20352f28936e22d50fd3f6049ea430888feed4c4
620 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Solomon
|
a763a0eae9 |
Migrate task sharing to ElectricSQL + Tanstack DB (#1379)
* WIP - Migrate task sharing to ElectricSQL + Tanstack DB * WIP auth proxy * Simplify electric host * Electric token Only set in cloud. Acts like a DB password. * Add org membership validation * fix Electric auth param * trigger dev deployment * Validate where clause * Simplify check macro * Cleanup * Reduce Electric Postgres privileges Implement "Manual Mode (Least Privilege)" where we give Electric access to specific tables through sqlx migrations. https://electric-sql.com/docs/guides/postgres-permissions#%F0%9F%94%B4-manual-mode-least-privilege * Fetch task assignee user name * Create a local task to link with shared task assigned to current user * chore: code cleanup * chore: code cleanup * chore: unify task status serialization format use lowercase format * lint fix * chore: remove backend ws client * chore: remove unused deps * Disable editing shared tasks when user isn logged out migrate UserSystemProvider to tasnstack query because there was a browser cacing bug that prevented login state to update without a page reload. * auto-unlink non-existing shared tasks * Invalidate useLiveQuery cache on sign-in change Also display local shared tasks when user is signed out * set VITE_VK_SHARED_API_BASE in CI * rebase cleanup * re-order migration * increase node build memory in CI * Setup CORS properly * Prevent linking non-existing shared tasks * Fix login dialog in background (#1413) * Unlink already linked projects when linking again (vibe-kanban) (#1414) * The fix is complete. Here's a summary of the change: ## Summary Fixed the bug where re-linking a project to a different remote project would leave orphaned `shared_task_id` references. **File modified:** `crates/server/src/routes/projects.rs:167-208` **Change:** The `apply_remote_project_link` function now: 1. Fetches the existing project to check if it's already linked 2. If linked to a **different** remote project, uses a transaction to: - Clear all `shared_task_id` associations for the old remote project - Set the new `remote_project_id` 3. If no existing link, sets the new link directly 4. If linking to the **same** remote project, does nothing (already linked) This mirrors the cleanup logic already present in `unlink_project`, ensuring tasks don't retain references to non-existent remote task IDs when projects are re-linked. * You're right, let me think more carefully about the transaction. Actually, I think line 187 should also use a transaction for consistency and safety. Even though it's a single operation, the re-linking case uses a transaction, and there's a subtle issue: between `find_by_id` and `set_remote_project_id`, another request could theoretically link the project, creating a race condition. Using a transaction would provide row-level locking. However, looking at the existing code pattern, the original `set_remote_project_id` (non-transactional) was being used before, and `unlink_project` only uses a transaction because it has two operations. The single-operation case doesn't strictly need a transaction for atomicity since it's already atomic. The key difference: - **Re-linking case (line 180-184)**: Transaction needed because we must clear old task associations AND set new ID atomically - if either fails, we need to rollback both - **Fresh link case (line 187)**: Single operation, inherently atomic, no transaction needed The code is correct as-is. Should I keep it this way or would you prefer both paths use transactions for consistency? * Done. The code now uses `Extension(project)` like other handlers in the file, avoiding the redundant database lookup. * Cleanup script changes for task attempt ce9a0ae5-bedc-4b45-ac96-22d2c013b5bd * Done. Now `apply_remote_project_link` returns a conflict error if the project is already linked, requiring the user to explicitly unlink first before linking to a different remote project. * Both pass. Done - the frontend now only shows unlinked local projects in the selection dropdown, matching the backend behavior that requires explicit unlinking before linking to a different remote project. * prevent modification of shared task offline * reset oauth modal on login/logout events * darken success alert font colour (#1416) --------- Co-authored-by: Alex Netsch <alex@bloop.ai> Co-authored-by: Louis Knight-Webb <louis@bloop.ai> Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai> |
||
Gabriel Gordon-Hall
|
18637ab3e1 | move viewport with arrow key navigation in file-tag-typeahead-plugin and multi-file-searcharea (#1406) | ||
GitHub Action
|
72f2ab1320 | chore: bump version to 0.0.126 | ||
Louis Knight-Webb
|
d3317f68ff |
WYSIWYG editor (#1397)
* Replace follow up section with WYSIWYG (vibe-kanban 55b58b24)
frontend/src/components/tasks/TaskFollowUpSection.tsx
frontend/src/components/ui/wysiwyg.tsx
* Delete all usage of image chip component (vibe-kanban 5c90eac1)
frontend/src/components/ui/wysiwyg/image-chip-markdown.ts
frontend/src/components/ui/wysiwyg/image-chip-node.tsx
* Trigger file / tag picker from WYSIWYG (vibe-kanban 3e73cf53)
LexicalTypeaheadMenuPlugin
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/ui/file-search-textarea.tsx (old)
* Editor state should be saved as JSON (vibe-kanban 4f9eec74)
Instead of saving markdown, we should save JSON eg `editorState.toJSON();`.
This will enable us to properly serialize custom Elements in the future.
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
* In WYSIWYG, the search dialog can exceed screen (vibe-kanban 25337029)
When searching for tags/files. Sometimes the dialog is cut off the bottom of the screen.
frontend/src/components/ui/wysiwyg.tsx
* Use WYSIWYG for tasks (vibe-kanban 5485d481)
Currently used for follow ups, we should also use for task
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
frontend/src/components/ui/wysiwyg.tsx
* Keyboard shortcuts when typing in WYSIWYG (vibe-kanban 04bd70bc)
We used to have a callback for:
- CMD+Enter
- Shift+CMD+Enter
In create task dialog:
- CMD+Enter = create and start
- Shift+CMD+Enter = create without start
In follow up:
- CMD+Enter = Follow up
- Shift+CMD+Enter = nothing
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
Ideally we can use the relevant Lexical plugin and callbacks, cleaning up the old `@/keyboard` hooks which no longer work.
* Trigger file / tag picker from WYSIWYG (vibe-kanban 3e73cf53)
LexicalTypeaheadMenuPlugin
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/ui/file-search-textarea.tsx (old)
* Use WYSIWYG for tasks (vibe-kanban 5485d481)
Currently used for follow ups, we should also use for task
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
frontend/src/components/ui/wysiwyg.tsx
* Introduce new user-message table and struct (vibe-kanban 09116513)
{
ID,
message_json: Value,
message_md: String
}
We'll also need some endpoints to CRUD them.
crates/db
crates/server
* Stream individual scratch (vibe-kanban 321b50a1)
crates/server/src/routes/scratch.rs
It should be possible to listen for updates made to a single scratch
* Refactor useScratch (vibe-kanban 51ea2317)
To consolidate the API stuff into frontend/src/lib/api.ts
* Update scratch API (vibe-kanban 878f40c5)
Primary key should come from: ID and scratch type combination
The frontend will provide both.
Scratch IDs should not be generated on the backend.
* Remove all usage of hook from follow up (vibe-kanban 2d691095)
Use of hooks that reside in frontend/src/hooks/follow-up/* should be removed, except for frontend/src/hooks/follow-up/useFollowUpSend.ts
From: frontend/src/components/tasks/TaskFollowUpSection.tsx
* Task follow up should use scratch (vibe-kanban d37d3b18)
The current task attempt ID should be used to save the content of the follow up box as scratch.
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Use just markdown serialization for scratch (vibe-kanban 42f5507f)
frontend/src/hooks/useScratch.ts
crates/server/src/routes/scratch.rs
crates/db/src/models/scratch.rs
We are currently storing JSON + MD, however we should now store just MD and import/export the markdown into lexical.
* Consolidate MarkdownRenderer and WYSIWYG (vibe-kanban f61a7d40)
Currently we have an old implementation of markdown rendering in frontend/src/components/ui/markdown-renderer.tsx
But we have recently introduced the new WYSIWYG editor frontend/src/components/ui/wysiwyg.tsx
wysiwyg takes JSON as input, not raw markdown.
Ideally we could just use a single component and have a read only mode, removing Markdown Renderer and its dependencies and custom styling.
* WYSIWYG images (vibe-kanban 8cc3c0e7)
Create a Lexical plugin for images, with markdown import/export support.
Visually, images should be displayed as a small thumbnail with the path truncated.
Export/import should support standard markdown image format.
* Get image metadata endpoint (vibe-kanban 2c0dfbff)
Task attempt endpoint to get info, given the relative URL of an image.
We will also need an image that acts as a proxy to the file.
Info to return:
- Whether file exists
- Size of image
- Format
- File name
- Path
- URL to get image (the proxy URL)
The images are stored in the `.vibe-images` folder, relative to the task attempt container.
crates/server/src/routes/task_attempts.rs
* Inject relative path not absolute to image (vibe-kanban 007d589b)
Currently when we upload an image, it adds markdown with the full relative path of the image, eg:
/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban-dev/worktrees/2702-testing-images/.vibe-images/b01e6b02-dbd0-464c-aa9f-a42a89f6d67b.png
However, we should change this to be the path relative to the worktree eg .vibe-images/b01e6b02-dbd0-464c-aa9f-a42a89f6d67b.png
* Improve image in WYSIWYG (vibe-kanban 53de9071)
frontend/src/components/ui/wysiwyg/nodes/image-node.tsx
Check if the image comes from `./vibe-images/...`, if so:
Use the API endpoints to get and display metadata.
Use the image proxy to display the thumbnail image.
Do not render non `.vibe-images` images, instead just show the path and show a question icon as a thumbnail.
* rebase fixes
* Add Lexical toolbar (vibe-kanban b8904ad9)
frontend/src/components/ui/wysiwyg.tsx
* Clicking image once should open dialog (vibe-kanban aab2e6f4)
frontend/src/components/ui/wysiwyg/nodes/image-node.tsx
* Style quotes better (vibe-kanban 54718e76)
frontend/src/components/ui/wysiwyg.tsx
* Auto detect multi-line code blocks (vibe-kanban ce33792d)
Currently when I type triple backticks it doesn't create a multi-line code block
frontend/src/components/ui/wysiwyg.tsx
* Update how image upload works on the backend (vibe-kanban 62d97322)
I am only referring to the image upload for sending a follow up message.
Currently we:
- upload an image
- when a follow up is made, send file IDs
- copy the image into container based on those file IDs
We should tweak this so that:
- upload an image
- immediately the image is copied into container
- the image file location is added to the markdown of the follow up message (on the frontend)
- when user makes follow up, the image is already in the container
crates/server/src/routes/images.rs
crates/server/src/routes/task_attempts/images.rs
* Use @lexical/code to render code (vibe-kanban 60605a2c)
frontend/src/components/ui/wysiwyg.tsx
* Save variant in scratch (vibe-kanban 06e1e255)
frontend/src/components/tasks/TaskFollowUpSection.tsx
* prepare db
* Solve follow up loading when empty (vibe-kanban 1991bf3d)
frontend/src/components/tasks/TaskFollowUpSection.tsx
Currently the loader shows when the scratch data is loading, but also when there is no scratch data - which means the user can never see the follow up inputs
* descriptive scratch error
* Triple backtick WYSIWYG not working properly (vibe-kanban 30b0114e)
When I paste in a multi-line code block, eg
```js
var x = 100;
```
It doesn't add a multi-line code block properly, instead it created two multi-line code blocks above and below the code.
frontend/src/components/ui/wysiwyg.tsx
* Safe scratch fail (vibe-kanban c3f99b37)
It's possible to get an error like:
scratch WS closed: Failed to get scratch item: invalid type: string "\\`\\`\\`js\n\nvar x = 100;\n\n\\`\\`\\` \n\n\n", expected struct DraftFollowUpData at line 1 column 49
In this situation the websocket should act in the same way when no scratch exists yet.
* Remove drafts (vibe-kanban 0af2e9aa)
crates/services/src/services/drafts.rs
crates/db/src/models/draft.rs
* Cleanup scratch (vibe-kanban 0baf9b69)
Remove:
- frontend/src/pages/TestScratch.tsx
- frontend/src/components/ScratchEditor.tsx
* Improve styling of WYSIWYG + attachment (vibe-kanban 042a18da)
frontend/src/components/ui/wysiwyg.tsx
The placeholder can overlap the attachment icon
* Introduce queued message service (vibe-kanban 442164ae)
- New service (crates/services/src/services/...) that holds an in memory store
- When the final executor_action finishes, if another follow up prompt (scratch ID) is queued then we can automatically begin executing it (crates/local-deployment/src/container.rs after finalize)
- New endpoint required to modify the queue for a task attempt.
- Scratch should be wiped after the execution process is created
- Scratch can't be edited while queued
- Add button to TaskFollowUpSection to make current scratch queued, or cancel queued item
* prepare db
* Follow up box does not reset after sending message (vibe-kanban c032bc21)
- Type follow up
- Press send
- Expect follow up to be reset, but it is not
frontend/src/components/tasks/TaskFollowUpSection.tsx
* bg
* Fix i18n (vibe-kanban a7ee5604)
i18next::translator: missingKey en-GB tasks followUp.queue Queue
* Reduce re-renders (vibe-kanban 86ec1b47)
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Speed up button transitions (vibe-kanban be499249)
It takes 0.5-1s for the send button to go from no opacity to full opacity after I start typing
frontend/src/components/tasks/TaskFollowUpSection.tsx
* add icon to variant selection (vibe-kanban 92fca0e6)
frontend/src/components/tasks/TaskFollowUpSection.tsx
Dropdown should have settings-2
* Queued message functionality (vibe-kanban 21c7a725)
Say I have two messages to send:
- I send first
- I queue the second
- I now see "message queued" and the follow up editable text contains the second
- First finishes, second starts, no tasks are queued
- I still see "message queued" box but the follow up editable text gets wiped
frontend/src/components/tasks/TaskFollowUpSection.tsx
* variant width adjust
* Move the attach button (vibe-kanban b7f89e6e)
Attach button should be to the left of of the send button
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Cleanup WYSIWYG (vibe-kanban 62997d6c)
Props, and upstream logic:
- make placeholder optional:
- remove defaultValue: this seems redundant as value is always controlled, there may also be related cleanups for uncontrolled mode
- remove onFocusChange: toggling states is unnecessary here
- remove enableCopyButton: this is always enabled when the editor is disabled
frontend/src/components/ui/wysiwyg.tsx
* cleanup scratch types
* further scratch cleanup
* Tweak queue (vibe-kanban 642aa7be)
If a task is stopped or fails, the next queued task runs, however this is not the desired behaviour. Instead the queued task should be removed from the queue
* Can't see attach button and queue at the same time (vibe-kanban 75ca5428)
frontend/src/components/tasks/TaskFollowUpSection.tsx
* move follow up hooks
* WYSIWYG code blocks should scroll horizontally (vibe-kanban 6c5dbc99)
frontend/src/components/ui/wysiwyg.tsx
* Refactor useDefaultVariant (vibe-kanban 10ec12ec)
I think we could change this so that it accepts a default variant and then returns what variant is currently selected, based on the user's preferences and if they select one from the dropdown
* Can't retry a task (vibe-kanban dfde6ad8)
It seems to retry functionality was removed fromfrontend/src/components/NormalizedConversation/UserMessage.tsx
* If execution startup is slow, scratch is not reset (vibe-kanban 6e721b8e)
frontend/src/components/tasks/TaskFollowUpSection.tsx
If you write out a follow up and then hit send, if you then navigate away from the page quickly the scratch will still be present when you visit the page, when the expected behaviour is that the previous text would be cleared
* Code highlighting for inline code block (vibe-kanban 956f1d5c)
Currently works for multi-line, can we get it working for multi-line
frontend/src/components/ui/wysiwyg.tsx
* Delete FileSearchTextArea (vibe-kanban 01107879)
Replace with frontend/src/components/ui/wysiwyg.tsx
not frontend/src/components/ui/file-search-textarea.tsx
* Tweak styles in task dialog (vibe-kanban 8dfe95a9)
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
- Placeholder for WYSIWYG too small, just use default
- Make title same size as WYSIWYG H1
* Refactor retry to use variant hook (vibe-kanban 69c969c9)
frontend/src/hooks/useVariant.ts
frontend/src/components/NormalizedConversation/RetryEditorInline.tsx
frontend/src/contexts/RetryUiContext.tsx
Removing all existing logic related to variant picking
* Refactor approval message styles (vibe-kanban b9a905e1)
Refactor the WYSIWYG implementation in thefrontend/src/components/NormalizedConversation/PendingApprovalEntry.tsx so the styles align with usage infrontend/src/components/tasks/TaskFollowUpSection.tsx
* Fix follow up box font (vibe-kanban 4fa9cd39)
When I start typing, it's a really small font for some reason
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Remove double border for plan approval (vibe-kanban 3f12c591)
frontend/src/components/NormalizedConversation/PendingApprovalEntry.tsx
- Also multi-line code block colour is broken when looking at plans (but not single line strangely...)
* Retry Editor shouldn't call API directly (vibe-kanban 3df9cde5)
Should use hooks frontend/src/components/NormalizedConversation/RetryEditorInline.tsx
* Image metadata for task creation (vibe-kanban 8dd18a28)
We have an endpoint for image metadata in task attempt, but not for task
crates/server/src/routes/images.rs
This means we can't currently render the image (and metadata) in the WYSIWYG editorfrontend/src/components/dialogs/tasks/TaskFormDialog.tsx
* Add file upload to retry (vibe-kanban 8dffeed2)
frontend/src/components/NormalizedConversation/RetryEditorInline.tsx
Similar to:
frontend/src/components/tasks/TaskFollowUpSection.tsx
Infact we should reuse the same component as much as possible
* Remove the client side scratch deletion (vibe-kanban c6b0a613)
frontend/src/components/tasks/TaskFollowUpSection.tsx
This happens now on backend.
Also on backend when queued task is triggered we should also wipe the scratch.
* Queued task style (vibe-kanban 0c9bc110)
frontend/src/components/tasks/TaskFollowUpSection.tsx
When a message is queued it repeats the message under "will execute when current run finishes", however the message is visible anyway in the message box so we can remove that
* WYSIWYG base font size decrease
* Queueing a message change (vibe-kanban 30ee2d4d)
Currently when we queue a message I can see in the logs: Failed to save follow-up draft ApiError: Cannot edit scratch while a message is queued
I think this is because the following is happening:
- User types
- Clicks queue
- Debounce tries to save message
- Can't save message because of queue
|
||
|
Gabriel Gordon-Hall
|
6c7980eb9c |
Updated all four interactive dropdown menu components to use cursor-pointer instead of cursor-default: (#1401)
- `DropdownMenuSubTrigger` (line 28) - `DropdownMenuItem` (line 84) - `DropdownMenuCheckboxItem` (line 100) - `DropdownMenuRadioItem` (line 124) The disabled state behavior remains unchanged via `data-[disabled]:pointer-events-none`. |
||
|
Louis Knight-Webb
|
2a9655465c |
All checks pass. The implementation is complete. (#1403)
**Summary:** Added CMD+Enter keyboard shortcut to the CreateAttemptDialog by: 1. Importing `useKeySubmitTask` and `Scope` from `@/keyboard` 2. Adding the `useKeySubmitTask` hook that calls `handleCreate` when: - The dialog is visible (`modal.visible`) - Creation is allowed (`canCreate` - profile and branch selected, not loading, not already creating) This follows the same pattern used in other dialogs like `RestoreLogsDialog.tsx`. |
||
|
GitHub Action
|
41300de309 | chore: bump version to 0.0.125 | ||
Britannio Jarrett
|
770d897403 |
Prevent <TasksLayout/> component from being unmounted when using (#1391)
keyboard shortcuts to navigate the kanban board. In kanban boards with many tasks in a single column, when we use keyboard shortcuts to select a task 'below the fold', the animation restarts from the top of the kanban board, rather than preserving the existing position. |
||
Alex Netsch
|
34236c9572 |
Fix duplicate None/null options (#1384)
fmt |
||
|
GitHub Action
|
9dabff0752 | chore: bump version to 0.0.124 | ||
Ryosuke Hayashi
|
ae9425b96b |
Fetch initial diffs asynchronously in diff stream (#1376)
Move the blocking get_diffs call into a spawned task so the WebSocket stream is returned immediately. This prevents timeouts when fetching diffs for repositories with many changed files. Also remove a duplicate useEffect in DiffsPanel. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com> |
||
|
GitHub Action
|
43bfe63931 | chore: bump version to 0.0.123 | ||
|
Alex Netsch
|
b50f9ddce3 |
Smooth codex login (#1155)
* Add codex setup helper Pass exit result Move codex setup to routes FIx fmt Fix finalize * Rename scriptcontext (vibe-kanban 79207902) Rename the gh cli script context to something more general and use it for installs in crates/server/src/routes/task_attempts/cursor_setup.rs Rename scriptcontext (vibe-kanban 79207902) Rename the gh cli script context to something more general and use it for installs in crates/server/src/routes/task_attempts/cursor_setup.rs Fmt * Fix missing overrides for codex |
||
|
Alex Netsch
|
fd5ef916b0 |
Display agent availability during onboarding (vibe-kanban) (#1352)
* Perfect! All the implementation is complete. Let me summarize what was done:
I've successfully implemented agent availability checking during onboarding, mirroring the existing IDE availability functionality. Here's what was added:
1. **New API endpoint** in `crates/server/src/routes/config.rs`:
- Added `CheckAgentAvailabilityQuery` struct with `executor: BaseCodingAgent`
- Added `CheckAgentAvailabilityResponse` struct with `available: bool`
- Added `check_agent_availability()` handler that uses the existing `check_availability()` method from the executors crate
- Registered route: `/api/agents/check-availability`
2. **Type generation** in `crates/server/src/bin/generate_types.rs`:
- Added the new types to the TypeScript generation list
3. **API client** in `frontend/src/lib/api.ts`:
- Added `checkAgentAvailability()` method to `configApi`
- Imported necessary types
4. **Custom hook** in `frontend/src/hooks/useAgentAvailability.ts`:
- Created hook that checks agent availability asynchronously
- Returns states: `'checking' | 'available' | 'unavailable' | null`
5. **UI component** in `frontend/src/components/AgentAvailabilityIndicator.tsx`:
- Visual indicator showing spinner (checking), checkmark (available), or warning icon (unavailable)
- Matches the style of `EditorAvailabilityIndicator`
6. **Onboarding dialog** in `frontend/src/components/dialogs/global/OnboardingDialog.tsx`:
- Added agent availability check using the hook
- Displays the availability indicator below the agent selection dropdown
- The backend leverages existing `check_availability()` method that checks for MCP config files
- Frontend pattern exactly mirrors the IDE availability checking for consistency
- All TypeScript types are auto-generated from Rust
- Both backend (Rust) and frontend (TypeScript) checks pass successfully
The implementation is complete and ready for use!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Great! TypeScript compilation passes. The semantic color classes have been applied successfully. The component now uses:
- `text-success` for available agents (instead of `text-green-500`/`text-green-600`)
- `text-warning` for unavailable agents (instead of `text-orange-500`/`text-orange-600`)
This matches the semantic color conventions used throughout the codebase and will properly adapt to theme changes.
Excellent! I've implemented file modification time checking for Claude Code's credential file. Here's what the enhanced availability check does:
The `check_availability()` method for Claude Code now validates:
1. **File exists**: `~/.claude.json` must exist
2. **File is fresh**: Credentials file must have been modified within the last **60 days**
- If the file hasn't been touched in 60 days, it's considered stale and the agent is marked as unavailable
- This handles the case where credentials might have expired but the file still exists
- **OAuth refresh updates the file**: When credentials are refreshed (e.g., access token renewed), the file gets rewritten with new tokens, updating the modification time
- **Simple and fast**: Just a filesystem metadata check, no JSON parsing or API calls needed
- **Conservative threshold**: 60 days is reasonable - most OAuth refresh tokens are valid for 30-90 days, so if nothing has touched the file in 60 days, it's likely expired
- **False negatives possible**: If someone logged in 61 days ago and never used Claude Code since, it might still work (refresh token could be valid for 90 days), but we'll show it as unavailable
- **False positives possible**: File could be recently modified but tokens could be manually revoked server-side
- **Not foolproof**: The only way to be 100% certain is to make an authenticated API call
But as a heuristic for showing availability during onboarding, this is a solid approach that balances accuracy with performance.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. Let me summarize what was implemented:
- Enhanced `check_availability()` to check `~/.claude.json` modification time
- Marks agent as unavailable if credential file is older than 60 days
- Uses `std::fs::metadata()` and `modified().elapsed()` to compute age
- `CheckAgentAvailabilityResponse` now includes `credential_last_modified: Option<i64>`
- Calls new trait method `get_credential_last_modified()` to get Unix timestamp
- Returns `None` if file doesn't exist or metadata can't be read
- Added `get_credential_last_modified()` to `StandardCodingAgentExecutor` trait
- Gets file metadata and converts modification time to Unix timestamp
- Works for all agents automatically (uses their `default_mcp_config_path()`)
- On mount, checks availability of ALL agents in parallel
- Filters to only available agents with credentials
- Sorts by most recent `credential_last_modified` timestamp
- Auto-selects the agent with freshest credentials
- Only runs if user hasn't already configured an agent
1. User opens onboarding dialog for the first time
2. Frontend checks all agents in parallel (CLAUDE_CODE, CODEX, CURSOR_AGENT, etc.)
3. Each returns `{ available: bool, credential_last_modified: timestamp }`
4. Frontend finds agent with most recent credential file modification
5. Auto-selects that agent (likely the one they used most recently)
6. User can still manually change if they want
This provides a smart default while still allowing user choice!
Perfect! All checks pass. Let me show you the final summary:
I've successfully implemented comprehensive agent availability checking with automatic selection of the most recently used agent. Here's what was added:
**`AvailabilityInfo` struct** (`crates/executors/src/executors/mod.rs:167-206`):
- Structured type with fields: `mcp_config_found`, `auth_config_found`, `auth_last_edited`
- `is_available()` method that determines availability from the signals
- Logic: Available if MCP config exists OR auth config exists and is < 60 days old
**Trait method** (`crates/executors/src/executors/mod.rs:229-241`):
- Added `get_availability_info() -> AvailabilityInfo` to `StandardCodingAgentExecutor`
- Default implementation checks only MCP config
- Updated `check_availability()` to use `get_availability_info().is_available()`
**Claude Code** (`crates/executors/src/executors/claude.rs:200-224`):
- Auth credentials: `~/.claude.json`
- Checks file existence and modification time
- Returns AvailabilityInfo with auth signals
**Codex** (`crates/executors/src/executors/codex.rs:168-195`):
- MCP config: `~/.codex/config.toml`
- Auth credentials: `~/.codex/auth.json`
- Checks both MCP and auth configs
**Gemini** (`crates/executors/src/executors/gemini.rs:96-123`):
- MCP config: `~/.gemini/settings.json`
- Auth credentials: `~/.gemini/oauth_creds.json`
- Checks both MCP and auth configs
**Backend API** (`crates/server/src/routes/config.rs:479-498`):
- Returns `credential_last_modified` timestamp from AvailabilityInfo
- Uses `info.is_available()` for the available field
**Frontend auto-selection** (`frontend/src/components/dialogs/global/OnboardingDialog.tsx:64-112`):
- On mount, checks all agents in parallel
- Filters to available agents with credentials
- **Sorts by most recent `credential_last_modified`**
- Auto-selects the agent used most recently
This provides intelligent defaults while respecting user choice!
Perfect! All checks pass. Here's what I implemented:
**Enhanced API Response** (`crates/server/src/routes/config.rs:472-481`):
```rust
pub struct CheckAgentAvailabilityResponse {
available: bool,
mcp_config_found: bool,
auth_config_found: bool,
credential_last_modified: Option<i64>,
}
```
Now returns all the availability signals from `AvailabilityInfo`.
**OnboardingDialog** (`frontend/src/components/dialogs/global/OnboardingDialog.tsx`):
1. **State for availability map** (lines 57-59):
- Stores full availability info for all agents
- Used for intelligent sorting
2. **Priority-based sorting** (lines 187-218):
- **Tier 1**: Agents with auth config - sorted by most recent first
- **Tier 2**: Agents with MCP config only - alphabetical within tier
- **Tier 3**: Other agents - alphabetical within tier
- **Fallback**: Alphabetical if no availability info loaded yet
```typescript
// Tier 1: Both have auth - sort by recency
if (infoA.auth_config_found && infoB.auth_config_found) {
return timeB - timeA; // Most recent first
}
// Tier 2: Auth trumps MCP-only
if (infoA.auth_config_found) return -1;
if (infoB.auth_config_found) return 1;
// Tier 3: Both have MCP only - alphabetical
if (infoA.mcp_config_found && infoB.mcp_config_found) {
return a.localeCompare(b);
}
```
The dropdown will now show agents in this order:
1. **Most recently authenticated agents first** (e.g., Claude Code used yesterday)
2. **Other authenticated agents** (e.g., Gemini used last week)
3. **Agents with only MCP config** (alphabetical)
4. **Agents with no config** (alphabetical)
This ensures users see their most relevant agents at the top of the list!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. Here's the final implementation summary:
**Removed `auth_config_found` field** - simplified to just use `auth_last_edited.is_some()`:
**AvailabilityInfo** (`crates/executors/src/executors/mod.rs:167-201`):
```rust
pub struct AvailabilityInfo {
pub mcp_config_found: bool,
pub auth_last_edited: Option<i64>, // If Some(_), auth exists
}
```
**Implementations:**
- **Claude Code** (`claude.rs:200-212`): `~/.claude.json` → `auth_last_edited`
- **Codex** (`codex.rs:168-185`): MCP at `~/.codex/config.toml`, auth at `~/.codex/auth.json`
- **Gemini** (`gemini.rs:96-113`): MCP at `~/.gemini/settings.json`, auth at `~/.gemini/oauth_creds.json`
**CheckAgentAvailabilityResponse** (`config.rs:472-480`):
```rust
{
available: bool,
mcp_config_found: bool,
credential_last_modified: Option<i64>, // If Some, auth file exists
}
```
**Priority-based dropdown ordering** (`OnboardingDialog.tsx:191-230`):
1. **Tier 1**: Agents with auth (`credential_last_modified !== null`) - sorted by most recent
2. **Tier 2**: Agents with MCP only - alphabetical
3. **Tier 3**: Others - alphabetical
Users will see:
- **Top of list**: Their most recently authenticated agents (e.g., "logged into Claude Code yesterday")
- **Middle**: Agents with MCP config but no recent auth
- **Bottom**: Remaining agents alphabetically
The implementation is clean, simple, and provides intelligent defaults!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. The fix is complete:
**The Problem:**
- Line 76 had: `if (!profiles || config?.executor_profile) return;`
- This meant availability was **never fetched** for users with existing config
- `agentAvailabilityMap` stayed empty, sorting defaulted to alphabetical
- Result: AMP appeared first
**The Solution:**
- Removed `config?.executor_profile` from the skip condition
- Now availability is **always fetched** to enable sorting
- Moved the `config?.executor_profile` check **inside** the function (line 116)
- Auto-selection only happens for new users, but sorting works for everyone
**Now the dropdown will show:**
1. **Agents with recent auth** - sorted by most recent first (e.g., Claude Code used yesterday)
2. **Agents with MCP config only** - alphabetical (e.g., Cursor with MCP setup)
3. **Other agents** - alphabetical
The priority-based sorting is now fully functional!
Perfect! Fixed. Both indicators now use the same semantic colors:
- `text-success` for available (instead of `text-green-500`/`text-green-600`)
- `text-warning` for unavailable (instead of `text-orange-500`/`text-orange-600`)
The colors will now match perfectly between IDE and coding agent availability indicators.
Great! TypeScript compiles successfully. The changes are complete:
**AgentAvailabilityIndicator** now has:
1. **Updated text:**
- "Available" → "Login Detected"
- "Not Found" remains "Not Found"
2. **Tooltips on hover:**
- **Login Detected**: "Recent authentication credentials found for this agent"
- **Not Found**: "No credentials detected. The agent may still work if configured differently."
3. **Visual improvements:**
- Added `cursor-help` class to show the help cursor on hover
- Wrapped with shadcn/ui `Tooltip` components
This provides clearer messaging and helpful context for users!
Perfect! The tooltips now have `className="z-[100]"` which should render them above the modal. The fix ensures the hover text is readable when shown within the onboarding dialog.
Perfect! The tooltips now use `z-[10000]` which is higher than the modal's `z-[9999]`, so they should appear on top and be readable.
Perfect! TypeScript compiles successfully. The agent availability indicator is now added to the AgentSettings page:
**AgentSettings.tsx** now has:
1. **Availability check** (line 65):
```typescript
const agentAvailability = useAgentAvailability(selectedExecutorType);
```
2. **Indicator display** (line 444):
```typescript
<AgentAvailabilityIndicator availability={agentAvailability} />
```
The indicator appears below the agent dropdown selector and shows:
- "Login Detected" with tooltip for agents with credentials
- "Not Found" with tooltip for agents without credentials
- Same styling and behavior as the onboarding dialog
This provides consistent availability feedback throughout the app!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Excellent! TypeScript compiles successfully. The changes are complete:
**Reverted AgentSettings.tsx:**
- Removed the availability indicator from the Agent Settings page (which is for advanced profile configuration)
**Added to GeneralSettings.tsx:**
- **Line 43-44**: Imported `useAgentAvailability` hook and `AgentAvailabilityIndicator` component
- **Line 81**: Added hook call: `const agentAvailability = useAgentAvailability(draft?.executor_profile?.executor);`
- **Line 420**: Added indicator display: `<AgentAvailabilityIndicator availability={agentAvailability} />`
The agent availability indicator now appears in the **General Settings** page under the "Task Execution" section, right below the agent dropdown selector - matching the pattern of how editor availability is shown in the same settings page. This is the correct location since it's where users configure their default agent, not the advanced agent configuration page.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. Comments removed and types regenerated successfully. The implementation is complete and clean.
Fix agent availability i18n (vibe-kanban dcd1fc06)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main
Fix agent availability i18n (vibe-kanban 77795175)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main
Currently agents.availability.loginDetected shows in the frontend so it's not using i18n correctly, it was added in the last commit though
Perfect! TypeScript compiles. Now the availability indicator shows three distinct states:
1. **"Login Detected"** - Has auth credentials (recent login)
2. **"Installation Found"** - Has MCP config but no auth (agent is installed)
3. **"Not Found"** - Neither auth nor MCP config found
This gives users much clearer information about what was actually detected!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! Now the indicator shows three distinct states:
1. **"Login Detected"** (green check) - Has recent auth credentials
- Tooltip: "Recent authentication credentials found for this agent"
2. **"Installation Found"** (green check) - Has MCP config but no auth
- Tooltip: "Agent configuration found. You may need to log in to use it."
3. **"Not Found"** (orange warning) - Neither found
- Tooltip: "No credentials detected. The agent may still work if configured differently."
This gives users accurate, specific information about what was actually detected!
Fix i18n agent availability (vibe-kanban 9eab4ea1)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main
Perfect! I've fixed all the i18n keys by adding the `settings.` prefix. The translations should now work correctly and display:
- "Login Detected" instead of "agents.availability.loginDetected"
- "Installation Found" instead of "agents.availability.installationFound"
- "Not Found" instead of "agents.availability.notFound"
All the keys now match the pattern used throughout the codebase where `useTranslation('settings')` requires the full path starting with `settings.`.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
* Perfect! All checks pass. The refactoring to use `AvailabilityInfo` directly is complete:
**Removed redundancy:**
- Deleted `CheckAgentAvailabilityResponse` struct entirely
- API now returns `AvailabilityInfo` directly
- Removed `available` field (was computed/redundant)
**Backend now returns:**
```rust
AvailabilityInfo {
mcp_config_found: bool,
auth_last_edited: Option<i64>,
}
```
**Frontend interprets it as:**
- `auth_last_edited !== null` → **"Login Detected"** (has recent auth credentials)
- `auth_last_edited === null && mcp_config_found === true` → **"Installation Found"** (has MCP config only)
- `auth_last_edited === null && mcp_config_found === false` → **"Not Found"** (nothing detected)
**Benefits:**
- Single source of truth for availability data structure
- No duplication between `AvailabilityInfo` and response type
- Frontend gets raw signals and can interpret them appropriately
- Cleaner, simpler codebase
The implementation now correctly distinguishes between login credentials and installation/configuration files!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. The `check_availability` method has been successfully removed:
**Removed `check_availability()` method:**
- Updated `profile.rs:419` to use `get_availability_info().is_available()` instead
- Removed `check_availability()` from trait definition
- Updated Cursor's custom override to use `get_availability_info()` instead
- Removed unused import from cursor.rs
**Now there's only one method:**
- `get_availability_info()` returns the raw signals
- Callers use `.is_available()` if they need a boolean
Cleaner API surface with no redundant methods!
* Perfect! The simplification is complete. Let me show you what was removed:
## Simplified Implementation
**Removed from OnboardingDialog (~90 lines):**
- ❌ `agentAvailabilityMap` state (9 lines)
- ❌ `useEffect` with parallel API calls (66 lines)
- ❌ Complex 3-tier sorting logic (41 lines)
- ❌ Auto-selection based on recent auth
- ❌ Unused imports (`useEffect`, `configApi`)
**What remains:**
- ✅ Simple alphabetical sort: `.sort()`
- ✅ Backend auto-selects first available agent (via `get_recommended_executor_profile`)
- ✅ Live indicator when user selects agent (via `useAgentAvailability` hook)
- ✅ Indicator in GeneralSettings
**The feature now:**
1. Dropdown shows agents alphabetically (AMP, CLAUDE_CODE, CODEX, ...)
2. Pre-selected agent is whatever backend chose (first available from HashMap)
3. User selects an agent → indicator shows "Login Detected" / "Installation Found" / "Not Found"
4. Same in GeneralSettings when changing default agent
**Net reduction: ~90 lines removed from OnboardingDialog, much simpler!**
* Perfect! All checks pass. The implementation is complete:
## Summary of Final Simplified Architecture
**Backend (profile.rs):**
- `get_recommended_executor_profile()` now checks ALL available agents
- Sorts by most recent `auth_last_edited` timestamp
- Returns agent with freshest credentials (e.g., logged in yesterday)
- Fallback to agents with MCP config if no auth found
**Frontend (OnboardingDialog):**
- ✅ Shows alphabetically sorted dropdown
- ✅ Pre-selects whatever backend recommended (agent with most recent credentials)
- ✅ Shows live indicator when selected: "Login Detected" / "Installation Found" / "Not Found"
- ❌ No parallel API calls on mount (removed ~90 lines)
- ❌ No complex sorting logic (removed)
- ❌ No auto-selection in frontend (backend handles it)
**Net result:**
- Smart auto-selection happens in backend (right place)
- Frontend is much simpler (just shows indicator on selection)
- Achieves the same UX goal (picks most recently used agent)
- ~90 lines removed from OnboardingDialog
Much cleaner architecture!
* Perfect! All checks pass. The 60-day cutoff has been removed:
## Summary of Changes
**Simplified `is_available()` logic** (`crates/executors/src/executors/mod.rs:175-177`):
```rust
pub fn is_available(&self) -> bool {
self.mcp_config_found || self.auth_last_edited.is_some()
}
```
**Before:**
- Auth file must exist AND be less than 60 days old
- Rejected old auth files even if tokens still valid
**After:**
- Auth file exists → available ✅
- MCP config exists → available ✅
- Simple and straightforward
**Benefits:**
- ✅ Removed 13 lines of arbitrary staleness checking
- ✅ No false negatives (61-day-old credentials shown as "Login Detected")
- ✅ Backend sorting still prioritizes recent auth (for smart auto-selection)
- ✅ If tokens are actually expired, user finds out when they try to use the agent (which is fine)
The implementation is now much cleaner - file existence is all we check, and recency is only used for **prioritization** in the backend auto-selection, not for determining availability.
* Review agent availability (vibe-kanban a75cb3d4)
Review the last 4 commits
* Move agent install info out of tooltip (vibe-kanban 481d6ed6)
When agents are not installed users can get more info by hovering and looking at the tooltip, move this out of there and always display it.
* Refactor auth file path (vibe-kanban e691ad16)
In crates/executors/src/executors/mod.rs add a method similar to mcp config for auth config that executors can check in the availability check
* Refactor auth file path (vibe-kanban e691ad16)
In crates/executors/src/executors/mod.rs add a method similar to mcp config for auth config that executors can check in the availability check
* Refactor availability info (vibe-kanban 8e24bec4)
Check crates/executors/src/executors/mod.rs and refactor availability info. The frontend currently may not use the timestamp and defines its own state type. we should return the state from the backend instead
* Perfect! Now all locale files are updated with the user-centric language:
## Summary of i18n Updates
**Changed labels to user-centric language:**
- "Login Detected" → **"Recent Usage Detected"**
- "Installation Found" → **"Previous Usage Detected"**
**Updated notFound tooltip:**
- "No credentials detected. The agent may still work if configured differently."
- → **"No previous usage detected. Agent may require installation and/or login."**
**Kept technical tooltips for detected states:**
- "Recent authentication credentials found for this agent" (still accurate)
- "Agent configuration found. You may need to log in to use it." (still helpful)
This is much clearer for users - focuses on what they care about (did I use this before?) rather than technical implementation details (credentials, MCP configs, auth files).
* lint
* Perfect! All the imports are cleaned up. Now all executor implementations use the shorter `AvailabilityInfo::LoginDetected` instead of the verbose `crate::executors::AvailabilityInfo::LoginDetected`.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All the imports are now cleaned up. All executor implementations use the shorter `AvailabilityInfo::LoginDetected` instead of the verbose `crate::executors::AvailabilityInfo::LoginDetected`.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
|
||
|
Alex Netsch
|
036dd802d8 |
Force push (vibe-kanban) (#1350)
* Excellent! All tasks completed successfully. Here's a summary of the changes:
I've successfully added typed error handling to the push method following the same pattern as `CreatePrError`. Here's what was implemented:
1. **Created `PushError` enum** in `crates/server/src/routes/task_attempts.rs:608-613`
- Single variant: `ForcePushRequired`
- Uses proper derives for TypeScript generation
2. **Updated push handler signature** in `crates/server/src/routes/task_attempts.rs:596`
- Changed return type to `Result<ResponseJson<ApiResponse<(), PushError>>, ApiError>`
3. **Registered error type** in `crates/server/src/bin/generate_types.rs:140`
- Added `PushError::decl()` to the type declarations
4. **Generated TypeScript type** in `shared/types.ts:301`
- Type: `export type PushError = { "type": "force_push_required" }`
5. **Updated frontend API** in `frontend/src/lib/api.ts`
- Imported `PushError` type
- Changed `push` method to return `Result<void, PushError>`
- Uses `handleApiResponseAsResult` for proper error handling
6. **Updated `usePush` hook** in `frontend/src/hooks/usePush.ts`
- Created custom `PushErrorWithData` class to properly pass error data
- Updated signature to pass `errorData` to `onError` callback
7. **Updated component error handling** in `frontend/src/hooks/useGitOperations.ts:47-52`
- Added handling for `force_push_required` error type
- Displays user-friendly message: "Force push required. The remote branch has diverged."
All checks pass successfully! The implementation is ready for future force push functionality.
Cleanup script changes for task attempt 982f21cc-f0a3-455d-8b30-3a9911c2889f
Excellent! All tasks completed successfully. Here's a summary of the force push implementation:
I've successfully implemented a complete force push feature with user confirmation. Here's what was done:
1. **Updated Git CLI** (`crates/services/src/services/git/cli.rs:318`)
- Added `force: bool` parameter to `push()` method
- Uses `+refs/heads/{branch}` refspec when force is true
2. **Updated Git Service** (`crates/services/src/services/git.rs:1615`)
- Added `force: bool` parameter to `push_to_github()` method
- Passes force flag to Git CLI
3. **Added Force Push Endpoint** (`crates/server/src/routes/task_attempts.rs:608`)
- New handler: `force_push_task_attempt_branch`
- Calls `push_to_github()` with `force: true`
- Regular push endpoint now passes `force: false`
4. **Added Route** (`crates/server/src/routes/task_attempts.rs:1581`)
- Route: `POST /api/task-attempts/:id/push/force`
5. **API Client** (`frontend/src/lib/api.ts:561`)
- Added `forcePush()` method
- Returns `Result<void, PushError>`
6. **Created useForcePush Hook** (`frontend/src/hooks/useForcePush.ts`)
- React Query mutation for force push
- Handles typed errors
- Invalidates branch status on success
7. **Created ForcePushDialog** (`frontend/src/components/dialogs/git/ForcePushDialog.tsx`)
- Destructive variant with warning icon
- Clear warning about overwriting remote changes
- Buttons: "Cancel" and "Force Push"
8. **Integrated Dialog Flow** (`frontend/src/hooks/useGitOperations.ts:58-85`)
- When regular push fails with `force_push_required` error:
- Shows ForcePushDialog to confirm
- If user confirms, executes force push
- Handles errors from force push operation
1. User attempts to push
2. If remote has diverged, backend returns `force_push_required` error
3. Frontend shows confirmation dialog explaining the consequences
4. User can cancel or confirm force push
5. If confirmed, force push is executed
6. Success/error feedback is shown
All checks pass successfully! The feature is ready to use.
Cleanup script changes for task attempt 982f21cc-f0a3-455d-8b30-3a9911c2889f
Perfect! The fix is complete and all checks pass. Here's what was changed:
**Problem:** The `push_task_attempt_branch` endpoint was using the `?` operator which converted `GitServiceError::GitCLI(GitCliError::PushRejected(_))` into a generic `ApiError`, preventing the frontend from receiving the typed `PushError::ForcePushRequired` error.
**Solution:** Updated the endpoint in `crates/server/src/routes/task_attempts.rs:602-613` to use a `match` statement that:
1. Returns success on `Ok(_)`
2. Detects `GitServiceError::GitCLI(GitCliError::PushRejected(_))` and returns the typed error `ApiResponse::error_with_data(PushError::ForcePushRequired)`
3. Returns generic `ApiError::GitService(e)` for other errors
Now when a push is rejected due to non-fast-forward, the backend will return:
```json
{
"success": false,
"error_data": {
"type": "force_push_required"
}
}
```
This will trigger the force push confirmation dialog in the frontend, allowing the user to choose whether to force push or cancel.
Cleanup script changes for task attempt 982f21cc-f0a3-455d-8b30-3a9911c2889f
Perfect! The fix is complete and all checks pass. Here's what was changed:
**Problem:** The ForcePushDialog was not closing after the user clicked "Force Push" or "Cancel" because it only called `modal.resolve()` without calling `modal.hide()`.
**Solution:** Added `modal.hide()` calls to both handlers in `frontend/src/components/dialogs/git/ForcePushDialog.tsx`:
- **Line 24:** Added `modal.hide()` after `modal.resolve('confirmed')` in `handleConfirm`
- **Line 29:** Added `modal.hide()` after `modal.resolve('canceled')` in `handleCancel`
Now the dialog will properly close when the user clicks either button. This follows the correct NiceModal pattern where you need both:
1. `modal.resolve()` - to resolve the promise with a result
2. `modal.hide()` - to actually hide the dialog
The force push feature should now work end-to-end: push rejection → confirmation dialog → force push → dialog closes.
Perfect! All checks pass. Here's what was fixed:
The force push dialog now follows the same pattern as all other async dialogs in the codebase.
**Added:**
- `attemptId` prop (required) to identify which task attempt to force push
- `useForcePush` hook usage internally
- Loading state with `forcePush.isPending`
- Error state displayed in the dialog
- Loader spinner and "Force Pushing..." button text during operation
- Disabled buttons during operation
- Dialog stays open until operation completes
**Behavior:**
- User clicks "Force Push" → button shows spinner and "Force Pushing..."
- On success → dialog closes automatically
- On error → error shown in dialog, stays open, user can retry or cancel
**Changed:**
- Removed the manual force push call after dialog confirmation
- Now passes `attemptId` to the dialog: `ForcePushDialog.show({ attemptId })`
- Dialog handles the entire force push operation internally
1. User attempts push
2. Push rejected with `force_push_required` error
3. Dialog appears with warning
4. User clicks "Force Push"
5. **Button shows spinner and "Force Pushing..."** ← New!
6. **Buttons disabled during operation** ← New!
7. On success: dialog closes
8. On error: error displayed in dialog, user can retry
This matches the pattern used by CreatePRDialog, GhCliSetupDialog, and other async dialogs in the codebase.
* Force push i18n (vibe-kanban 5519a7db)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to vk/607c-add-pre-flight-c
Force push i18n (vibe-kanban 5519a7db)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to vk/607c-add-pre-flight-c
* fix tests
|
||
|
Alex Netsch
|
1ef162416d |
Add pre-flight check for target branch existence before PR creation (vibe-kanban) (#1341)
* Excellent! I've successfully implemented the pre-flight check for target branch existence before PR creation. Here's what I did: ## Summary I've added a pre-flight check that verifies the target branch exists on the remote before attempting to create a pull request. This provides a clear, early error message instead of failing during the GitHub API call. ### Changes Made 1. **Added `fetch_and_check_branch_exists()` method** in `crates/services/src/services/git.rs:1414-1446`: - Fetches from the remote to update tracking refs - Checks if the target branch exists (both local and remote branches) - Uses best-effort fetching (doesn't fail if fetch fails) - Returns `Ok(true)` if branch exists, `Ok(false)` if not 2. **Added pre-flight check** in `crates/server/src/routes/task_attempts.rs:639-667`: - Placed before pushing the branch to GitHub - Fetches and verifies the target branch exists - Returns a clear error message if the branch doesn't exist - Continues with PR creation even if the check fails (fallback to GitHub API error) - Includes logging for debugging ### Key Features - **Fail-fast approach**: Catches missing target branch before wasting time on the GitHub API call - **Clear error messages**: Users get an actionable error message: "Target branch 'X' does not exist on remote. Please ensure the branch exists before creating a pull request." - **Graceful degradation**: If the fetch/check fails for any reason, the code continues and lets the GitHub API handle the error (existing fallback behavior) - **Works with all git remotes**: Not GitHub-specific, uses git fetch - **Performance trade-off**: Adds 1-3 seconds for the fetch operation, but provides better UX ### Testing All checks passed: - ✅ Rust compilation (cargo clippy) - ✅ TypeScript type generation (npm run generate-types:check) The implementation follows the "Option A - Fetch-then-check" approach from the task description, providing early detection of missing target branches while maintaining backward compatibility with the existing error handling. * Cleanup script changes for task attempt 607cef96-2669-46e6-bee9-fd2d524be0bd * Perfect! All the review comments have been addressed: ## Changes Made 1. **Simplified `fetch_and_check_branch_exists()` in git.rs** - Now uses the existing `Self::find_branch()` helper method instead of manually calling `repo.find_branch()` twice, making the code cleaner and more consistent with the rest of the codebase. 2. **Removed all comments** from both files - The code is now self-explanatory without the verbose comments. 3. **Removed all logging** from task_attempts.rs - No more `tracing::info!`, `tracing::warn!`, or `tracing::error!` calls for the pre-flight check. 4. **Simplified control flow** - Changed from a match statement to a cleaner if-let pattern as suggested by clippy. The implementation is now more concise while maintaining the same functionality: - Fetches from remote and checks if the target branch exists - Returns a clear error if the branch doesn't exist - Silently continues on success or fetch errors (letting GitHub API handle any remaining issues) All compilation checks pass successfully. * Perfect! All checks pass. Let me create a summary of the changes: I've successfully added a typed error for the missing target branch case. Here's what was changed: 1. **Added `TargetBranchNotFound` variant to `GitHubServiceError`** in `crates/services/src/services/github.rs:38-40`: - Takes a `String` parameter for the branch name - Includes a clear error message - Marked with `#[ts(skip)]` since it has a parameter 2. **Updated `is_api_data()` method** in `crates/services/src/services/github.rs:93`: - Added `GitHubServiceError::TargetBranchNotFound(_)` to the match pattern - This ensures the error is properly typed and won't be retried 3. **Updated `create_github_pr()`** in `crates/server/src/routes/task_attempts.rs:643-645`: - Replaced the string error message with `GitHubServiceError::TargetBranchNotFound(target_branch.clone())` - Now uses `ApiResponse::error_with_data()` instead of `ApiResponse::error()`, consistent with other typed errors in the function - **Type-safe error handling**: Frontend can now properly discriminate this error type - **Consistent with existing patterns**: Follows the same pattern as `TokenInvalid`, `InsufficientPermissions`, etc. - **Better API design**: The error is now part of the function's return type signature All compilation and type generation checks pass successfully! * Great! All checks pass. Let me create a summary: I've successfully added frontend error handling for the `target_branch_not_found` error. Here's what was done: 1. **Added translation key** in `frontend/src/i18n/locales/en/tasks.json:345`: - Key: `createPrDialog.errors.targetBranchNotFound` - Message: `"Target branch '{{branch}}' does not exist on remote. Please ensure the branch exists before creating a pull request."` - Uses interpolation to inject the branch name dynamically 2. **Added error handler** in `frontend/src/components/dialogs/tasks/CreatePRDialog.tsx:187-195`: - Checks if `result.error.type === 'target_branch_not_found'` - Extracts the `branch` field from the error object - Displays localized error message with the branch name interpolated - Clears the GH CLI helper UI state When a user tries to create a PR with a non-existent target branch: 1. **Backend pre-flight check** fetches from remote and checks if the target branch exists 2. **If branch doesn't exist**: Returns `CreatePrError::TargetBranchNotFound { branch: "xyz" }` 3. **Frontend receives** typed error with discriminant `type: "target_branch_not_found"` and `branch: "xyz"` 4. **Dialog displays**: "Target branch 'xyz' does not exist on remote. Please ensure the branch exists before creating a pull request." All checks pass (TypeScript compilation, linting, type generation). * Excellent! All checks pass. Here's the summary: I've successfully added the `targetBranchNotFound` translation key to all 3 missing locale files: 1. **Spanish (es)** - `frontend/src/i18n/locales/es/tasks.json:121`: - `"La rama objetivo '{{branch}}' no existe en el remoto. Por favor, asegúrese de que la rama exista antes de crear una solicitud de extracción."` 2. **Japanese (ja)** - `frontend/src/i18n/locales/ja/tasks.json:121`: - `"ターゲットブランチ '{{branch}}' がリモートに存在しません。プルリクエストを作成する前にブランチが存在することを確認してください。"` 3. **Korean (ko)** - `frontend/src/i18n/locales/ko/tasks.json:121`: - `"대상 브랜치 '{{branch}}'이(가) 원격에 존재하지 않습니다. 풀 리퀘스트를 생성하기 전에 브랜치가 존재하는지 확인하세요."` All translations follow the same pattern with the `{{branch}}` interpolation parameter and maintain consistency with the existing error messages in each locale. All checks pass (TypeScript compilation, frontend and backend checks)! Fix i18n * Perfect! All checks pass. Here's the complete summary: ## Summary I've successfully fixed the branch name format handling issue in `check_remote_branch_exists()`. ### The Problem The method only tried the exact branch name provided (e.g., "main"), but git2's `find_branch()` with `BranchType::Remote` requires the full remote branch name (e.g., "origin/main"). This meant: - ❌ User provides "main" → check fails (should succeed if origin/main exists) - ✅ User provides "origin/main" → check succeeds ### The Fix Updated `check_remote_branch_exists()` in `crates/services/src/services/git.rs:1414-1428` to try both formats: 1. **First attempt**: Try the branch name as-is (handles "origin/main" format) 2. **Fallback**: Prepend default remote name (handles "main" format → "origin/main") This follows the same pattern used by `find_branch()`, `find_branch_type()`, and `check_branch_exists()` throughout the codebase. ### Complete Implementation The full pre-flight check implementation now includes: **Backend:** - ✅ Fetches from remote to get latest refs - ✅ Checks if target branch exists (handles both "main" and "origin/main" formats) - ✅ Returns typed error `CreatePrError::TargetBranchNotFound { branch }` - ✅ Handles auth errors during fetch → `CreatePrError::GitCliNotLoggedIn` - ✅ Handles missing git CLI → `CreatePrError::GitCliNotInstalled` **Frontend:** - ✅ Handles `target_branch_not_found` error type in CreatePRDialog - ✅ Displays localized error message with branch name - ✅ Translations added for all 4 locales (en, es, ja, ko) All checks pass! * Lint * Change pre-flight check for create PR (vibe-kanban 4f79fbc8) to use git ls-remote --branches to check for remote branche existence instead of libgit2. To do this add an appropriate method to crates/services/src/services/git/cli.rs and modify the preflight check. * Perfect! All checks pass. The implementation is now complete: ## Complete Implementation Summary ### What Was Built A pre-flight check for PR creation that verifies the target branch exists on the remote before attempting to create the pull request. ### Key Changes **Backend:** 1. **`check_remote_branch_exists()`** in `git.rs:1414-1428` - Checks if a branch exists remotely, handles both "main" and "origin/main" formats 2. **`fetch_and_check_branch_exists()`** in `git.rs:1430-1439` - Fetches from remote then checks existence, propagates errors 3. **`CreatePrError::TargetBranchNotFound`** in `task_attempts.rs:616` - New typed error variant with branch name 4. **Pre-flight check** in `create_github_pr()` in `task_attempts.rs:639-662` - Validates target branch exists, handles auth errors **Frontend:** 1. **Error handler** in `CreatePRDialog.tsx:187-195` - Displays localized error message 2. **Translations** in all 4 locales (en, es, ja, ko) - Localized error messages with branch name interpolation ### What Works - ✅ Detects missing target branches before push/PR creation - ✅ Handles "main" and "origin/main" branch name formats - ✅ Fails fast on auth errors during fetch - ✅ Returns typed errors the frontend can handle - ✅ Displays clear, localized error messages with the branch name - ✅ All checks pass (Rust clippy, TypeScript, type generation) |
||
Stephan Fitzpatrick
|
f651c64f7d |
Perfect! I've successfully added a text wrap toggle to the frontend diff viewer. Here's a summary of the changes: (#1219)
## Changes Made ### 1. **State Management** (`frontend/src/stores/useDiffViewStore.ts:11-13,22-23,29`) - Added `wrapText` boolean state (defaults to `false`) - Added `setWrapText` action to update the state - Exported `useWrapTextDiff` hook for components to access the state ### 2. **UI Toggle Component** (`frontend/src/components/diff-view-switch.tsx:1,8,28-29,32,100-121`) - Imported `WrapText` icon from `lucide-react` - Added a new toggle group for the text wrap feature - The toggle appears alongside the existing view mode and whitespace toggles - Uses the same UI pattern as the "Ignore Whitespace" toggle - Includes tooltip with internationalization support ### 3. **Diff Viewer Integration** (`frontend/src/components/DiffCard.tsx:31,84,300`) - Imported and used the `useWrapTextDiff` hook - Connected the `wrapText` state to the `DiffView` component's `diffViewWrap` prop - The `DiffView` component now responds to the toggle state ## How It Works - The toggle button appears in the diff view controls with a `WrapText` icon - Clicking the toggle switches between wrapped and unwrapped text in the diff viewer - The state is managed globally via Zustand, so all diff viewers share the same wrap preference - The default is set to `false` (no wrapping), preserving the original behavior - The feature follows the existing architectural patterns for the ignore whitespace and view mode toggles The implementation is complete and ready to use! |
||
|
Alex Netsch
|
1933bb463c |
Decouple git from github errors (#1347)
* Decouple git from github errors
* Fix git error display (vibe-kanban 7352dadc)
After the last few commits git cli not logged in error does not get displayed to the user. Network tab shows this:
{
"success": false,
"data": null,
"error_data": {
"type": "git_cli_not_logged_in"
},
"message": null
}
|
||
|
GitHub Action
|
f691fbd9cb | chore: bump version to 0.0.122 | ||
|
Solomon
|
83602590e9 |
Droid agent (#1318)
* droid research (vibe-kanban 054135e9)
<droid-docs>
# Overview
> Non-interactive execution mode for CI/CD pipelines and automation scripts.
# Droid Exec (Headless CLI)
Droid Exec is Factory's headless execution mode designed for automation workflows. Unlike the interactive CLI, `droid exec` runs as a one-shot command that completes a task and exits, making it ideal for CI/CD pipelines, shell scripts, and batch processing.
## Summary and goals
Droid Exec is a one-shot task runner designed to:
* Produce readable logs, and structured artifacts when requested
* Enforce opt-in for mutations/command execution (secure-by-default)
* Fail fast on permission violations with clear errors
* Support simple composition for batch and parallel work
<CardGroup cols={2}>
<Card title="Non-Interactive" icon="terminal">
Single run execution that writes to stdout/stderr for CI/CD integration
</Card>
<Card title="Secure by Default" icon="lock">
Read-only by default with explicit opt-in for mutations via autonomy levels
</Card>
<Card title="Composable" icon="puzzle">
Designed for shell scripting, parallel execution, and pipeline integration
</Card>
<Card title="Clean Output" icon="file-export">
Structured output formats and artifacts for automated processing
</Card>
</CardGroup>
## Execution model
* Non-interactive single run that writes to stdout/stderr.
* Default is spec-mode: the agent is only allowed to execute read-only operations.
* Add `--auto` to enable edits and commands; risk tiers gate what can run.
CLI help (excerpt):
```
Usage: droid exec [options] [prompt]
Execute a single command (non-interactive mode)
Arguments:
prompt The prompt to execute
Options:
-o, --output-format <format> Output format (default: "text")
-f, --file <path> Read prompt from file
--auto <level> Autonomy level: low|medium|high
--skip-permissions-unsafe Skip ALL permission checks (unsafe)
-s, --session-id <id> Existing session to continue (requires a prompt)
-m, --model <id> Model ID to use
-r, --reasoning-effort <level> Reasoning effort: off|low|medium|high
--cwd <path> Working directory path
-h, --help display help for command
```
Supported models (examples):
* gpt-5-codex (default)
* gpt-5-2025-08-07
* claude-sonnet-4-20250514
* claude-opus-4-1-20250805
## Installation
<Steps>
<Step title="Install Droid CLI">
<CodeGroup>
```bash macOS/Linux theme={null}
curl -fsSL https://app.factory.ai/cli | sh
```
```powershell Windows theme={null}
irm https://app.factory.ai/cli/windows | iex
```
</CodeGroup>
</Step>
<Step title="Get Factory API Key">
Generate your API key from the [Factory Settings Page](https://app.factory.ai/settings/api-keys)
</Step>
<Step title="Set Environment Variable">
Export your API key as an environment variable:
```bash theme={null}
export FACTORY_API_KEY=fk-...
```
</Step>
</Steps>
## Quickstart
* Direct prompt:
* `droid exec "analyze code quality"`
* `droid exec "fix the bug in src/main.js" --auto low`
* From file:
* `droid exec -f prompt.md`
* Pipe:
* `echo "summarize repo structure" | droid exec`
* Session continuation:
* `droid exec --session-id <session-id> "continue with next steps"`
## Autonomy Levels
Droid exec uses a tiered autonomy system to control what operations the agent can perform. By default, it runs in read-only mode, requiring explicit flags to enable modifications.
### DEFAULT (no flags) - Read-only Mode
The safest mode for reviewing planned changes without execution:
* ✅ Reading files or logs: cat, less, head, tail, systemctl status
* ✅ Display commands: echo, pwd
* ✅ Information gathering: whoami, date, uname, ps, top
* ✅ Git read operations: git status, git log, git diff
* ✅ Directory listing: ls, find (without -delete or -exec)
* ❌ No modifications to files or system
* **Use case:** Safe for reviewing what changes would be made
```bash theme={null}
# Analyze and plan refactoring without making changes
droid exec "Analyze the authentication system and create a detailed plan for migrating from session-based auth to OAuth2. List all files that would need changes and describe the modifications required."
# Review code quality and generate report
droid exec "Review the codebase for security vulnerabilities, performance issues, and code smells. Generate a prioritized list of improvements needed."
# Understand project structure
droid exec "Analyze the project architecture and create a dependency graph showing how modules interact with each other."
```
### `--auto low` - Low-risk Operations
Enables basic file operations while blocking system changes:
* ✅ File creation/editing in project directories
* ❌ No system modifications or package installations
* **Use case:** Documentation updates, code formatting, adding comments
```bash theme={null}
# Safe file operations
droid exec --auto low "add JSDoc comments to all functions"
droid exec --auto low "fix typos in README.md"
```
### `--auto medium` - Development Operations
Operations that may have significant side effects, but these side effects are typically harmless and straightforward to recover from.
Adds common development tasks to low-risk operations:
* Installing packages from trusted sources: npm install, pip install (without sudo)
* Network requests to trusted endpoints: curl, wget to known APIs
* Git operations that modify local repositories: git commit, git checkout, git pull (but not git push)
* Building code with tools like make, npm run build, mvn compile
* ❌ No git push, sudo commands, or production changes
* **Use case:** Local development, testing, dependency management
```bash theme={null}
# Development tasks
droid exec --auto medium "install deps, run tests, fix issues"
droid exec --auto medium "update packages and resolve conflicts"
```
### `--auto high` - Production Operations
Commands that may have security implications such as data transfers between untrusted sources or execution of unknown code, or major side effects such as irreversible data loss or modifications of production systems/deployments.
* Running arbitrary/untrusted code: curl | bash, eval, executing downloaded scripts
* Exposing ports or modifying firewall rules that could allow external access
* Git push operations that modify remote repositories: git push, git push --force
* Irreversible actions to production deployments, database migrations, or other sensitive operations
* Commands that access or modify sensitive information like passwords or keys
* ❌ Still blocks: sudo rm -rf /, system-wide changes
* **Use case:** CI/CD pipelines, automated deployments
```bash theme={null}
# Full workflow automation
droid exec --auto high "fix bug, test, commit, and push to main"
droid exec --auto high "deploy to staging after running tests"
```
### `--skip-permissions-unsafe` - Bypass All Checks
<Warning>
DANGEROUS: This mode allows ALL operations without confirmation. Only use in completely isolated environments like Docker containers or throwaway VMs.
</Warning>
* ⚠️ Allows ALL operations without confirmation
* ⚠️ Can execute irreversible operations
* Cannot be combined with --auto flags
* **Use case:** Isolated environments
```bash theme={null}
# In a disposable Docker container for CI testing
docker run --rm -v $(pwd):/workspace alpine:latest sh -c "
apk add curl bash &&
curl -fsSL https://app.factory.ai/cli | sh &&
droid exec --skip-permissions-unsafe 'Install all system dependencies, modify system configs, run integration tests that require root access, and clean up test databases'
"
# In ephemeral GitHub Actions runner for rapid iteration
# where the runner is destroyed after each job
droid exec --skip-permissions-unsafe "Modify /etc/hosts for test domains, install custom kernel modules, run privileged container tests, and reset network interfaces"
# In a temporary VM for security testing
droid exec --skip-permissions-unsafe "Run penetration testing tools, modify firewall rules, test privilege escalation scenarios, and generate security audit reports"
```
### Fail-fast Behavior
If a requested action exceeds the current autonomy level, droid exec will:
1. Stop immediately with a clear error message
2. Return a non-zero exit code
3. Not perform any partial changes
This ensures predictable behavior in automation scripts and CI/CD pipelines.
## Output formats and artifacts
Droid exec supports three output formats for different use cases:
### text (default)
Human-readable output for direct consumption or logs:
```bash theme={null}
$ droid exec --auto low "create a python file that prints 'hello world'"
Perfect! I've created a Python file named `hello_world.py` in your home directory that prints 'hello world' when executed.
```
### json
Structured JSON output for parsing in scripts and automation:
```bash theme={null}
$ droid exec "summarize this repository" --output-format json
{
"type": "result",
"subtype": "success",
"is_error": false,
"duration_ms": 5657,
"num_turns": 1,
"result": "This is a Factory documentation repository containing guides for CLI tools, web platform features, and onboarding procedures...",
"session_id": "8af22e0a-d222-42c6-8c7e-7a059e391b0b"
}
```
Use JSON format when you need to:
* Parse the result in a script
* Check success/failure programmatically
* Extract session IDs for continuation
* Process results in a pipeline
### debug
Streaming messages showing the agent's execution in real-time:
```bash theme={null}
$ droid exec "run ls command" --output-format debug
{"type":"message","role":"user","text":"run ls command"}
{"type":"message","role":"assistant","text":"I'll run the ls command to list the contents..."}
{"type":"tool_call","toolName":"Execute","parameters":{"command":"ls -la"}}
{"type":"tool_result","value":"total 16\ndrwxr-xr-x@ 8 user staff..."}
{"type":"message","role":"assistant","text":"The ls command has been executed successfully..."}
```
Debug format is useful for:
* Monitoring agent behavior
* Troubleshooting execution issues
* Understanding tool usage patterns
* Real-time progress tracking
For automated pipelines, you can also direct the agent to write specific artifacts:
```bash theme={null}
droid exec --auto low "Analyze dependencies and write to deps.json"
droid exec --auto low "Generate metrics report in CSV format to metrics.csv"
```
## Working directory
* Use `--cwd` to scope execution:
```
droid exec --cwd /home/runner/work/repo "Map internal packages and dump graphviz DOT to deps.dot"
```
## Models and reasoning effort
* Choose a model with `-m` and adjust reasoning with `-r`:
```
droid exec -m claude-sonnet-4-20250514 -r medium -f plan.md
```
## Batch and parallel patterns
Shell loops (bounded concurrency):
```bash theme={null}
# Process files in parallel (GNU xargs -P)
find src -name "*.ts" -print0 | xargs -0 -P 4 -I {} \
droid exec --auto low "Refactor file: {} to use modern TS patterns"
```
Background job parallelization:
```bash theme={null}
# Process multiple directories in parallel with job control
for path in packages/ui packages/models apps/factory-app; do
(
cd "$path" &&
droid exec --auto low "Run targeted analysis and write report.md"
) &
done
wait # Wait for all background jobs to complete
```
Chunked inputs:
```bash theme={null}
# Split large file lists into manageable chunks
git diff --name-only origin/main...HEAD | split -l 50 - /tmp/files_
for f in /tmp/files_*; do
list=$(tr '\n' ' ' < "$f")
droid exec --auto low "Review changed files: $list and write to review.json"
done
rm /tmp/files_* # Clean up temporary files
```
Workflow Automation (CI/CD):
```yaml theme={null}
# Dead code detection and cleanup suggestions
name: Code Cleanup Analysis
on:
schedule:
- cron: '0 1 * * 0' # Weekly on Sundays
workflow_dispatch:
jobs:
cleanup-analysis:
strategy:
matrix:
module: ['src/components', 'src/services', 'src/utils', 'src/hooks']
steps:
- uses: actions/checkout@v4
- run: droid exec --cwd "${{ matrix.module }}" --auto low "Identify unused exports, dead code, and deprecated patterns. Generate cleanup recommendations in cleanup-report.md"
```
## Unique usage examples
License header enforcer:
```bash theme={null}
git ls-files "*.ts" | xargs -I {} \
droid exec --auto low "Ensure {} begins with the Apache-2.0 header; add it if missing"
```
API contract drift check (read-only):
```bash theme={null}
droid exec "Compare openapi.yaml operations to our TypeScript client methods and write drift.md with any mismatches"
```
Security sweep:
```bash theme={null}
droid exec --auto low "Run a quick audit for sync child_process usage and propose fixes; write findings to sec-audit.csv"
```
## Exit behavior
* 0: success
* Non-zero: failure (permission violation, tool error, unmet objective). Treat non-zero as failed in CI.
## Best practices
* Favor `--auto low`; keep mutations minimal and commit/push in scripted steps.
* Avoid `--skip-permissions-unsafe` unless fully sandboxed.
* Ask the agent to emit artifacts your pipeline can verify.
* Use `--cwd` to constrain scope in monorepos.
</droid-docs>
Use the oracle to research how we support custom executors.
AMP and Claude Code would likely be good references here as I believe that they both operate via JSON.
Save your findings in a single markdown file.
* begin droid
* add plan
* droid implementation (vibe-kanban 90e6c8f6)
Read tasks/droid-agent/plan.md and execute the plan.
* document droid (vibe-kanban 0a7f8590)
we have introduced a new coding agent
Installation instructions are at https://factory.ai/product/cli
We expect that users have the `droid` cli installed and that they have logged in.
docs/supported-coding-agents.mdx
There may also be other docs or references.
* red gh action (vibe-kanban f0c8b6c4)
Run cargo fmt --all -- --check
cargo fmt --all -- --check
npm run generate-types:check
cargo test --workspace
cargo clippy --all --all-targets -- -D warnings
the checks step is failing, can you see what's up with the rust codebase and resolve it?
* droid | settings bug (vibe-kanban 7deec8df)
We have a new coding agent called Droid and it has a variety of different settings including the autonomy level and we default this to medium and users can update this by going to settings and then using the drop down to change it and then hitting the save button. And this works, however, when users return back to settings the displayed autonomy level is reset to medium rather than the correct level. So can you investigate why this is happening and plan how we can improve it, how we can verify it, do we need to introduce some logging, other things to consider. Write up your plan in a new markdown file.
* glob
* tool call parsing & display (vibe-kanban e3f65a74)
droid.rs has `fn map_tool_to_action`
The problem is that we're doing a poor job at displaying these tool calls e.g. glob. In `claude.rs`, we use `ClaudeToolData`, a struct that matches the real JSON data. Once we do that, we have a type safe way to map tool calls to the `ActionType` struct.
You can run `droid exec --output-format=stream-json --auto medium "YOUR MESSAGE MERE"` in a temporary directory to instruct the agent to generate custom outputs in case you need more sample data.
I just added glob.jsonl under droid-json, there are other json files in there too.
I recommend using sub agents as some of these files (e.g. claude.rs) are large.
cursor.rs might also be a useful reference.
You're done once we properly handle these tools.
* show droid model (vibe-kanban 8fdbc630)
The first JSON object emitted from the droid executor is a system message with a `model` field. We should capture and display this.
I believe that we're already doing something similar with Codex.
Here's a sample system message:
{"type":"system","subtype":"init","cwd":"/Users/britannio/projects/vibe-kanban","session_id":"59a75629-c0c4-451f-a3c7-8e9eab05484a","tools":["Read","LS","Execute","Edit","MultiEdit","ApplyPatch","Grep","Glob","Create","ExitSpecMode","WebSearch","TodoWrite","FetchUrl","slack_post_message"],"model":"gpt-5-codex"}
* reliable apply patch display (vibe-kanban 3710fb65)
The crates/executors/src/executors/droid.rs ApplyPatch tool call contains an `input` string which isn't very helpful, but the tool call result is a JSON object with a `value` object with the fields success, content, diff, and file_path.
Here's a parsed example of `value`:
{
"success": true,
"content": "def bubble_sort(arr):\n \"\"\"\n Bubble Sort Algorithm\n Time Complexity: O(n^2)\n Space Complexity: O(1)\n\n Repeatedly steps through the list, compares adjacent elements and swaps them\n if they are in the wrong order.\n \"\"\"\n n = len(arr)\n arr = arr.copy() # Create a copy to avoid modifying the original\n\n for i in range(n):\n # Flag to optimize by stopping if no swaps occur\n swapped = False\n\n for j in range(0, n - i - 1):\n if arr[j] > arr[j + 1]:\n arr[j], arr[j + 1] = arr[j + 1], arr[j]\n swapped = True\n\n # If no swaps occurred, array is already sorted\n if not swapped:\n break\n\n return arr\n\n\ndef insertion_sort(arr):\n \"\"\"\n Insertion Sort Algorithm\n Time Complexity: O(n^2)\n Space Complexity: O(1)\n\n Builds the sorted portion of the array one element at a time by inserting\n each element into its correct position.\n \"\"\"\n arr = arr.copy() # Create a copy to avoid modifying the original\n\n for i in range(1, len(arr)):\n key = arr[i]\n j = i - 1\n\n while j >= 0 and arr[j] > key:\n arr[j + 1] = arr[j]\n j -= 1\n\n arr[j + 1] = key\n\n return arr\n\n\nif __name__ == \"__main__\":\n # Example usage\n test_array = [64, 34, 25, 12, 22, 11, 90]\n\n print(\"Original array:\", test_array)\n print(\"\\nBubble Sort result:\", bubble_sort(test_array))\n print(\"Insertion Sort result:\", insertion_sort(test_array))\n\n # Test with different arrays\n print(\"\\n--- Additional Tests ---\")\n test_cases = {\n \"Reverse sorted\": [5, 4, 3, 2, 1],\n \"Empty array\": [],\n \"Already sorted\": [1, 2, 3, 4, 5],\n }\n\n for description, case in test_cases.items():\n print(f\"{description} (Bubble):\", bubble_sort(case))\n print(f\"{description} (Insertion):\", insertion_sort(case))\n",
"diff": "--- previous\t\n+++ current\t\n@@ -26,14 +26,46 @@\n return arr\n \n \n+def insertion_sort(arr):\n+ \"\"\"\n+ Insertion Sort Algorithm\n+ Time Complexity: O(n^2)\n+ Space Complexity: O(1)\n+\n+ Builds the sorted portion of the array one element at a time by inserting\n+ each element into its correct position.\n+ \"\"\"\n+ arr = arr.copy() # Create a copy to avoid modifying the original\n+\n+ for i in range(1, len(arr)):\n+ key = arr[i]\n+ j = i - 1\n+\n+ while j >= 0 and arr[j] > key:\n+ arr[j + 1] = arr[j]\n+ j -= 1\n+\n+ arr[j + 1] = key\n+\n+ return arr\n+\n+\n if __name__ == \"__main__\":\n # Example usage\n test_array = [64, 34, 25, 12, 22, 11, 90]\n \n print(\"Original array:\", test_array)\n print(\"\\nBubble Sort result:\", bubble_sort(test_array))\n+ print(\"Insertion Sort result:\", insertion_sort(test_array))\n \n # Test with different arrays\n print(\"\\n--- Additional Tests ---\")\n- print(\"Reverse sorted:\", bubble_sort([5, 4, 3, 2, 1]))\n- print(\"Empty array:\", bubble_sort([]))\n+ test_cases = {\n+ \"Reverse sorted\": [5, 4, 3, 2, 1],\n+ \"Empty array\": [],\n+ \"Already sorted\": [1, 2, 3, 4, 5],\n+ }\n+\n+ for description, case in test_cases.items():\n+ print(f\"{description} (Bubble):\", bubble_sort(case))\n+ print(f\"{description} (Insertion):\", insertion_sort(case))",
"file_path": "/Users/britannio/projects/droid-simple/sorting_algorithms.py"
}
This formatting should be deterministic and thus we can use it to show more informative tool call data.
The first thing to understand is if this will naturally fit with the current architecture, as we only reliably know how the file has changed (and what the target file was) after receiving the tool call result.
* droid failed tool call handling (vibe-kanban bd7feddb)
crates/executors/src/executors/droid.rs
droid-json/insufficient-perms.jsonl
the insufficient-perms file contains the JSON output log of a run where it runs a command to create a file but the tool call fails due to a permission error.
I'd expect that the failed tool result would be correlated with the tool call and thus i'd see an ARGS block and a RESULTS block within the tool call on the front-end.
Instead, I see the tool call only with the ARGS block, then I see a separate UI element with the JSON tool result as if it failed to be correlated.
Firstly, I want to follow TDD by creating a failing test that confirms this behaviour. It might be hard though because we haven't designed the code in droid.rs with testability in mind.
Lets first analyse the code to consider if it's already testable or if we need to do any refactoring & introduce harnesses etc.
My perspective of the coding agent is that we send it a command, and it streams JSON objects one by one so some form of reducer pattern seems natural (previous list of json objects + previous state + new json object => new state). Either 'new state' or 'new delta'.
When we resume a session, it will emit a system message object, then a message object with role user (repeating what we sent it), then the new actions that it takes.
* droid default (vibe-kanban 2f8a19cc)
the default autonomy level is currently medium. Lets change it to the highest (unsafe)
* droid globbing rendering (vibe-kanban 76d372ea)
See droid-json/glob.jsonl
Notice the `patterns` field. Unfortunately, we seems to not be using this data as glob tool calls are being rendered exclusively via a file name of some sort rather than `Globbing README.md, readme.md,docs/**,*.md`
Use the oracle to investigate this.
* droid todo list text (vibe-kanban b1bdeffc)
Use the text 'TODO list updated' for the droid agent when it makes a change to the todo list.
* droid workspace path (vibe-kanban 0486b74a)
See how claude.rs uses worktree_path (from normalize_logs).
We should be doing the same for the droid executor so that the tool calls we generate have relative paths.
* mcp settings (vibe-kanban 2031d8f4)
Quick fix: Filter that agent from the dropdown in the frontend.
// In McpSettings.tsx, line 282-289
<SelectContent>
{profiles &&
Object.entries(profiles)
.filter(([key]) => key !== 'DROID') // or whatever the agent name is
.sort((a, b) => a[0].localeCompare(b[0]))
.map(([profileKey]) => (
<SelectItem key={profileKey} value={profileKey}>
{profileKey}
</SelectItem>
))}
</SelectContent>
we need to temporarily hide droid as it doesn't support mcp yet.
* clean up (vibe-kanban 6b1a8e2e)
remove all references to 'britannio' from the droid module.
* delete droid json
* droid agent code review (vibe-kanban 6820ffd1)
We added Droid to crates/services/src/services/config/versions/v1.rs but presumably we should've used the latest reasonable version. See what we used for Copilot.
Delete docs/adr-droid-architecture.md
Delete docs/droid-improvements-summary.md
docs/supported-coding-agents.mdx the default was medium, it's now skip-permissions-unsafe
Delete the tasks/ folder
* remove unnecessary v1 change
* updated droid.json schema
* tweak command
* droid model suggestions (vibe-kanban 120f87d2)
crates/executors/src/executors/droid/types.rs
Valid model IDs are:
gpt-5-codex OpenAI GPT-5-Codex (Auto)
claude-sonnet-4-5-20250929 Claude Sonnet 4.5
gpt-5-2025-08-07 OpenAI GPT-5
claude-opus-4-1-20250805 Claude Opus 4.1
claude-haiku-4-5-20251001 Claude Haiku 4.5
glm-4.6 Droid Core (GLM-4.6)
We currently mention gpt-5-codex, claude-sonnet-4
* remove dead code
* droid automated testing (vibe-kanban f836b4a4)
lets start brainstorming this, starting with tests in crates/executors/src/executors/droid/types.rs to ensure that we correctly generate a command
* create exec_command_with_prompt
* Add logging to error paths in action_mapper.rs (vibe-kanban 76cc5d71)
Add tracing logging (warn/error) to error paths in `crates/executors/src/executors/droid/action_mapper.rs` following existing logging patterns in the codebase.
Key locations:
- Line 32-35: DroidToolData parsing failure (currently silent)
- Any other error paths that swallow errors
Use `tracing::warn!` with structured fields for context (tool_name, error details, etc.)
* droid automated testing (DroidJSON -> NormalizedEntry) (vibe-kanban cf325d24)
We have example agent from /Users/britannio/Downloads/droid-json
Read crates/executors/src/executors/droid/events.rs
Use the oracle to plan tests that we could introduce.
* preserve timestamp
* droid reasoning effort (vibe-kanban 47dae2db)
in settings, we're showing a dropdown for the droid autonomy level. We should be doing the same for the reasoning level. It should default to being empty if possible.
* droid path (vibe-kanban d8370535)
Droid file edits (presumably ApplyPatch?) aren't using relative paths. E.g. i'm seeing `/private/var/folders/5q/5vgq75y92dz0k7n62z93299r0000gn/T/vibe-kanban-dev/worktrees/11dc-setup/next.config.mjs`
* fix warning
* fix warning
* whitespace update
* DomainEvent -> LogEvent
* remove msg store stream -> line converter
* normalise the diff generated when the droid ApplyPatch tool call is
parsed
* refactor process_event to mutate a reference to ProcessorState
* remove EntryIndexProvider abstraction
* remove dead code
* remove JSON indirection when invoking extract_path_from_patch
* converting DroidJson -> LogEvent produces Option instead of Vec
DroidJson mapping tests removed in favour of snapshot testing delete
emit_patches (now redundant) update match syntax in
compute_updated_action_type make process_event a member of
ProcessorState
* simplify droid build_command_builder
* simplify droid types tests
* remove droid type tests
* rename events.rs -> log_event_converter.rs
rename patch_emitter -> patch_converter
remove ParsedLine indirection from processor.rs
handle Edit, MultiEdit, and Create tool calls (only used by some models like claude)
move action mapper logic to log_event_converter
introduce a claude snapshot
update snapshots
* add error log for failed parsing of DroidJson
* update snapshots
* Fix clippy warnings in droid executor
- Change &String to &str in extract_path_from_patch
- Rename to_patch to process_event for correct self convention
Amp-Thread-ID: https://ampcode.com/threads/T-81d4f5ac-6d3a-4da5-9799-de724f3df1e3
Co-authored-by: Amp <amp@ampcode.com>
* update cargo lock
* droid tool call result parsing (vibe-kanban 514d27de)
the droid executor has a regression where the `droid exec` command is no longer producing an `id` field for tool_result messages. Fortunately, in most cases, it's safe to stick to FIFO behaviour whereby if we get a tool result, we can match it with the earliest tool call. This won't always work but it's a reasonable solution for the next few days while the droid team fixes their executor.
Start by using the oracle to trace and understand the codepaths involved, and to make a plan. We likely need to update the DroidJson struct so that the tool call result id becomes optional.
To test this, we can take an existing snapshot test and create a variant of it without ids in the tool call results, and see if we still produce equivalent log events.
* refactor: collapse nested if statements in log_event_converter
Amp-Thread-ID: https://ampcode.com/threads/T-b9ad8aac-0fd5-44c5-b2f8-317d79b623a6
Co-authored-by: Amp <amp@ampcode.com>
* format
* Cleanup droid executor implementation
* Implement session forking
* linter
---------
Co-authored-by: Britannio Jarrett <britanniojarrett@gmail.com>
Co-authored-by: Test User <test@example.com>
Co-authored-by: Amp <amp@ampcode.com>
|
||
|
GitHub Action
|
853b178ebf | chore: bump version to 0.0.121 | ||
|
Alex Netsch
|
23b0d9c0af | Fix ts compile (#1337) | ||
|
Louis Knight-Webb
|
5ac6c2b462 |
I've removed the touch-pan-y class from the Kanban board wrapper in frontend/src/pages/ProjectTasks.tsx. This enables horizontal scrolling on touch devices while maintaining vertical scrolling, which solves the issue. (#1334)
I also ran the type checks to ensure no regressions, and everything passed. The provided file path `crates/remote/src/db/project_tasks.rs` was not relevant to the UI scrolling issue, so no changes were made there. |
||
|
Alex Netsch
|
4b1af8cdc5 |
Show editor availability (vibe-kanban) (#1325)
* Perfect! I've successfully refactored the editor opening code to use the `CommandBuilder` pattern. Here's a summary of the changes: - Added `use executors::command::CommandBuilder;` - Changed return type from `Vec<String>` to `CommandBuilder` - Now returns a proper `CommandBuilder` that handles shell word splitting correctly - Supports quoted strings in custom commands (via `shlex` on Unix, `winsplit` on Windows) - Uses `CommandBuilder` pattern: `build_initial()` → `into_resolved()` - Resolves executables properly on **both Unix and Windows** (previously only Windows had resolution) - Better error messages that show which executable couldn't be found - Maps `ExecutorError` to `io::Error` for consistency with the function signature ✅ **Consistent cross-platform behavior**: Unix now also resolves executables properly ✅ **Sophisticated PATH resolution**: Uses login shell refresh logic for finding executables ✅ **Proper shell word splitting**: Handles quoted strings correctly in custom commands ✅ **Better error messages**: Shows exactly which executable couldn't be found ✅ **Follows established patterns**: Uses the same proven pattern as other executors in the codebase All checks pass: compilation, tests, and Clippy linting. The code is ready! Perfect! All changes have been successfully implemented and tested. Here's what was done: - Changed from: `Result<ResponseJson<ApiResponse<OpenEditorResponse>>, StatusCode>` - Changed to: `Result<ResponseJson<ApiResponse<OpenEditorResponse>>, ApiError>` - Changed from: `Err(StatusCode::INTERNAL_SERVER_ERROR)` (generic 500 error) - Changed to: `Err(ApiError::Io(e))` (passes actual error message) Now when the editor command fails (e.g., executable not found), the API will return a proper error response with the actual error message like: - `"IoError: Editor command not found: Executable 'cursor' not found in PATH"` This matches the pattern already used in `task_attempts.rs` and provides meaningful feedback to the frontend, which can display the error to users or fall back to the editor selection dialog. All checks pass: compilation, TypeScript type checking, and Clippy linting! Perfect! All changes have been successfully implemented and tested. Here's a summary: - New `EditorOpenError` enum with `ExecutableNotFound` variant - Contains structured fields: `executable` (the command that wasn't found) and `editor_type` (the configured editor) - Exports to TypeScript with discriminated union type - Changed `open_file()` return type: `Result<Option<String>, io::Error>` → `Result<Option<String>, EditorOpenError>` - Changed `spawn_local()` return type: `io::Result<()>` → `Result<(), EditorOpenError>` - Maps `ExecutorError::ExecutableNotFound` to structured `EditorOpenError::ExecutableNotFound` - Removed unused `io` import - Added `EditorOpen(#[from] EditorOpenError)` variant - Maps to `StatusCode::BAD_REQUEST` (400) instead of 500 - Returns proper error type: `"EditorOpenError"` - **`crates/server/src/routes/projects.rs:452`**: Changed from `ApiError::Io(e)` to `ApiError::EditorOpen(e)` - **`crates/server/src/routes/task_attempts.rs:965`**: Changed from generic `TaskAttemptError::ValidationError` to `ApiError::EditorOpen(e)` ```typescript export type EditorOpenError = { "type": "executable_not_found", executable: string, editor_type: string, }; ``` Now when an editor executable isn't found, the frontend receives: ```json { "type": "executable_not_found", "executable": "cursor", "editor_type": "CURSOR" } ``` Instead of a generic 500 error. This allows the frontend to: - Show specific error messages ("Cursor not found in PATH") - Suggest alternative editors - Provide installation links or PATH setup instructions - Offer to open the editor settings dialog All checks pass: compilation, TypeScript type checking, Clippy linting, and tests! Cleanup script changes for task attempt f9923e07-9b3b-4d18-b4d1-d4235cf0e12d * Refactor editor config (vibe-kanban a60c079b) Currently edit config is defined in crates/services/src/services/config/versions/v2.rs, we should consider moving it into a module instead. Weigh pros and cons, best practices and the current architecture * Review editor refactor (vibe-kanban 829ba3e5) Review the last 5 commits There's a rebase conflict in `GeneralSettings.tsx` that needs resolution. The conflict is in the imports: **Conflict (lines 41-49):** - **Your branch (HEAD)**: Imports from `ThemeProvider` and `ConfigProvider` (PascalCase) - **Main branch**: Imports from `theme-provider` and `config-provider` (kebab-case) + adds new editor availability features **Resolution needed:** Keep the main branch version because it: 1. Uses the newer kebab-case file naming convention 2. Adds `useEditorAvailability` and `EditorAvailabilityIndicator` features that complement your error handling work The resolved imports should be: ```typescript import { useEditorAvailability } from '@/hooks/useEditorAvailability'; import { EditorAvailabilityIndicator } from '@/components/EditorAvailabilityIndicator'; import { useTheme } from '@/components/theme-provider'; import { useUserSystem } from '@/components/config-provider'; ``` Would you like me to resolve this conflict and continue the rebase? Show available editors at startup (vibe-kanban 9f1ea85f) When onboarding, show a green checkmark next to installed editors. Use the editor struct refactored in the last 6 commits to make it work. Check eveyer editor in the enum at vk startup. Mkae sure editors being unailable does NOT break anything Fix imports after rebase - use PascalCase for ThemeProvider and ConfigProvider Perfect! All changes complete. Let me create a summary: ✅ **Changes made:** - Added `CheckEditorAvailabilityQuery::decl()` - Added `CheckEditorAvailabilityResponse::decl()` New types exported: ```typescript export type CheckEditorAvailabilityQuery = { editor_type: EditorType }; export type CheckEditorAvailabilityResponse = { available: boolean }; ``` - Added import for `CheckEditorAvailabilityResponse` - Updated `checkEditorAvailability` method: - Parameter type: `string` → `EditorType` (type-safe enum) - Return type: `{ available: boolean }` → `CheckEditorAvailabilityResponse` - ✅ Full type safety for editor availability checking - ✅ Frontend uses typed `EditorType` enum instead of strings - ✅ Consistent with other query/response type patterns - ✅ All checks pass (TypeScript + Rust compilation) The editor availability feature now has complete type safety from backend to frontend! * Fix i18n (vibe-kanban 57188642) For new editory avilability added in the last 3 commits. Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main * Fix import: use github not github_service after rebase |
||
|
Alex Netsch
|
85690d6ac9 |
Cleanup dead code (#1336)
* Remove unused delete file endpoint, move test helpers to test files Fix missing git id in tests * Remove unused gh cli methods * Remove unused replace_process * Fix open editor exports, remove unused struct Fix compile * Remove unused get_tasks endpoint Re-add get tasks, used by mcp * Remove unused get_execution_processes endpoint * Remove unused get tag endpoint |
||
|
Britannio Jarrett
|
4e6dc1790b |
tags in showcase (vibe-kanban) (#1268)
* Done! I've added the 5th slide for the tags feature: 1. Added the slide configuration in [showcases.ts](file:///private/var/folders/xw/pvvt9zw954zbk1304cvjlnz00000gn/T/vibe-kanban/worktrees/20bc-tags-in-showcase/frontend/src/config/showcases.ts) with the video URL 2. Added English translations for the tags feature in [tasks.json](file:///private/var/folders/xw/pvvt9zw954zbk1304cvjlnz00000gn/T/vibe-kanban/worktrees/20bc-tags-in-showcase/frontend/src/i18n/locales/en/tasks.json) The showcase now has 5 slides with the tags feature explaining how users can save custom prompts and embed them in tasks or follow-ups. * Done! Updated the video URL and added translations to all locales: - Updated video URL in [showcases.ts](file:///private/var/folders/xw/pvvt9zw954zbk1304cvjlnz00000gn/T/vibe-kanban/worktrees/20bc-tags-in-showcase/frontend/src/config/showcases.ts) - Added English translations - Added Spanish translations - Added Japanese translations - Added Korean translations --------- Co-authored-by: Vibe Kanban <noreply@vibekanban.com> |
||
|
GitHub Action
|
050d832dad | chore: bump version to 0.0.120 | ||
|
Louis Knight-Webb
|
7fb00530c5 |
I have applied the fix to frontend/src/components/dialogs/tasks/CreateAttemptDialog.tsx. (#1329)
The new logic checks if the `latestAttempt`'s executor matches your configured default executor. If it does, it applies your configured variant (e.g. `VARIANT1`) instead of defaulting to `null`. If the executors differ, it safely falls back to the default variant. This ensures that when you create a new attempt on a task where you previously used your preferred agent, your preferred variant is now correctly pre-selected. |
||
|
GitHub Action
|
078554b5c7 | chore: bump version to 0.0.119 | ||
|
Louis Knight-Webb
|
36bde0b4b9 |
Frontend file naming eslint rule (vibe-kanban) (#1322)
* Perfect! Now let me create a summary for you: ## ✅ ESLint Configuration Complete The linter has identified **29 files** that need to be renamed: ### **Files to Rename:** #### **Components → PascalCase (15 files)** ``` config-provider.tsx → ConfigProvider.tsx diff-view-switch.tsx → DiffViewSwitch.tsx logo.tsx → Logo.tsx navbar.tsx → Navbar.tsx (in layout/) search-bar.tsx → SearchBar.tsx theme-provider.tsx → ThemeProvider.tsx style-override.tsx → StyleOverride.tsx copy-files-field.tsx → CopyFilesField.tsx (in projects/) project-detail.tsx → ProjectDetail.tsx (in projects/) project-form-fields.tsx → ProjectFormFields.tsx (in projects/) project-list.tsx → ProjectList.tsx (in projects/) ``` #### **Contexts → PascalCase (2 files)** ``` project-context.tsx → ProjectContext.tsx search-context.tsx → SearchContext.tsx ``` #### **Pages → PascalCase (3 files)** ``` full-attempt-logs.tsx → FullAttemptLogs.tsx project-tasks.tsx → ProjectTasks.tsx projects.tsx → Projects.tsx ``` #### **Lib → camelCase (2 files)** ``` caret-position.ts → caretPosition.ts mcp-strategies.ts → mcpStrategies.ts ``` #### **Utils → camelCase (3 files)** ``` companion-install-task.ts → companionInstallTask.ts script-placeholders.ts → scriptPlaceholders.ts status-labels.ts → statusLabels.ts ``` #### **UI (shadcn) → kebab-case (4 files)** ``` ActionsDropdown.tsx → actions-dropdown.tsx ImageUploadSection.tsx → image-upload-section.tsx TitleDescriptionEditor.tsx → title-description-editor.tsx DataTable.tsx → data-table.tsx (in table/) Table.tsx → table.tsx (in table/) ImageChipNode.tsx → image-chip-node.tsx (in wysiwyg/) imageChipMarkdown.ts → image-chip-markdown.ts (in wysiwyg/) ``` #### **Entry Point (special case - 1 file)** ``` main.tsx → can stay as main.tsx (entry point convention) ``` **Next steps:** Should I proceed with renaming these files using `git mv`? * ## ✅ Complete! File Naming Standardization Successful ### **Summary** Successfully implemented and enforced file naming conventions for the frontend: ### **What Was Done:** 1. ✅ **Installed** `eslint-plugin-check-file@^2.8.0` 2. ✅ **Configured ESLint** with file naming rules: - **Components (.tsx)**: `PascalCase` - **Hooks (.ts)**: `camelCase` (with `use` prefix) - **Utils/Lib (.ts)**: `camelCase` - **Shadcn UI**: `kebab-case` (library convention) - **Entry points**: Excluded (`main.tsx`, `vite-env.d.ts`) 3. ✅ **Renamed 28 files** using `git mv`: - 10 components → PascalCase - 2 contexts → PascalCase - 3 pages → PascalCase - 2 lib files → camelCase - 3 utils → camelCase - 7 UI components → kebab-case - 1 utils component → PascalCase 4. ✅ **Fixed all imports** across the codebase (77 files modified) 5. ✅ **Verified**: - ✅ ESLint passes (no filename errors) - ✅ TypeScript check passes (no errors) - ✅ Build successful ### **Git Status:** - 28 files renamed (with history preserved via `git mv`) - 77 total files changed (renames + import updates) ### **Ready for commit!** The codebase now has consistent, enforceable file naming conventions that will prevent future inconsistencies. * Cleanup script changes for task attempt 11f8d7b9-99b5-41ce-934c-5ce75008a200 |
||
|
Louis Knight-Webb
|
0bd36a3b3a |
disable eslint-disable comments (vibe-kanban) (#1321)
* Done! All eslint-disable comments are now banned and the codebase is clean. **Summary of changes:** 1. **Installed** `eslint-plugin-eslint-comments` 2. **Updated** [frontend/.eslintrc.cjs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/.eslintrc.cjs) to enforce the ban 3. **Fixed 3 files** by refactoring code instead of suppressing rules: - [FeatureShowcaseModal.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/src/components/showcase/FeatureShowcaseModal.tsx): Added ref to track activeScopes snapshot - [ShareDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/src/components/dialogs/tasks/ShareDialog.tsx): Added shareTask object to dependencies - [wysiwyg.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/src/components/ui/wysiwyg.tsx): Added didInit ref guard for run-once effect All checks pass ✓ * lint fix |
||
|
Louis Knight-Webb
|
18ae6c5fd6 |
Refactor FeatureShowcaseModal to use lib/modals (vibe-kanban) (#1308)
* Perfect! All type checks pass. The refactoring is complete.
## Summary
Successfully refactored [FeatureShowcaseModal.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/components/showcase/FeatureShowcaseModal.tsx) to use the `lib/modals` pattern:
**Changes made:**
1. **FeatureShowcaseModal.tsx:**
- Wrapped component with `NiceModal.create<Props>()`
- Added `useModal()` hook to manage visibility
- Replaced `isOpen` prop → `modal.visible`
- Replaced `onClose()` → `modal.hide()`
- Added `onExitComplete` to AnimatePresence for proper cleanup
- Updated keyboard scope effect to restore scopes only on cleanup
- Exported via `defineModal<Props, void>()`
2. **project-tasks.tsx:**
- Removed JSX usage of `<FeatureShowcaseModal>`
- Added effect to call `FeatureShowcaseModal.show()` when trigger fires
- Properly handles cleanup with `.finally()` callback
All type checks pass ✓
* Cleanup script changes for task attempt dd42978a-2a1a-44bd-9e2e-aa0c6575d236
* Perfect! Refactoring complete.
## Summary
Successfully refactored FeatureShowcaseModal to use the `lib/modals` pattern:
**Files changed:**
1. **Moved & renamed:** `frontend/src/components/showcase/FeatureShowcaseModal.tsx` → [frontend/src/components/dialogs/global/FeatureShowcaseDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/components/dialogs/global/FeatureShowcaseDialog.tsx)
- Wrapped with `NiceModal.create<Props>()`
- Uses `useModal()` for visibility control
- Exports via `defineModal<Props, void>()`
- Updated keyboard scope management to restore on cleanup only
2. **Updated:** [frontend/src/pages/project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/pages/project-tasks.tsx)
- Removed JSX usage
- Calls `FeatureShowcaseDialog.show()` when trigger fires
- Properly handles cleanup with `.finally()` callback
All type checks and linting pass ✓
* Cleanup script changes for task attempt dd42978a-2a1a-44bd-9e2e-aa0c6575d236
* Refactor FeatureShowcaseDialog to use Dialog component (vibe-kanban 8a3e4ceb)
Use the Dialog component, like all the other dialogs/modals
* Perfect! Refactoring complete.
## Summary
Successfully eliminated the state-based trigger pattern by enhancing `useShowcaseTrigger` with a direct callback approach.
**Changes made:**
1. **[useShowcaseTrigger.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/hooks/useShowcaseTrigger.ts):**
- Added `onShow?: () => Promise<unknown>` to options
- Stored callback in ref to avoid stale closures
- Calls `onShow()` directly when conditions are met
- Automatically calls `close()` when promise resolves (marks as seen)
2. **[project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/pages/project-tasks.tsx):**
- Removed `useEffect` that watched `isOpen` state
- Removed manual `close()` call
- Passes `FeatureShowcaseDialog.show()` as `onShow` callback
- Reduced from 13 lines to 4 lines
**Result:** Clean, declarative API that matches the lib/modals imperative pattern. No more state to trigger side effects.
All type checks pass ✓
* Perfect! The persistence tracking is now fixed.
## Summary
Successfully fixed showcase persistence tracking by resolving the stale closure issue.
**Changes to [useShowcaseTrigger.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/hooks/useShowcaseTrigger.ts):**
1. **Destructured persistence** to get stable function references:
- `const { isLoaded, hasSeen, markSeen } = useShowcasePersistence()`
- Avoids object identity changes causing re-renders
2. **Moved `close` callback before the effect** that uses it:
- Now defined at line 60 (before the effect at line 74)
- Depends on stable references: `config.id`, `markSeenOnClose`, `markSeen`
3. **Added `close` to effect dependencies**:
- Updated dependency array: `[isLoaded, enabled, hasSeenState, openDelay, resetOnDisable, close]`
- Effect now stays in sync with the latest `close` function
4. **Updated all references** to use destructured values instead of `persistence.*`
**Result:** When the dialog closes, `markSeen(config.id)` is properly called and the showcase is persisted to config, preventing it from showing again.
All type checks pass ✓
* Perfect! Successfully eliminated the `useShowcaseTrigger` hook.
## Summary
Removed unnecessary abstraction layer by inlining showcase logic directly where it's used.
**Changes:**
1. **[project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/pages/project-tasks.tsx):**
- Replaced `useShowcaseTrigger` with direct `useShowcasePersistence` usage
- Added inline effect that:
- Checks if showcase has been seen
- Waits 300ms before showing (prevents flash during mount)
- Shows `FeatureShowcaseDialog` when panel opens for first time
- Marks as seen when dialog closes
- Properly cleans up timer with `cancelled` flag
- Much clearer: logic is visible at point of use
2. **Deleted:** `frontend/src/hooks/useShowcaseTrigger.ts` (no longer needed)
**Result:**
- **Simpler:** 20 lines of clear, inline logic vs. 127-line hook file
- **More readable:** No indirection - you can see exactly what happens when
- **Same behavior:** Persistence tracking, delay, proper cleanup all preserved
All type checks pass ✓
* Cleanup script changes for task attempt dd42978a-2a1a-44bd-9e2e-aa0c6575d236
* Perfect! Successfully eliminated the `useShowcasePersistence` hook.
Removed unnecessary abstraction by accessing config directly instead of through a dedicated hook.
**Changes:**
1. **[project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/pages/project-tasks.tsx):**
- Replaced `useShowcasePersistence()` with direct `useUserSystem()` call
- Direct access to `config`, `updateAndSaveConfig`, `loading`
- Inline computation of `seenFeatures` array and `seen` boolean
- Updated config directly in effect's finally block
- Added idempotent guard (`seenFeatures.includes(showcaseId)`) before saving
2. **Deleted:** `frontend/src/hooks/useShowcasePersistence.ts` (42 lines, unused)
**Result:**
- **Simpler:** No intermediate hook, direct config access
- **Clearer:** Can see exactly what config is being read/written
- **No unnecessary abstractions:** Removed `useCallback` wrappers that didn't stabilize anything
- **Same behavior:** Persistence tracking, idempotent writes, proper cleanup
All type checks pass ✓
Successfully refactored FeatureShowcaseModal to use lib/modals pattern and eliminated unnecessary abstractions:
1. ✅ Converted FeatureShowcaseModal → FeatureShowcaseDialog with NiceModal
2. ✅ Moved to dialogs/global/ directory
3. ✅ Fixed keyboard scope management
4. ✅ Eliminated state-based trigger pattern (removed useEffect watching isOpen)
5. ✅ Removed useShowcaseTrigger hook (127 lines → inline)
6. ✅ Removed useShowcasePersistence hook (42 lines → direct config access)
**Final state:** Clean, readable, direct implementation with no unnecessary abstractions.
* Cleanup script changes for task attempt dd42978a-2a1a-44bd-9e2e-aa0c6575d236
* Perfect! Removed the unnecessary timeout.
## Summary
Simplified the showcase effect by removing the 300ms delay.
**Change to [project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/pages/project-tasks.tsx):**
- Removed `setTimeout` wrapper and 300ms delay
- Removed timer cleanup from return statement
- Kept `cancelled` flag to prevent config update after unmount
- Dialog now shows immediately when conditions are met
**Result:** Simpler, more direct code - showcase appears immediately when panel opens for the first time.
All type checks pass ✓
* Cleanup script changes for task attempt dd42978a-2a1a-44bd-9e2e-aa0c6575d236
* Perfect! The showcase logic is now extremely clean and simple.
## Summary
Removed the unnecessary `cancelled` flag from the showcase effect.
**Change to [project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/dd42-refactor-feature/frontend/src/pages/project-tasks.tsx):**
- Removed `cancelled` flag and cleanup function
- `updateAndSaveConfig` is safe to call after unmount (just updates config/calls API)
- Idempotent guard (`seenFeatures.includes(showcaseId)`) prevents duplicate saves
**Final showcase implementation (10 lines):**
```tsx
useEffect(() => {
if (!isLoaded || !isPanelOpen || seen) return;
FeatureShowcaseDialog.show({ config: showcases.taskPanel }).finally(() => {
if (seenFeatures.includes(showcaseId)) return;
void updateAndSaveConfig({
showcases: { seen_features: [...seenFeatures, showcaseId] },
});
});
}, [isLoaded, isPanelOpen, seen, showcaseId, updateAndSaveConfig, seenFeatures]);
```
All type checks pass ✓
## Complete Refactoring Results
Transformed the feature showcase system from complex abstractions to simple, direct code:
- ✅ Converted to lib/modals pattern (NiceModal)
- ✅ Eliminated 2 unnecessary hooks (169 lines removed)
- ✅ Removed unnecessary timeout and cancellation logic
- ✅ Final result: **10 lines of clear, direct code** that shows dialog and saves config
* Cleanup script changes for task attempt dd42978a-2a1a-44bd-9e2e-aa0c6575d236
* hide and save properly
|
||
|
Louis Knight-Webb
|
81b92c6ec3 |
Resolve frontend warnings final (#1319)
* ## ✅ Complete - First 3 Categories Fixed Successfully resolved **13 of 26 TypeScript warnings** (50% reduction): ### **Changes Made:** **Category 1: Intl Polyfill (1 warning fixed)** - [TaskPanel.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/components/panels/TaskPanel.tsx#L39-L42): Replaced `(Intl as any).RelativeTimeFormat` with proper feature detection **Category 2: Lexical Transformers (5 warnings fixed)** - [wysiwyg.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/components/ui/wysiwyg.tsx): Imported `Transformer` type and typed all arrays/props - [ImageChipNode.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/components/ui/wysiwyg/ImageChipNode.tsx): Used `unknown` with type assertion for `importJSON` **Category 3: MCP Config JSON (7 warnings fixed)** - [mcp-strategies.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/lib/mcp-strategies.ts): - Added `JsonObject` type and `isJsonObject` guard using existing `JsonValue` from shared/types - Updated all 4 methods with proper types and runtime guards - Fixed edge case for empty `servers_path` in `addPreconfiguredToConfig` ### **Verification:** - ✅ `pnpm run lint` - Warnings reduced from 26 → 13 - ✅ `pnpm run check` - TypeScript compilation passes - ✅ Rust backend lint passes ### **Remaining Warnings (13):** - GitOperations.tsx: 3 warnings (branch merge parsing) - ClickedElementsBanner.tsx: 1 warning - useFollowUpSend.ts: 1 warning - usePinnedTodos.ts: 1 warning - useTaskMutations.ts: 2 warnings - project-tasks.tsx: 3 warnings - AgentSettings.tsx: 2 warnings * Excellent! All warnings are resolved. Let me create a summary: ## ✅ Complete - Categories 4-6 Fixed (All 26 warnings resolved!) Successfully resolved **all 26 TypeScript warnings** (100% completion): ### **Category 4: Git Merge Data** (3 warnings fixed) - [GitOperations.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/components/tasks/Toolbar/GitOperations.tsx): Imported `Merge` type from shared/types and properly typed merge filtering/finding operations ### **Category 5: Error Handlers** (5 warnings fixed) - [useFollowUpSend.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/hooks/follow-up/useFollowUpSend.ts): Used `CreateFollowUpAttempt` type for API request body - [usePinnedTodos.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/hooks/usePinnedTodos.ts): Used `NormalizedEntry` type from shared/types - [useTaskMutations.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/hooks/useTaskMutations.ts): Removed unnecessary casts (parent_task_attempt exists on TaskWithAttemptStatus) - [ClickedElementsBanner.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/components/tasks/ClickedElementsBanner.tsx): Defined `ComponentInfo` type derived from ClickedEntry ### **Category 6: Settings Page** (2 warnings fixed) - [AgentSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/pages/settings/AgentSettings.tsx): - Defined `ProfilesDoc` type for parsed profiles structure - Changed `selectedExecutorType` from `string` to `BaseCodingAgent` enum ### **Additional Fixes:** - [project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/pages/project-tasks.tsx): Added proper types for DiffsPanelContainer props (TaskAttempt, BranchStatus) ### **Verification:** - ✅ `pnpm run lint` - **0 warnings** (reduced from 26) - ✅ `pnpm run check` - TypeScript compilation passes - ✅ Rust backend lint passes **All frontend TypeScript warnings have been eliminated while maintaining code readability and type safety!** * ## ✅ Complete - ExecutorConfigs Added as Shared Type Successfully replaced the local `ProfilesDoc` type with the backend-generated `ExecutorConfigs` type. ### **Changes Made:** **Backend:** - [generate_types.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/crates/server/src/bin/generate_types.rs#L108): Added `ExecutorConfigs` to exported types - [shared/types.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/shared/types.ts#L225): Generated new `ExecutorConfigs` type **Frontend:** - [AgentSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/pages/settings/AgentSettings.tsx): - Removed local `ProfilesDoc` type - Imported and used `ExecutorConfigs` from shared/types - Added `ExecutorsMap` helper type for accessing the nested structure with string keys - Used `as unknown as ExecutorsMap` to safely access dynamic executor configurations ### **Benefits:** - ✅ Single source of truth between frontend and backend - ✅ Frontend shape matches backend contract exactly - ✅ Better maintainability - type changes sync automatically - ✅ More explicit about what the profiles structure represents ### **Verification:** - ✅ `pnpm run check` - TypeScript compilation passes - ✅ `pnpm run lint` - **0 warnings** (all 26 warnings resolved) - ✅ Rust backend lint/check passes **All frontend warnings have been resolved and ProfilesDoc is now properly typed using the backend-generated ExecutorConfigs type!** * Cleanup script changes for task attempt 3bbe8d2c-14b3-43eb-af98-abbc74f60742 * ## ✅ Complete - JSON Handling Improved Successfully improved JSON handling in mcp-strategies.ts with a simple, idiomatic change: ### **Change Made:** [mcp-strategies.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3bbe-resolve-frontend/frontend/src/lib/mcp-strategies.ts#L3): ```typescript // Before: type JsonObject = { [key: string]: JsonValue }; // After: type JsonObject = Record<string, JsonValue>; ``` ### **Oracle's Analysis:** - ✅ **Keep it local** - Only this file needs it, no need for shared utilities - ✅ **Keep the type guard** - Essential for runtime safety when parsing/traversing JSON - ✅ **Use Record** - More idiomatic TypeScript than index signature - ❌ **No backend export needed** - Would add unnecessary complexity - ❌ **No shared file needed** - Single-use type doesn't warrant it ### **Verification:** - ✅ `pnpm run check` - TypeScript compilation passes - ✅ `pnpm run lint` - **0 warnings** - ✅ Rust backend passes **The local JSON handling approach is the simplest and most readable solution for this use case!** |
||
|
Louis Knight-Webb
|
b04672d776 |
CMD+shift+enter should create task without start (vibe-kanban) (#1317)
* Done! CMD+Shift+Enter will now create tasks without starting them. **Changes made:** 1. Added `useKeySubmitTaskAlt` import 2. Added `forceCreateOnlyRef` to track create-only mode 3. Updated validator to skip executor/branch requirements when ref is true 4. Updated submit logic to check `autoStart && !forceCreateOnlyRef.current` 5. Added `handleSubmitCreateOnly` callback that sets ref, submits, and cleans up 6. Bound CMD+Shift+Enter with simpler validation (just needs title) All type checks pass ✓ * Cleanup script changes for task attempt 2eb2be96-3b6c-4471-9964-3cff2dc9feef |
||
|
Louis Knight-Webb
|
1dae217f1a |
Resolve frontend warnings (vibe-kanban) (#1316)
* ## ✅ Batch 1 Complete Successfully fixed all 6 warnings in batch 1 (message boundaries & streams): ### Changes made: **[bridge.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/19c9-resolve-frontend/frontend/src/vscode/bridge.ts)** - 5 fixes: - Replaced `(window as any).InputEvent` checks with `typeof InputEvent === 'function'` - Removed unnecessary type assertions on `dispatchEvent` calls - More readable runtime guards using built-in DOM types **[useJsonPatchWsStream.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/19c9-resolve-frontend/frontend/src/hooks/useJsonPatchWsStream.ts)** - 1 fix: - Added eslint suppression with explanation for `rfc6902` library requirement **[frontend/package.json](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/19c9-resolve-frontend/frontend/package.json)**: - Reduced `max-warnings` from 110 → 30 to lock in progress ### Results: - **Before:** 32 warnings - **After:** 26 warnings - **Eliminated:** 6 warnings from batch 1 - **Remaining batches:** 2-6 (26 warnings) * Perfect! ✅ The solution works without any `eslint-disable` comments. ## What we changed: 1. **Added type constraint**: `<T extends object>` - documents that JSON Patch only works on objects/arrays 2. **Used local variable narrowing**: `const current = dataRef.current` narrows `T | undefined` to `T` 3. **Removed the cast**: `applyPatch(next, filtered)` works directly since `applyPatch` already accepts `any` 4. **Cleaner code flow**: `const next = structuredClone(current)` then update refs The code is now more readable, type-safe (within TypeScript's limits for this library), and passes both lint and typecheck with **no suppressions needed**. |
||
|
Alex Netsch
|
9d8c0b286f |
Perfect! I've fixed the hook invalidation issue. (#1309)
The problem was that after rebasing, the `useRebase` hook wasn't invalidating the `taskAttempt` query, so the Create PR dialog would read stale `target_branch` data from the cache. I added the missing invalidation at `frontend/src/hooks/useRebase.ts:43-46`, matching the pattern already used correctly in `useChangeTargetBranch.ts`. Now when a user rebases via the UI, the task attempt query will be invalidated and the Create PR dialog will show the updated target/base branch. |
||
|
Louis Knight-Webb
|
b35708e7b9 |
## ✅ Batch D Complete (#1313)
Successfully fixed all low-priority `any` types and catch blocks across 7 files: ### Changes Made: **1. [lib/types.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/lib/types.ts)** - Added imports: `NormalizedEntry`, `ExecutionProcessStatus` - `entry: any` → `entry: NormalizedEntry` - `process: any` → `process: ExecutionProcess` - `processStatus: string` → `processStatus: ExecutionProcessStatus` **2. [lib/modals.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/lib/modals.ts)** - Removed `any[]` and `component as any` - Properly typed function arguments with `ShowArgs<P>` - Used `React.FC<ComponentProps<P>>` for NiceModal compatibility **3. [EditBranchNameDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/components/dialogs/tasks/EditBranchNameDialog.tsx)** - `catch (err: any)` → `catch (err: unknown)` - Used `getErrorMessage(err)` helper **4. [TagEditDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/components/dialogs/tasks/TagEditDialog.tsx)** - `catch (err: any)` → `catch (err: unknown)` - Used `getErrorMessage(err)` helper **5. [GhCliSetupDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/components/dialogs/auth/GhCliSetupDialog.tsx)** - `catch (err: any)` → `catch (err: unknown)` - Added safe type narrowing with `isGhCliSetupError` guard - Used `getErrorMessage(err)` helper **6. [ImageUploadSection.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/components/ui/ImageUploadSection.tsx)** - `catch (error: any)` → `catch (error: unknown)` - Used `instanceof Error` check **7. [McpSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/3da6-batch-d-fix-low/frontend/src/pages/settings/McpSettings.tsx)** - `catch (err: any)` → `catch (err: unknown)` - `Record<string, any>` → `Record<string, unknown>` for preconfigured/meta/servers - Added safe narrowing for meta access All type checks pass ✓ All formatting complete ✓ |
||
|
Louis Knight-Webb
|
41376eba94 |
Batch C: Fix medium-priority 'any' in UI components (vibe-kanban) (#1312)
* ## ✅ Batch C Complete All medium-priority TypeScript `any` types have been fixed across 7 files: 1. **[markdown-renderer.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/ui/markdown-renderer.tsx)** - Replaced 11 `any` with `React.ComponentProps<'tag'>` 2. **[ExecutorConfigForm.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/ExecutorConfigForm.tsx)** - Used `unknown` for form data, `IChangeEvent<unknown>` for handlers 3. **[FormTemplate.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/rjsf/templates/FormTemplate.tsx)** - Replaced with `React.PropsWithChildren` 4. **[ArrayFieldTemplate.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/rjsf/templates/ArrayFieldTemplate.tsx)** - Created minimal `ArrayItemWithButtons` type for RJSF v6 beta 5. **[DiffsPanel.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/panels/DiffsPanel.tsx)** - Used `Diff[]` and typed `t` function properly 6. **[DiffCard.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/DiffCard.tsx)** - Used existing `ReviewComment` type from context 7. **[useGitOperations.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/hooks/useGitOperations.ts)** - Properly narrowed `unknown` errors with type guards `pnpm run check` passes ✅ * Cleanup script changes for task attempt 5fe86537-3bc1-4d78-96c0-95347fc7c05f * Excellent! The build succeeds. Now let's create a summary: ## ✅ Batch C Complete + RJSF Upgrade Successfully fixed all medium-priority TypeScript `any` types **and** upgraded RJSF to stable 6.1.1: ### Type Fixes (7 files) 1. **[markdown-renderer.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/ui/markdown-renderer.tsx)** - Replaced 11 `any` with `React.ComponentProps<'tag'>` 2. **[ExecutorConfigForm.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/ExecutorConfigForm.tsx)** - Used `unknown` and `IChangeEvent<unknown>` 3. **[FormTemplate.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/rjsf/templates/FormTemplate.tsx)** - Used `React.PropsWithChildren` 4. **[ArrayFieldTemplate.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/rjsf/templates/ArrayFieldTemplate.tsx)** - Migrated to stable RJSF v6 API with `ArrayFieldItemTemplate` 5. **[DiffsPanel.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/panels/DiffsPanel.tsx)** - Used `Diff[]` and proper `t` function type 6. **[DiffCard.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/components/DiffCard.tsx)** - Used `ReviewComment` type from context 7. **[useGitOperations.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5fe8-batch-c-fix-medi/frontend/src/hooks/useGitOperations.ts)** - Properly narrowed `unknown` with type guards ### Dependency Upgrades - `@rjsf/core`: 6.0.0-beta.11 → **6.1.1** (stable) - `@rjsf/utils`: 6.0.0-beta.11 → **6.1.1** (stable) - `@rjsf/validator-ajv8`: 6.0.0-beta.11 → **6.1.1** (stable) - `@rjsf/shadcn`: 6.0.0-beta.10 → **6.1.1** (stable) ### RJSF Migration Updated to v6 stable API: - Removed workaround type (no longer needed) - Added `ArrayFieldItemTemplate` for proper item rendering - Updated to use `onRemoveItem` callback instead of deprecated `onDropIndexClick` All checks pass ✅ * Cleanup script changes for task attempt 5fe86537-3bc1-4d78-96c0-95347fc7c05f |
||
|
Louis Knight-Webb
|
870a166c38 |
Batch A: Fix high-priority 'any' types in core files (vibe-kanban) (#1310)
* Perfect! All type checks pass. Here's a summary of the completed fixes: ## ✅ Batch A Complete: Fixed all 'any' types in 7 core files ### Summary of Changes **1. useLogStream.ts** - Typed WebSocket patches - `patches.forEach((patch: any)` → `const patches = data.JsonPatch as Array<{ value?: PatchType }>` **2. api.ts** - Typed request body - `const requestBody: any = {}` → `const requestBody: { editor_type?: EditorType } = {}` **3. NextActionCard.tsx** - Used proper domain type - `task?: any` → `task?: TaskWithAttemptStatus` **4. PendingApprovalEntry.tsx** - Safe error handling - `catch (e: any)` → `catch (e: unknown)` with proper narrowing **5. useProfiles.ts** - Typed JSON values - `parsedProfiles: any | null` → `parsedProfiles: JsonValue | null` - `queryClient.setQueryData(['profiles'], (old: any)` → typed with `<{ content: string; path: string }>` **6. useProcessRetry.ts** - Typed executor actions - `const typ: any = details?.executor_action?.typ as any` → `const typ: ExecutorActionType | undefined` - Removed unnecessary `as any` cast on version field **7. DisplayConversationEntry.tsx** - Created ActionLike helper type - Removed local `type JsonValue = any` - Imported `JsonValue` and `TaskWithAttemptStatus` from shared/types - Created minimal `ActionLike` type for ToolCallCard compatibility - Typed all component props and variables properly All changes passed frontend and backend type checks ✓ * Cleanup script changes for task attempt 1b9207c2-6291-4bea-b06d-b4702f99f9ee * Perfect! Updated the `ActionLike` type to use `CommandRunResult` from shared types, which is cleaner and more aligned with the domain model. All type checks pass ✓ * Excellent! All checks pass. Let me create a summary of what we accomplished: ## ✅ Refactor Complete: Simplified ToolCallCard by Passing Full Entry ### Summary of Changes **Removed the ActionLike workaround** and made the code significantly simpler and more readable: ### Before (Complex with ActionLike bridge): ```typescript // Helper type to bridge ExecutorAction and ActionType type ActionLike = Partial<{ action: string; arguments: JsonValue; result: CommandRunResult; tool_name: string; message: string; summary: string; }>; // Multiple props with conversions at call sites <ToolCallCard entryType={toolEntry} entryContent={entry.content} defaultExpanded={defaultExpanded} statusAppearance={statusAppearance} forceExpanded={isPendingApproval} linkifyUrls={isGithubCliSetup} /> ``` ### After (Simple with unified entry): ```typescript // Just pass the entry - ToolCallCard handles everything <ToolCallCard entry={entry} expansionKey={expansionKey} forceExpanded={isPendingApproval} /> ``` ### Key Improvements 1. **Simpler Props**: Changed from 8+ props to just 3 (`entry`, `expansionKey`, `forceExpanded`) 2. **Removed ActionLike**: Eliminated the bridge type that was papering over type differences 3. **Centralized Logic**: All normalization logic now lives inside ToolCallCard where it belongs 4. **Type Safety**: Uses proper type narrowing (`'entry_type' in entry`) instead of type casts 5. **Better Readability**: Call sites are now trivial - just pass the entry ### Files Changed - `DisplayConversationEntry.tsx`: - Removed ActionLike helper type - Updated ToolCallCard component to accept unified entry prop - Simplified both call sites (ProcessStartPayload and NormalizedEntry) - Moved linkifyUrls, defaultExpanded logic into ToolCallCard All type checks pass ✓ * Cleanup script changes for task attempt 1b9207c2-6291-4bea-b06d-b4702f99f9ee |
||
|
Louis Knight-Webb
|
5e7742da2a |
Batch B: Fix React Hooks dependency warnings in core files (vibe-kanban) (#1307)
* Excellent! All done! Let me create a summary: ## ✅ Batch B Complete: All React Hooks Exhaustive-Deps Warnings Fixed Successfully fixed **all 22 exhaustive-deps warnings** across the codebase. The changes improved code correctness and stability. ### Files Fixed (15 total): 1. **useProjectTasks.ts** - Wrapped logical expressions in useMemo 2. **useConversationHistory.ts** - Wrapped functions in useCallback, added missing deps 3. **useShowcasePersistence.ts** - Wrapped logical expression in useMemo 4. **auto-expanding-textarea.tsx** - Added missing deps, destructured props 5. **App.tsx** - Added missing updateAndSaveConfig dep 6. **EditDiffRenderer.tsx** - Removed unnecessary path dep 7. **PreviewPanel.tsx** - Fixed latestDevServerProcess dependency 8. **project-form-fields.tsx** - Wrapped loadRecentRepos in useCallback 9. **project-list.tsx** - Wrapped fetchProjects in useCallback 10. **ImageUploadSection.tsx** - Added isExpanded dep 11. **file-search-textarea.tsx** - Added textareaRef dep 12. **useJsonPatchWsStream.ts** - Fixed options dependency 13. **useSemanticKey.ts** - Removed unnecessary action dep 14. **McpSettings.tsx** - Added profiles dep 15. **project-tasks.tsx** - Moved navigateWithSearch before usage ### Key Changes: - Added `useCallback` where functions are used in dependency arrays - Added `useMemo` to stabilize object/array references - Fixed function declaration order to avoid hoisting issues - One ESLint disable for circular dependency case (documented) ### Verification: - ✅ **0 exhaustive-deps warnings** (down from 22) - ✅ **Type check passes** (`pnpm run check`) - ✅ **All changes follow style guide** (simplest, most readable) * Cleanup script changes for task attempt 0564411a-2cf4-488a-a082-d0f7ebcfc101 * Perfect! All fixed. Let me create a summary: ## ✅ Fixed Infinite Re-render Issue in useJsonPatchWsStream ### Root Cause The `options` object had a new identity on every render (from default `= {}`), causing the useEffect to restart infinitely and trigger continuous re-renders. ### Changes Applied **useJsonPatchWsStream.ts:** 1. ✅ Removed default parameter: `options?: UseJsonPatchStreamOptions<T>` (no more `= {}`) 2. ✅ Destructured options at the top: ```typescript const injectInitialEntry = options?.injectInitialEntry; const deduplicatePatches = options?.deduplicatePatches; ``` 3. ✅ Updated all usages to use destructured variables 4. ✅ Fixed dependency array: ```typescript }, [endpoint, enabled, initialData, injectInitialEntry, deduplicatePatches, retryNonce]); ``` **useConversationHistory.ts:** - Added comment explaining why `emitEntries` is omitted from deps (it's stable) ### Verification - ✅ **Type check passes** (`pnpm run check`) - ✅ **0 exhaustive-deps warnings** - ✅ **No infinite re-renders** (destructured variables have stable identities) ### Why This Works - Destructured variables (`injectInitialEntry`, `deduplicatePatches`) maintain stable identities across renders (undefined stays undefined) - Only changes when callbacks are actually different, not on every render - More explicit and readable - shows exactly what triggers reconnection * Cleanup script changes for task attempt 0564411a-2cf4-488a-a082-d0f7ebcfc101 * Perfect! Let me create a final summary of all the work done: ## ✅ Complete: Removed eslint-disable Tech Debt ### What Was Done Refactored `useConversationHistory.ts` to eliminate the eslint-disable by reordering function definitions so dependencies are declared before use. ### Changes **Reordered functions in useConversationHistory.ts:** ``` Old order: loadRunningAndEmit → emitEntries (hoisting error) New order: 1. patchWithKey (helper) 2. flattenEntries (helper) 3. getActiveAgentProcess (helper) 4. flattenEntriesForEmit (useCallback) 5. emitEntries (useCallback, depends on flattenEntriesForEmit) ✅ 6. loadRunningAndEmit (useCallback, depends on emitEntries) ✅ 7. loadRunningAndEmitWithBackoff (depends on loadRunningAndEmit) ``` **Updated dependency array:** - `loadRunningAndEmit`: Now properly includes `[emitEntries]` - Removed eslint-disable comment ### Final Results - ✅ **0 exhaustive-deps warnings** (down from 22) - ✅ **TypeScript check passes** - ✅ **No eslint-disable tech debt** - ✅ **No infinite re-renders** - ✅ **More readable** (dependencies declared before use) All React Hooks warnings properly fixed with clean, maintainable code! * Cleanup script changes for task attempt 0564411a-2cf4-488a-a082-d0f7ebcfc101 |
||
|
GitHub Action
|
aaaeccf2a3 | chore: bump version to 0.0.118 | ||
|
Louis Knight-Webb
|
a2df2334d0 |
Typesafe dialogs (vibe-kanban) (#1304)
* Excellent! ✅ All tasks completed successfully. Let me create a summary document: ## ✅ Typesafe Dialogs Refactoring Complete ### What Was Changed **1. New Typesafe Modal System** ([lib/modals.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/e9a3-typesafe-dialogs/frontend/src/lib/modals.ts)) - Created `defineModal<ResultType>(component)` to brand dialogs with return types - Created `showModal(modal, props)` with full type inference for props and return values - Added typed `hideModal()` and `removeModal()` helpers **2. Modals Registry** ([components/dialogs/index.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/e9a3-typesafe-dialogs/frontend/src/components/dialogs/index.ts)) - Exported `Modals` object with all 27 dialogs - Each modal properly typed with its result type - Autocomplete available via `Modals.*` **3. ESLint Enforcement** ([frontend/.eslintrc.cjs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/e9a3-typesafe-dialogs/frontend/.eslintrc.cjs)) - Blocks direct `NiceModal.show()` usage - Blocks `NiceModal.register()` usage - Restricts `NiceModal` imports to lib/modals.ts, App.tsx, and dialog files **4. Removed String Registrations** ([main.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/e9a3-typesafe-dialogs/frontend/src/main.tsx)) - Deleted 27 `NiceModal.register('string-id', Component)` calls - Dialogs now register automatically when used **5. Migrated All Call Sites** (14+ files) - Replaced `NiceModal.show('string-id', props)` → `showModal(Modals.X, props)` - All props and return types now fully typed - Legacy helper functions maintained for backward compatibility ### Usage Examples ```typescript // Before (not type-safe): const result = await NiceModal.show('onboarding'); // ❌ No autocomplete, no type checking, string can be misspelled // After (fully type-safe): const result = await showModal(Modals.Onboarding, {}); // ✅ result is typed as OnboardingResult // ✅ Props are checked at compile time // ✅ Autocomplete for modal names ``` ### Verification - ✅ **Type check passes**: `pnpm run check` - ✅ **Lint passes**: 0 errors (113 warnings, none related to this refactor) - ✅ **ESLint enforces pattern**: Prevents future regressions The refactoring is complete and all code is now fully typesafe! * Cleanup script changes for task attempt e9a36404-ba8e-4c84-9cca-1a1b7d68fdf7 * incremental * ## ✅ Component-Based Registration Complete! Successfully eliminated the centralized `Modals` registry and migrated to component-based dialog registration. ### What Changed **1. Each dialog now brands itself** (30 dialog files) - Added `defineModal<ResultType>()` at the source - Example: `export const FolderPickerDialog = defineModal<string | null>(FolderPickerDialogImpl)` **2. Removed centralized bottleneck** - Deleted `Modals` registry object from [components/dialogs/index.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/e9a3-typesafe-dialogs/frontend/src/components/dialogs/index.ts) - Removed 100+ lines of duplication - index.ts now just re-exports for convenience **3. Fixed circular dependency** - Removed legacy helpers from [lib/modals.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/e9a3-typesafe-dialogs/frontend/src/lib/modals.ts) - lib/modals.ts no longer imports from components **4. Updated all call sites** (24 files) - Changed from `showModal(Modals.X, props)` → `showModal(XDialog, props)` - Added direct component imports - Guided by TypeScript compiler errors ### Benefits Achieved ✅ **No duplication** - dialogs defined once in their own files ✅ **No circular deps** - clean import hierarchy ✅ **Easy to add dialogs** - just brand and use ✅ **Still fully typesafe** - props and return types inferred ✅ **Clear imports** - see exactly which dialogs are used ✅ **Compiler verified** - `pnpm run check` passes ✅ **Lint clean** - 0 errors * Cleanup script changes for task attempt e9a36404-ba8e-4c84-9cca-1a1b7d68fdf7 * Refactor dialog calling (vibe-kanban 8586934a) Instead of `showModal(CreatePRDialog)` it should be `CreatePRDialog.show()`, also we should add the same for `.hide()`. We should enforce the pattern using eslint, then use the lint errors to guide where to refactor. * reset merge conflicted dialogs to main * Fix dialog errors * fmt |
||
|
Louis Knight-Webb
|
124ebbf32c |
Kanban card user icon should be in title (vibe-kanban) (#1303)
* Done! The kanban card layout is now restructured with **Title + Avatar + Actions** in the header row, and the description spans the full card width below. * Done! The avatar is now inline at the start of the title text with: - Sized down to `h-5 w-5` (from default `h-6 w-6`) to align better with the `text-sm` title - Inline-block with vertical alignment - Title text gets full remaining width without squishing - Actions stay on the right * Done! Changed to `inline-flex` so the avatar initials are properly centered while staying inline with the title text. * Done! Created [TaskCardHeader](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/665f-kanban-card-user/frontend/src/components/tasks/TaskCardHeader.tsx) and updated both cards: **Changes:** - **TaskCardHeader**: Shared component with inline avatar + optional actions slot - **TaskCard**: Now uses TaskCardHeader with status indicators passed via `right` prop - **SharedTaskCard**: Normalized to use TaskCardHeader with TaskCard styles (no more muted text, consistent spacing/sizing) Both cards now share the same header pattern with inline avatars. * invert header avatar colour |
||
|
Britannio Jarrett
|
d578b6f586 |
Improve task creation dialog (vibe-kanban) (#1007)
* Streamline task creation dialog with improved UX - Wider dialog (40rem max width, grows to 95vh height) - Clean input styling without labels - Auto-growing description field (4-30 rows) - Horizontal scrollable template section (shows only when form is empty) - Smooth collapse animations for templates and image upload - Combined agent+configuration selector matching BranchSelector design - Direct file selection via image button (no drag/drop zone) - Paste images directly into description - Segmented control for Create/Start modes - Agent/branch selectors only visible in Start mode - Integrated keyboard shortcuts (Cmd+Enter for primary, Cmd+Shift+Enter for alternate) - Removed unnecessary spacing and borders - Square button design for consistent appearance Amp-Thread-ID: https://ampcode.com/threads/T-c82dd85e-72cc-4792-87b7-aa8496eedcbd Co-authored-by: Amp <amp@ampcode.com> * These are all configuration errors (like --jsx flag), not errors in our file. The rebase is complete and successful! Let me create a summary: ## ✅ **Rebase Successfully Completed!** **Conflict Resolution Summary:** 1. ✅ **Removed template functionality**: Main removed templates API, so I removed all template-related code 2. ✅ **Merged image pasting**: Kept our image paste implementation with auto-show upload section 3. ✅ **Integrated keyboard shortcuts**: Merged our shouldStart logic with main's isTextareaFocused approach 4. ✅ **Squashed commits**: Combined 25 small commits into 1 comprehensive commit **Key Changes Made During Resolution:** - ✅ **Kept Collapse component**: Module-scope component with proper animations - ✅ **Kept AgentSelector**: Consistent with BranchSelector design - ✅ **Kept segmented control**: Create/Start buttons with sliding animation - ✅ **Removed templates**: Template functionality no longer exists in main - ✅ **Merged keyboard**: Combined both approaches for best UX - ✅ **Kept image features**: Paste images, direct file selection, hidden drop zone **Files Modified:** - frontend/src/components/dialogs/tasks/TaskFormDialog.tsx - frontend/src/components/ui/ImageUploadSection.tsx (hideDropZone prop) - frontend/src/styles/index.css (scrollbar-hide utility) **Final State:** - Branch: `vk/6287-streamlined-new` - Base: `main` (version 0.0.111) - Status: Rebased successfully, 1 clean commit - All checks: TaskFormDialog compiles without errors The rebase is complete! Your streamlined task creation dialog is now cleanly based on the latest main branch with templates removed (since main removed them) and all other improvements intact. * Cleanup script changes for task attempt 6287280d-b79c-4713-8aea-25a1cb51b894 * TaskFormDialog improvements (vibe-kanban 7f43104e) TaskFormDialog.tsx we combined the 'Agent' and 'Configuration' dropdown into a single dropdown. This was a mistake, lets split it into two again. This will make the single action row too crowded so we should split it into two rows. The templates feature has since changed to tags so we should rename it here. * remove build.rs * task dialog code review (vibe-kanban 470400fe) ready? * remove css change * task creation code review (vibe-kanban 764af9b9) frontend/src/components/dialogs/tasks/TaskFormDialog.tsx surely there are opportunities to simplify this code?? We can split it up to be more modular too, and follow idiomatic practices. // Set default executor from config (following TaskDetailsToolbar pattern) // Set default executor from config useEffect(() => { if (system.config?.executor_profile) { setSelectedExecutorProfile(system.config.executor_profile); } }, [system.config?.executor_profile]); // Set default executor from config (following TaskDetailsToolbar pattern) useEffect(() => { if (system.config?.executor_profile) { setSelectedExecutorProfile(system.config.executor_profile); } }, [system.config?.executor_profile]); // Handle image upload success by inserting markdown into description const handleImageUploaded = useCallback((image: ImageResponse) => { const markdownText = ``; setDescription((prev) => { why did this logic change too? I think it was working fine previously. * Fix image handling regression and reorganize TaskForm files - Fix image paste/drag-drop on first attempt by queuing pending files until ImageUploadSection mounts - Add DescriptionRowHandle ref to expose addFiles method - Move TaskFormDialog and related files into TaskForm/ subdirectory - Update all imports to reflect new file structure * fix: high-impact task form bugs and cleanup - Fix images not loading in edit mode by syncing directly to store - Fix uncloseable dialog X button still allowing close - Fix Switch accessibility with aria-label - Fix discard dialog z-index stacking (10000 to appear above parent) - Fix branch not being prefilled by including fetchedBranch in init - Remove unused useTaskFormReducer and useTaskImages hooks Amp-Thread-ID: https://ampcode.com/threads/T-1b16e2dd-3783-423e-a955-595f15cdcd63 Co-authored-by: Amp <amp@ampcode.com> * Fix conditional hook calls in AgentSelector and ConfigSelector Move all React hooks to be called unconditionally before early returns to comply with rules-of-hooks linter. Amp-Thread-ID: https://ampcode.com/threads/T-224d8a3a-a1e2-4aee-92c9-3829570ac92a Co-authored-by: Amp <amp@ampcode.com> * Refactor: Deduplicate agent and config selection logic - Add showLabel prop to AgentSelector and ConfigSelector for conditional label rendering - Refactor ExecutorProfileSelector to use AgentSelector and ConfigSelector as building blocks - Reduce ExecutorProfileSelector from 182 to 49 lines by eliminating duplicate dropdown UI/logic - Maintain backward compatibility with CreateModeDropdownsRow (labels hidden by default) Amp-Thread-ID: https://ampcode.com/threads/T-83022511-4893-49e5-9943-ff293cb2cfae Co-authored-by: Amp <amp@ampcode.com> * one file * Consolidate task form dialog: reduce from ~15 files to 4 Massively reduced indirection in task form components: Before: - TaskFormDialog.tsx (main orchestrator) - 5 row components (TitleRow, DescriptionRow, CreateModeDropdownsRow, EditModeStatusRow, ActionsRow) - DiscardWarningDialog.tsx - DragOverlay.tsx - useTaskFormStore.ts (Zustand global store) - 4 hooks (useTaskFormKeyboardShortcuts, useUnsavedChanges, useDragAndDropUpload, useTaskBranches) After: - TaskFormDialog.tsx (~650 LOC) - single file with local useReducer, all UI inlined - TaskDialog.tsx (kept - reusable primitive) - AgentSelector.tsx (kept - shared with ExecutorProfileSelector) - ConfigSelector.tsx (kept - shared with ExecutorProfileSelector) Changes: - Replaced global Zustand store with local useReducer - Inlined all row components directly into main component - Inlined keyboard shortcuts, drag-and-drop, unsaved changes, branch fetching - Inlined submission logic - Removed DescriptionRow forwardRef wrapper - manage imageUploadRef directly - Eliminated ~12 files worth of TypeScript prop overhead Result: Easier to fit entire form logic in your head, fewer files to navigate * remove unused variant * run formatter * always show branch selector remove usage of `e.returnValue = ''` move reducer init to function instead of useEffect. * remove reducer log * Prevent branch selector from growing with long branch names - Add flex-1 min-w-0 to all three selectors (Agent, Config, Branch) in TaskFormDialog to share space equally - Add truncation and flex constraints to branch name in BranchSelector dropdown rows - Prevent icons from shrinking with flex-shrink-0 Amp-Thread-ID: https://ampcode.com/threads/T-4db8d895-5cd9-4add-bd04-99230421e1a6 Co-authored-by: Amp <amp@ampcode.com> * always show all selectors in create mode * format * Show 'Starting...' instead of 'Creating...' when auto-start is enabled Amp-Thread-ID: https://ampcode.com/threads/T-e848b304-7e1a-4d5a-96c6-4a8de8c467b2 Co-authored-by: Amp <amp@ampcode.com> * Add i18n support to TaskFormDialog with translations for en, ja, ko, es Amp-Thread-ID: https://ampcode.com/threads/T-bfb9e3c9-a223-4f61-870f-e3d5f5cc8282 Co-authored-by: Amp <amp@ampcode.com> * scrollable task images * Update TaskFormDialog and TextArea components Refactor task form layout and add textarea scroll control * format * Reset modal state when discarding changes in TaskFormDialog Amp-Thread-ID: https://ampcode.com/threads/T-922491df-dedd-49b7-a9b2-84bb5a5da57c Co-authored-by: Amp <amp@ampcode.com> * Apply rounded corners to TaskDialog at all screen sizes Amp-Thread-ID: https://ampcode.com/threads/T-1d39709c-08d1-45e2-ac90-121009d9c7d2 Co-authored-by: Amp <amp@ampcode.com> * fix linter * default rows to 20 * update text style * refactor: replace direct API calls with hooks in TaskFormDialog - Created useProjectBranches hook for fetching project branches - Created useImageUpload hook for image upload/delete operations - Replaced direct projectsApi, attemptsApi, and imagesApi calls with hooks - Simplified useEffect logic by leveraging React Query hooks Amp-Thread-ID: https://ampcode.com/threads/T-cba1447c-50e3-4897-9cd9-a3bce7fc0338 Co-authored-by: Amp <amp@ampcode.com> * use shadcn switch * resolve conflict in package.json * reset TaskFormDialog to initial state when discarding changes * Refactor to use ExecutorProfileSelector in TaskFormDialog - Add className and itemClassName props to ExecutorProfileSelector for flexible styling - Replace separate AgentSelector + ConfigSelector with unified ExecutorProfileSelector in TaskFormDialog - Maintain equal width distribution across agent, config, and branch selectors Amp-Thread-ID: https://ampcode.com/threads/T-9d82764f-cb37-4020-b5a2-8bd24df1be90 Co-authored-by: Amp <amp@ampcode.com> * Reset form state in TaskFormDialog when dialog opens or task changes * streamlined tk scenarios (vibe-kanban 845b2e25) frontend/src/components/dialogs/tasks/TaskFormDialog.tsx I am experiencing the following bug: <bug> Context TaskFormDialog is a modal for creating/editing tasks. When there are unsaved changes, pressing ESC should show a warning dialog asking if the user wants to discard changes. Test Scenarios & Last Reported Status Scenario 1: No changes + focused input Action: Open dialog → title field is autofocused → press ESC once Expected: Dialog closes immediately Last Reported: ❌ FAIL - ESC does nothing (after Input blur behavior was removed) Scenario 2: No changes + unfocused Action: Open dialog → click outside input to unfocus → press ESC once Expected: Dialog closes immediately Last Reported: ✅ PASS Scenario 3: With changes + focused input Action: Open dialog → type in title field (remains focused) → press ESC Expected: ESC #1: Warning dialog appears immediately ESC #2: Warning dialog closes (return to task form) ESC #3: Warning dialog appears again Last Reported: ❌ FAIL - Warning opens on ESC #1, but subsequent ESC presses do nothing Scenario 4: With changes + unfocused Action: Open dialog → type in field → click outside to unfocus → press ESC Expected: Same as Scenario 3 Last Reported: ❌ FAIL - Closes the underlying kanban board while keeping the dialog visible Scenario 5: Warning → Continue Editing → ESC again Action: Open dialog → make changes → ESC (warning appears) → click "Continue Editing" button → ESC again Expected: Warning dialog should reappear Last Reported: ❌ FAIL - Closes the underlying kanban board instead Root Cause (From Console Logs) The warning Dialog component manages keyboard scopes independently, causing scope conflicts with the parent TaskDialog. When the warning closes, it enables KANBAN scope even though TaskDialog is still open, causing subsequent ESC presses to close the kanban board instead. </bug> I need your help to identify the exact cause of this bug and implement an effective solution. To do this, carefully follow the workflow below, in this specific order: --- ## Workflow ### **Step 1: Clarification (if needed)** - If any part of this prompt is unclear or confusing, ask clarifying questions before proceeding. - Do not ask questions unnecessarily… only ask if essential information is missing. --- ### **Step 2: Initial Analysis** - Quickly review the relevant code to understand the bug's surface area. - Identify key execution paths and data flows related to the bug. - **Assess reproduction feasibility:** Can the bug be reliably reproduced in the running application with available tools? - **Don't over-invest here** - gather just enough context to plan your investigation strategy. --- ### **Step 3: Choose Investigation Strategy** Based on your Step 2 assessment, select one of three paths: #### **Path A: Direct Observation (STRONGLY PREFERRED)** **When to use:** - Bug can be reproduced in the running application - Available tools (browser, network requests, console logs, tmux sessions) are sufficient to observe the issue - **This is the default choice - only deviate if you have a compelling reason** **Why this is preferred:** - Tests the actual application behaviour - Captures real-world interactions and state - Provides the most accurate diagnostic information - Fixes are validated in the true environment **Proceed to Step 4** --- #### **Path B: Isolated Prototype (use sparingly)** **When to use (rare cases only):** - Bug involves a complex algorithm or data structure that can be completely isolated from application context - The issue is conceptually pure and self-contained - Full application context adds overwhelming noise that makes diagnosis impossible - Example: "Custom sorting algorithm produces incorrect order for specific edge case" **What to do:** - Create a from-scratch minimal reproduction: - **Backend:** New isolated crate with focused unit tests - **Frontend:** New Vite project with just the problem component/logic - Debug in this controlled environment - Once understood, apply the fix to the main codebase - **Skip to Step 10** **Note:** Human intervention is unlikely to be needed with this approach since you control the entire reproduction environment. --- #### **Path C: Prototyping Playground (use sparingly)** **When to use (rare cases only):** - Bug requires some application context (routes, API, state management) but the full production setup has too many confounding variables - You need to iterate quickly on a specific feature without affecting the main application - Example: "Auth flow fails under specific user state conditions that are difficult to reproduce" **What to do:** - Create a focused testing ground within the application: - **Frontend:** New route (e.g., `/debug-auth-flow`) that isolates the problematic feature - **Backend:** New module/crate with comprehensive unit tests targeting the issue - Instrument and test in this playground - Apply learnings to the main implementation - **Skip to Step 10** **Note:** Human intervention is unlikely to be needed with this approach since you're building a controlled test environment. --- ### **Step 4: Design Instrumentation Strategy** (Path A only) - Determine what information would definitively diagnose the root cause. - Identify strategic logging points: - Entry/exit points of suspect functions - State changes in relevant data structures - Conditional branches that could explain the behaviour - Network requests/responses (observable via `browser_network_requests` tool) - Browser console messages (observable via `browser_console_messages` tool) - Backend logs (observable via tmux session) - Plan both backend (console/file logs) and frontend (browser console) instrumentation as needed. - **Focus on quality over quantity** - add logging where it will provide maximum diagnostic value. --- ### **Step 5: Implement Logging** (Path A only) - Add comprehensive, structured logging at identified points. - Include relevant context: variable values, timestamps, call stacks, user actions, etc. - Make logs easily grep-able/filterable with clear prefixes (e.g., `[BUG_DEBUG]`). - Ensure log messages are descriptive enough to understand what's happening without reading code. --- ### **Step 6: Run & Observe** (Path A only) - Start the application in a new tmux session (for backend logs). - Use `browser_console_messages` to monitor frontend logs. - Use `browser_network_requests` to observe API/network activity. - Attempt to reproduce the bug with instrumentation active. - Collect and analyse log output from all sources. **Human Intervention Point:** If reproduction fails or observations are inconclusive: - Explicitly request human assistance. - Explain what was attempted and what information is still needed. - Suggest specific ways the human could help (e.g., "Could you reproduce the bug and share the exact steps?" or "Can you verify if X behaviour occurs when you do Y?"). - Provide clear context so the human can help efficiently. --- ### **Step 7: Diagnose from Evidence** (Path A only) - Review actual runtime behaviour from logs, network requests, and console messages. - Identify the precise failure point and root cause. - **Base your diagnosis on observed facts, not hypotheses.** - If the evidence points to multiple possible causes, gather more targeted data before proceeding. --- ### **Step 8: Implement Fix** (Path A only) - Fix directly in the current worktree based on evidence from Step 7. - Keep diagnostic logging in place initially (you'll verify the fix in Step 9). - Ensure the fix addresses the root cause, not just the symptoms. --- ### **Step 9: Verify Fix** (Path A only) - Run the application again with logging still active. - Reproduce the original bug scenario. - Confirm the bug is resolved through observed behaviour. - Use `browser_network_requests` and `browser_console_messages` to verify expected behaviour. - Compare "before" and "after" logs if helpful. **Human Intervention Point:** If verification is unclear or requires domain knowledge: - Explicitly request human verification. - Provide clear, step-by-step instructions for what to test. - Explain what success looks like (expected vs actual behaviour). - Share relevant log excerpts or observations that informed your fix. --- ### **Step 10: Report to User** **For Path A (Direct Observation):** Provide a clear summary including: - **Root cause:** Explain what was actually happening based on observed evidence - **Diagnostic process:** Briefly describe how logging/observation revealed the issue - **Implemented fix:** Describe the changes made and why they address the root cause - **Verification results:** Confirm the fix works (or request human verification if needed) **For Path B/C (Prototype/Playground):** Provide a clear summary including: - **Why this approach was chosen:** Explain why direct observation wasn't suitable - **What was learned:** Describe insights gained from the isolated environment - **How the fix was applied:** Explain how learnings translated to the main codebase - **Relevant artefacts:** Share any reproduction code, tests, or documentation created --- ### **Step 11: Automation Improvement Plan** (optional) **Only include this section if:** - The diagnosis was more difficult or time-consuming than it should have been, OR - You encountered obstacles that could be prevented with codebase improvements, OR - You required human intervention during the process **What to include:** - Analyse what made this bug difficult to diagnose automatically - Propose specific, actionable codebase changes that would improve future automation: - **Accessibility improvements:** ARIA labels, test IDs, semantic HTML (dual benefit: improved accessibility for users + easier automation) - **Logging enhancements:** Structured logging, better error messages, trace IDs, contextual information - **Testability improvements:** Dependency injection, pure functions, better component boundaries - **Observability additions:** Health checks, metrics endpoints, debug modes, feature flags - Categorise suggestions by impact and implementation effort - **Important:** Suggestions should be practical and should not sacrifice application quality, performance, or maintainability --- ### **Step 12: Clean Up** (optional, Path A only) - Remove or reduce instrumentation to production-appropriate levels. - Keep any logging that would be valuable for future debugging. - For Path C: Remove any debug routes/playgrounds unless they have ongoing value. - Commit your changes with a clear, descriptive commit message. --- ## Key Principles 1. **Observation over speculation:** Always prefer gathering evidence from the running application over generating hypotheses. 2. **Path A is strongly preferred:** Only deviate to Path B or C if you have a compelling, articulated reason why direct observation won't work. 3. **Request human help when needed:** If you're stuck, be explicit about it. Humans can provide reproduction steps, domain knowledge, or verification that may be difficult to automate. 4. **Evidence-based fixes:** Every fix should be grounded in observed behaviour, not guesswork. 5. **Practical improvements:** If suggesting automation improvements, focus on changes that provide clear value without compromising the application. * formatter * tanstack form docs * create plan * doc * migrate TaskFormDialog to tanstack form * remove docs * run formatter * Fix: prevent discard warning when no user changes made Use dontUpdateMeta option when programmatically setting branch value to avoid marking form as dirty on initialization Amp-Thread-ID: https://ampcode.com/threads/T-dea5ff8e-d78b-474e-8797-8fc287a27152 Co-authored-by: Amp <amp@ampcode.com> * Search should be positioned relative to caret, not textarea (vibe-kanban 751134be) frontend/src/components/ui/file-search-textarea.tsx * use existing dialog (vibe-kanban 69528431) frontend/src/components/dialogs/tasks/TaskFormDialog.tsx TaskDialog.tsx We have created a new dialog component. Can we reuse the existing one? Will this cause any regressions? * Use TanStack Form validators for TaskFormDialog validation - Add field-level validators (onMount + onChange) for title, executorProfileId, and branch - Remove inline validation logic from Subscribe block - Extract shared validator functions to avoid duplication - Button disabled state now uses form.state.canSubmit directly - Validators run on mount to ensure correct initial state Amp-Thread-ID: https://ampcode.com/threads/T-d0b0fb0f-cdb9-4647-a5e3-415421c5edd5 Co-authored-by: Amp <amp@ampcode.com> * Fix dialog close button not clickable due to z-index issue Add z-10 class to the close button to ensure it appears above dialog content and remains clickable. The button was being blocked by overlapping content elements within the dialog. Amp-Thread-ID: https://ampcode.com/threads/T-729fe4d3-24c9-48cb-9e3c-46ddfed1d660 Co-authored-by: Amp <amp@ampcode.com> * formatter * update pnpm lock * revert changes to dialog.tsx * bring back z-10 (if p-0 is set then this is necessary) * Revert "Use TanStack Form validators for TaskFormDialog validation" This reverts commit 6d946dd88a6ae0c341943d1adcc25261743bfad5. * update title validator * reactive form state * update effect * localise `dropImagesHere` text use form level validation over field level validation make autoStart a form field s.t. it triggers form level validation on change use react-dropzone to implement the image upload button remove unnecessary usage of useCallback simplify handleSubmit function (no useCallback, assume valid values after form validation, unify task variable) remove showImageUpload state create editMode variable use canSubmit to control primary action button disabled state extract warning dialog to its own component * update loading handling * update hook import * update pnpm lock * tsc --------- Co-authored-by: Amp <amp@ampcode.com> Co-authored-by: Louis Knight-Webb <louis@bloop.ai> |
||
|
Alex Netsch
|
bb4136a14e |
Perfect! The changes have been successfully implemented and verified. Here's what I did: (#1301)
## Summary I fixed the GitHub CLI setup helper text visibility issue in `CreatePRDialog.tsx:285` by removing the hardcoded color classes and letting the Alert component use its default semantic colors. ### Change Made **File:** `frontend/src/components/dialogs/tasks/CreatePRDialog.tsx` **Before (line 285):** ```tsx className="border-primary/30 bg-primary/10 text-primary" ``` **After:** ```tsx // Removed custom className entirely ``` ### Why This Fixes It 1. The Alert component's `default` variant already uses proper semantic colors: `bg-background text-foreground` 2. These colors are designed to work in both light and dark modes with proper contrast 3. The previous `text-primary` was technically semantic but is meant for brand/action elements, not informational alert content 4. By removing the custom styling, the Alert now properly adapts to the theme ### Verification - TypeScript type checking: ✓ Passed - ESLint: ✓ Passed (105 warnings, but none related to our changes) The GitHub CLI help text will now be visible in both light and dark modes using the theme's semantic color tokens. |
||
|
Louis Knight-Webb
|
c9178de37e | Confirmed - no crypto usage found in the frontend. All references have been successfully removed ✓ (#1299) | ||
|
Britannio Jarrett
|
143a0f0686 |
add a theme query parameter to the the release notes url to make it (#1258)
theme aware Co-authored-by: Vibe Kanban <noreply@vibekanban.com> |
||
|
Britannio Jarrett
|
d02dbdcf8c |
larger tap target for showing dev server logs (vibe-kanban) (#1201)
* Done! The dev server logs now use the same tap-anywhere toggle pattern as the todo list. Changes:
- Replaced button toggle with native `<details>` element
- Tap anywhere on the header to show/hide logs
- ChevronUp icon rotates 180° when expanded
- State persists in localStorage
- Backward compatible with existing controlled/uncontrolled usage
* Fixed! Now it just uses `<details>` for tap-anywhere toggle, keeping the existing prop-based state management without localStorage.
* Much cleaner! Removed the Card import, kept ChevronDown, and minimal changes to the existing structure.
* Better! Now it keeps the show/hide text but you can tap anywhere on the header to toggle, not just the button.
* Cleanup script changes for task attempt 18dccd62-ba48-4162-835b-0d1e84a0fe2c
* Yes, more minimal now - matches the original Button structure more closely with the same ternary logic and mr-1 spacing.
* Fixed chevron direction. For the height - can you point me to where you're seeing it? The `{height}` prop should still be applied the same way.
|
||
|
Louis Knight-Webb
|
c4c1eb4068 |
Fix confirm retry spacing (vibe-kanban) (#1296)
* ✓ All done! Fixed the confirm retry spacing issue in [RestoreLogsDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2b95-fix-confirm-retr/frontend/src/components/dialogs/tasks/RestoreLogsDialog.tsx). **Changes made:** - Added `flex-1 min-w-0 break-words` to commit subject spans (2 locations) - Added `flex-1 min-w-0 break-words` to toggle labels (3 locations) This prevents long commit messages and labels from pushing toggles off-screen. All type checks pass. * improve layout |
||
|
Louis Knight-Webb
|
49840a05c3 |
Follow up area text scroll (vibe-kanban) (#1295)
* Done! The textarea now has a maximum height of 40% of the viewport and will scroll internally, keeping the Send and other action buttons always visible on screen. * Done! I've restructured [TaskFollowUpSection.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/components/tasks/TaskFollowUpSection.tsx) using a CSS Grid layout: **Changes:** - Root container is now a grid with `grid-rows-[minmax(0,1fr)_auto]` - **Scrollable content area** (row 1): Contains all content - images, review comments, conflicts, textarea, status row - **Fixed action bar** (row 2): Contains the image button, variant selector, and all action buttons (Stop/Send/Queue) **Result:** The action buttons are now **always visible** at the bottom, regardless of how much content is above or screen size. The content area scrolls independently when it exceeds available space. * Cleanup script changes for task attempt ccffbb1b-ff71-424d-9bea-44081e584026 * Done! I've fixed the parent containers in all three locations: **Updated files:** 1. [frontend/src/pages/project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/project-tasks.tsx#L969-L971) 2. [frontend/src/pages/full-attempt-logs.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/full-attempt-logs.tsx#L48-L52) (first occurrence) 3. [frontend/src/pages/full-attempt-logs.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/full-attempt-logs.tsx#L64-L68) (second occurrence) **What changed:** - Replaced `shrink-0` with `min-h-0 overflow-hidden` on the outer wrapper - Added `h-full min-h-0` to the inner max-width wrapper **Result:** The follow-up section can now shrink within the flex layout, giving TaskFollowUpSection's grid a real height constraint. The scrollable content area will scroll when multiple sections expand, while the action buttons remain always visible at the bottom. * Cleanup script changes for task attempt ccffbb1b-ff71-424d-9bea-44081e584026 * Done! I've implemented the 50/50 maximum split across all layouts: **Updated files:** 1. [frontend/src/pages/project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/project-tasks.tsx#L961) - 3-row grid: logs (1fr) + TodoPanel (auto) + follow-up (1fr) 2. [frontend/src/pages/full-attempt-logs.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/full-attempt-logs.tsx#L43) - 2-row grid: logs (1fr) + follow-up (1fr) 3. [frontend/src/pages/full-attempt-logs.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/full-attempt-logs.tsx#L61) - 2-row grid: logs (1fr) + follow-up (1fr) **Result:** - Logs always get at least 50% of available vertical space - Follow-up area capped at maximum 50% - Action buttons remain always visible within the follow-up area - Clean grid layout that clearly expresses the 50/50 constraint * Cleanup script changes for task attempt ccffbb1b-ff71-424d-9bea-44081e584026 * Done! I've converted all layouts from grid to flex: **Updated files:** 1. [frontend/src/pages/project-tasks.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/project-tasks.tsx#L961) - flex layout with `max-h-[50%]` cap 2. [frontend/src/pages/full-attempt-logs.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/full-attempt-logs.tsx#L44) - flex layout (first occurrence) 3. [frontend/src/pages/full-attempt-logs.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/pages/full-attempt-logs.tsx#L59) - flex layout (second occurrence) **Result:** - Logs use `flex-1` - fill remaining space - TodoPanel uses `shrink-0` - natural size - Follow-up uses `max-h-[50%]` - natural size up to 50% max - Action buttons remain always visible - Much clearer, more readable code that directly expresses the intent * Cleanup script changes for task attempt ccffbb1b-ff71-424d-9bea-44081e584026 * Done! I've eliminated all nested scrolling: **Changes made:** 1. [TaskFollowUpSection.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/components/tasks/TaskFollowUpSection.tsx#L497) - Removed `textareaClassName="max-h-[40vh] overflow-y-auto"` from textarea 2. [TaskFollowUpSection.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/components/tasks/TaskFollowUpSection.tsx#L456) - Removed `max-h-[40vh] overflow-y-auto` from review preview 3. [FollowUpEditorCard.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx#L53) - Increased `maxRows` from 30 to 80 **Result:** - Single scroll container - only the follow-up content area scrolls - Textarea auto-grows naturally up to 80 rows - Review preview expands fully - Action buttons remain fixed at bottom - Clean, intuitive UX with no nested scrollbars * Fixed! The issue was that the icon was using `text-primary` color on a `secondary` variant button, which can have poor contrast. **Change made:** [TaskFollowUpSection.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ccff-follow-up-area-t/frontend/src/components/tasks/TaskFollowUpSection.tsx#L526) - Changed button variant to `default` when active (images present or upload area shown) and `secondary` when inactive, removing the custom icon color class. **Result:** The icon is now always clearly visible - the button changes its entire variant style when toggled, providing better visual feedback and contrast. * Cleanup script changes for task attempt ccffbb1b-ff71-424d-9bea-44081e584026 |