fix: route ExitPlanMode through request_permission instead of - #31
Merged
Conversation
elicitation form ExitPlanMode previously went through elicitation/create when the client supported it, which surfaced a generic "input request / waiting for input" shell that reads wrong for a plan-approval flow. Plan approval is a permission decision, not structured input — route it through session/request_permission like claude-agent-acp does, so it renders as the same Approve/Reject dialog as tool permission. AskUserQuestion still uses elicitation/create (it is the actual input case). Trade-off: the user can no longer attach free-text feedback when rejecting. They can give reasons in the next normal message instead.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
elicitation form
ExitPlanMode previously went through elicitation/create when the client supported it, which surfaced a generic "input request / waiting for input"
shell that reads wrong for a plan-approval flow. Plan approval is a permission decision, not structured input — route it through session/request_permission like claude-agent-acp does, so it renders as the
same Approve/Reject dialog as tool permission.
AskUserQuestion still uses elicitation/create (it is the actual input case).
Trade-off: the user can no longer attach free-text feedback when rejecting.
They can give reasons in the next normal message instead.