nchandhi and
toherman-msft
as code owners
July 17, 2026 11:13
Roopan-Microsoft
approved these changes
Jul 20, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
This pull request strengthens and clarifies how team scope and agent capabilities are evaluated and communicated throughout the orchestration system. The changes ensure that requests are only accepted if they both match a team's domain and can actually be fulfilled by its agents, and that users receive clear, accurate feedback when requests are out of scope—especially for actions the agents cannot perform (such as deleting or modifying data). Messaging and prompt templates have been updated across the codebase to reflect these stricter, more explicit policies.
Scope and Capability Evaluation Policy Updates:
_evaluate_team_scope(orchestration_manager.py) now instructs the classifier to consider both the team's specialization and the actual capabilities of its agents, explicitly distinguishing between "domain" and "capability" out-of-scope cases. It also clarifies that destructive or state-changing actions are not allowed unless explicitly supported.plan_review_helpers.pywas updated to require that requests must be both within an agent's domain and ask for actions the agents can actually perform, with explicit instructions for handling unsupported actions and clearer out-of-scope messaging.User Messaging and Logging Improvements:
_handle_out_of_scope) now informs users whether a request is out of scope due to domain or unsupported action, and always clarifies that no data was changed.Does this introduce a breaking change?
How to Test
What to Check
Verify that the following are valid
Other Information