-
Notifications
You must be signed in to change notification settings - Fork 0
Add AI Review auto-start and Problems tab UI #4
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
Conversation
Implement auto-execution of AI Review when development completes and add a new Problems tab in task detail panel to display AI Review findings with selection and action capabilities. Includes accordion-style UI for severity-grouped findings, individual and group selection, and Fix/Skip actions. 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <[email protected]>
|
Caution Review failedThe pull request is closed. 📝 WalkthroughWalkthroughThis pull request introduces an auto-execution workflow for tasks and a new ProblemsTab component for displaying AI review findings. The auto-execute feature triggers task execution when certain events occur, while ProblemsTab enables users to view, filter, and manage code review findings grouped by severity with bulk actions. Changes
Sequence DiagramsequenceDiagram
participant App
participant useEventStream
participant SSEEvent as SSE Event
participant useExecuteTask
participant API as Tasks API
App->>useEventStream: Pass onAutoExecute handler
SSEEvent->>useEventStream: Task status changed (in_progress → ai_review)
useEventStream->>useEventStream: Check status transition
alt Status is ai_review
useEventStream->>App: Trigger onAutoExecute(taskId)
App->>useExecuteTask: Call executeTask.mutate({ id: taskId })
useExecuteTask->>API: POST /tasks/{taskId}/execute
API-->>useExecuteTask: Success
useExecuteTask-->>App: Task executed
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Poem
✨ Finishing touches
📜 Recent review detailsConfiguration used: defaults Review profile: CHILL Plan: Pro ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (6)
Comment |
Greptile SummaryThis PR implements automatic AI Review execution when development completes and adds a new Problems tab for managing review findings. Key Changes:
Issues Found:
Confidence Score: 4/5
Important Files Changed
Sequence DiagramsequenceDiagram
participant User
participant TaskDetailPanel
participant Backend
participant EventStream
participant App
participant ProblemsTab
Note over User,ProblemsTab: Development Phase Completes
Backend->>EventStream: task.status_changed (in_progress → ai_review)
EventStream->>App: onAutoExecute(taskId)
App->>Backend: POST /api/tasks/{id}/execute
Backend-->>App: 202 Accepted
Note over Backend: AI Review Executes
Backend->>EventStream: session.started
Backend->>EventStream: session.ended (success)
Backend->>EventStream: task.status_changed (ai_review → review)
Note over User,ProblemsTab: User Opens Task Detail
TaskDetailPanel->>Backend: GET /api/tasks/{id}/findings
Backend-->>TaskDetailPanel: findings data
TaskDetailPanel->>TaskDetailPanel: hasFindings = true
TaskDetailPanel->>ProblemsTab: render with findings
Note over User,ProblemsTab: User Interacts with Findings
User->>ProblemsTab: Select findings
User->>ProblemsTab: Click "Fix selected"
ProblemsTab->>Backend: POST /api/tasks/{id}/fix-findings
Backend-->>ProblemsTab: 202 Accepted
ProblemsTab->>ProblemsTab: Invalidate queries & clear selection
alt User skips findings
User->>ProblemsTab: Click "Skip"
ProblemsTab->>Backend: POST /api/tasks/{id}/skip-findings
Backend-->>ProblemsTab: 200 OK
ProblemsTab->>ProblemsTab: Invalidate task query only
end
|
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.
6 files reviewed, 1 comment
| const skipFindings = useSkipFindings({ | ||
| mutation: { | ||
| onSuccess: () => { | ||
| void queryClient.invalidateQueries({ queryKey: getListTasksQueryKey() }); | ||
| toast.success("Findings skipped, task moved to review"); | ||
| }, | ||
| onError: () => { | ||
| toast.error("Failed to skip findings"); | ||
| }, | ||
| }, | ||
| }); |
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.
logic: missing query invalidation - should invalidate findings query like fixFindings does on line 73, otherwise UI may show stale findings after skip
Prompt To Fix With AI
This is a comment left during a code review.
Path: frontend/src/components/task-detail/ProblemsTab.tsx
Line: 83:93
Comment:
**logic:** missing query invalidation - should invalidate findings query like `fixFindings` does on line 73, otherwise UI may show stale findings after skip
How can I resolve this? If you propose a fix, please make it concise.
Summary
Test plan
🤖 Generated with Claude Code
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.