story-kit: start 62_story_allow_frontend_ui_to_accept_permissions_requests
This commit is contained in:
@@ -0,0 +1,26 @@
|
||||
---
|
||||
name: Agent Permission Prompts in Web UI
|
||||
test_plan: pending
|
||||
---
|
||||
|
||||
# Story 62: Agent Permission Prompts in Web UI
|
||||
|
||||
## User Story
|
||||
|
||||
As a user interacting with an agent through the web UI, I want to be prompted for permission approvals (e.g. file writes, commits) so that the agent can complete tasks that require elevated permissions without getting blocked.
|
||||
|
||||
Right now, the web UI does not have any way of the user allowing permissions requests, so dev processes are basically blocked.
|
||||
|
||||
## Acceptance Criteria
|
||||
|
||||
- [ ] When an agent action requires permission (e.g. writing to a file, committing), the web UI surfaces a prompt to the user
|
||||
- [ ] The user can approve or deny the permission request from the UI
|
||||
- [ ] On approval, the agent continues with the requested action
|
||||
- [ ] On denial, the agent receives the denial and adjusts its approach
|
||||
- [ ] Permission prompts display enough context (file path, action type) for the user to make an informed decision
|
||||
|
||||
|
||||
## Out of Scope
|
||||
|
||||
- Bulk/blanket permission grants (e.g. "allow all writes to this directory")
|
||||
- Persisting permission decisions across sessions
|
||||
Reference in New Issue
Block a user