daonanchao/vibe-kanban
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
947 Commits 1 Branch 0 Tags
a4b67504df91a700c6624974ec96d7291c7fff0c
Commit Graph

467 Commits

Author SHA1 Message Date
Gabriel Gordon-Hall
a4b67504df improve spacing in markdown renderer (#1021) 2025-10-15 15:54:19 +01:00
Alex Netsch
aaaf8532a7 Add close button to preview warning banner (vibe-kanban) (#1013) 
* ## Summary

I've successfully fixed the issue where the red preview warning banner was blocking the preview even when a working output on a port was discovered.

### Root Cause
The issue was in `frontend/src/components/tasks/TaskDetails/PreviewTab.tsx:108-118`. The component had two separate "ready" states:
1. **`previewState.status === 'ready'`** - Set when a URL is detected in dev server logs (preview working)
2. **`isReady`** - Set when the web companion sends a 'ready' postMessage (optional, only for click-to-component)

The warning banner was showing whenever `!isReady` was true after 5 seconds, even if the preview was fully functional with a discovered URL.

### Solution
I added a check for `previewState.status !== 'ready'` to the warning condition at line 112. Now the warning banner only shows when:
- 5 seconds have elapsed
- No web companion ready message received
- **AND no URL was discovered** (preview actually broken)
- Dev server is running

### Result
The red warning banner will no longer appear when the preview is working correctly (URL discovered and iframe loaded), even if the web companion is not installed. It will only show when there's an actual problem with the preview not loading.

**File changed:** `frontend/src/components/tasks/TaskDetails/PreviewTab.tsx:112,123`

* ## Summary

I've successfully implemented a simple solution that shows two different types of warnings based on the actual state of the preview:

### Changes Made

**1. Modified `frontend/src/components/tasks/TaskDetails/PreviewTab.tsx`:**

- Added `X` icon import from lucide-react for the dismiss button
- Added new state: `showCompanionWarning` to track the companion info banner
- Updated the warning logic (lines 110-126) to differentiate between two scenarios:
  - **Critical Error (Red Alert)**: Shows when `previewState.status !== 'ready'` - dev server is running but no URL was discovered (actual preview problem)
  - **Companion Info (Blue Alert)**: Shows when `previewState.status === 'ready'` - preview is working but web companion is not detected
- Added dismissible blue info banner (lines 218-244) with:
  - Title: "Enable Click-to-Component"
  - Message about installing web companion
  - Link to installation guide
  - X button to dismiss (no localStorage, resets each time)
- Updated state management to clear both warnings appropriately

**2. Added translations to `frontend/src/i18n/locales/en/tasks.json`:**
- Added new `companionAlert` section with title, message, and link text

### Result

Now the UX works as follows:

1. **Preview is broken** (no URL discovered): Red destructive alert shows with all troubleshooting steps and "Stop Dev Server & Resolve Issues" button
2. **Preview is working** (URL discovered, iframe loaded): Blue info alert shows suggesting web companion installation, with dismiss button (X)
3. **Web companion detected**: No warnings shown

This allows users to:
- See their preview immediately without blocking errors
- Still discover the web companion feature through a friendly, dismissible notification
- Distinguish between critical errors and optional features
- Dismiss the companion warning if not interested (persists only for current session)

* Perfect! All review comments have been addressed. Let me create a summary:

## Summary of Changes

I've successfully addressed all three review comments:

### 1. **Why import X?** (Line 3)
The `X` icon from lucide-react is used for dismiss buttons on both alert banners (lines 225 and 240).

### 2. **Missing translations** (Line 100)
Added `companionAlert` translations to both additional language files:

**Spanish** (`frontend/src/i18n/locales/es/tasks.json:100-104`):
- title: "Habilitar Click-to-Component"
- message: "Instala el Web Companion para desbloquear la funcionalidad de clic para editar."
- link: "Ver guía de instalación"

**Japanese** (`frontend/src/i18n/locales/ja/tasks.json:100-104`):
- title: "Click-to-Componentを有効化"
- message: "Web Companionをインストールして、クリックして編集機能を有効にします。"
- link: "インストールガイドを表示"

### 3. **Critical error alert should be dismissible** (Line 122)
Modified the red destructive alert in `PreviewTab.tsx:186-229` to:
- Wrap content in a flex container with space for the close button
- Add an X button in the top-right corner (same pattern as companion warning)
- Keep the "Stop Dev Server & Resolve Issues" button for those who want to stop
- Allow dismissal for backend-only users who want to focus on logs

**Files changed:**
- `frontend/src/components/tasks/TaskDetails/PreviewTab.tsx` (lines 186-229)
- `frontend/src/i18n/locales/es/tasks.json` (lines 100-104)
- `frontend/src/i18n/locales/ja/tasks.json` (lines 100-104)

Both alerts (critical error and companion warning) are now dismissible, fully translated, and provide a better UX for different user scenarios.

* Cleanup script changes for task attempt a91eb42f-7923-473a-8e9c-7e471e9ccb3d

* Perfect! Let me create a summary:

## Summary - Simple Solution Implemented

I've reverted to a much simpler approach that solves all the problems with minimal changes:

### What Changed

**Single file modified:** `frontend/src/components/tasks/TaskDetails/PreviewTab.tsx`

**Changes:**
1. Added `X` import from lucide-react (line 3)
2. Made the warning alert dismissible by:
   - Wrapping the alert content in a flex container (line 178)
   - Adding an X button in the top-right corner (lines 211-218)
   - Clicking X calls `setShowHelp(false)` to dismiss the alert

### What This Solves

✅ **Original issue**: Users can dismiss false-positive warnings when preview is working
✅ **Backend users**: Can dismiss the alert and fullscreen the logs tab
✅ **Web companion discovery**: Warning still shows (includes companion installation info) but is dismissible
✅ **Simplicity**: Minimal code change, no complex logic, easy to understand

### Code Structure

The warning now has this structure:
```tsx
[Warning Title]                                    [X]
[Troubleshooting items 1-3]
[Stop Dev Server & Resolve Issues button]
```

Users can either:
- Click X to dismiss and continue working
- Click "Stop Dev Server & Resolve Issues" to stop and fix problems

**Note:** I kept the companion alert translations in `es/tasks.json` and `ja/tasks.json` in case you want to use them in the future, but they're not referenced in the code anymore.

* Done. All unused translations removed.

## Final Summary - Simple Solution

**Files changed:**
- `frontend/src/components/tasks/TaskDetails/PreviewTab.tsx`

**What changed:**
1. Added `X` import from lucide-react
2. Made the warning alert dismissible with an X button in the top-right corner

**What this solves:**
- Users can dismiss false-positive warnings
- Backend users can dismiss and focus on logs
- Web companion is still discoverable (warning shows but is dismissible)
- Minimal, clean code change

No unused code left behind.
 2025-10-15 13:03:36 +01:00
Gabriel Gordon-Hall
77309ff601 tone down log level of recurrent errors (#1016) 2025-10-15 12:05:28 +01:00
Britannio Jarrett
7136085d52 enforce switch statement exhaustiveness in linter (#941) 
remove padding from windsurf logos
 2025-10-15 10:45:10 +01:00
Y. Fred Kim
83d6195466 완벽합니다! 한국어 로케일 추가 작업이 완료되었습니다. 변경된 내용을 요약해드리겠습니다: (#994) 
## 완료된 작업 ✓

### 1. **Rust 백엔드 업데이트**
- `crates/services/src/services/config/versions/v6.rs:21`에 `Ko` (Korean) variant 추가

### 2. **한국어 번역 파일 생성**
`frontend/src/i18n/locales/ko/` 디렉토리에 4개의 JSON 파일 생성:
- `common.json` - 공통 UI 요소 (버튼, 상태, 언어 등)
- `projects.json` - 프로젝트 관련 텍스트
- `settings.json` - 설정 페이지 전체 번역
- `tasks.json` - 작업 관리 관련 텍스트

### 3. **프론트엔드 i18n 설정 업데이트**
- `frontend/src/i18n/languages.ts:13` - `UI_TO_I18N`에 `KO: 'ko'` 추가
- `frontend/src/i18n/languages.ts:16` - `SUPPORTED_UI_LANGUAGES`에 `'KO'` 추가
- `frontend/src/i18n/languages.ts:23` - `FALLBACK_ENDONYMS`에 `ko: '한국어'` 추가
- `frontend/src/i18n/config.ts:19-22` - 한국어 번역 파일 import 추가
- `frontend/src/i18n/config.ts:43-48` - resources 객체에 한국어 리소스 추가

### 4. **TypeScript 타입 업데이트**
- `shared/types.ts:109` - `UiLanguage` 타입에 `"KO"` 추가

### 검증 완료
- ✅ 모든 JSON 파일이 유효한 형식
- ✅ Git에 변경사항 확인됨
- ✅ 한국어 로케일 디렉토리 및 파일 생성 완료

이제 사용자는 설정에서 언어를 "한국어"�� 선택할 수 있으며, UI가 한국어로 표시됩니다!
 2025-10-13 10:35:01 +01:00
Solomon
3d2f062c2f fix: retry modal horizontal overflow (#991) 
Break content onto the next line horizontal space runs out.
 2025-10-10 14:46:34 +01:00
Louis Knight-Webb
f78decada9 Adjust useConversationHistory (vibe-kanban) (#989) 
* Done! The changes ensure user messages display immediately when a coding agent execution process is created.

**What changed:**
1. `getActiveAgentProcess()` - now detects created/queued/running processes (not just running)
2. `ensureProcessVisible()` - adds process to state with empty entries and emits immediately
3. `idStatusKey` - tracks status changes so effect runs when process transitions states
4. Active process effect - calls `ensureProcessVisible()` before starting stream

**Result:** User sees their message instantly, then logs populate as they stream in.

* Done! All consistency issues fixed:

**Changes made:**
1. ✅ Moved `emitEntries()` out of `ensureProcessVisible()` to caller - consistent with pattern where helpers mutate but don't emit
2. ✅ Updated both historic loaders to skip `['created', 'queued', 'running']` - prevents race condition with active process path
3. ✅ Renamed `lastRunningProcessId` → `lastActiveProcessId` - accurate naming for what it tracks

The implementation is now internally consistent with the existing codebase patterns.

* Done! The fix ensures streaming only starts when the process is actually `running`, not when it's just `created` or `queued`.

**How it works now:**
1. Process detected (created/queued/running) → user message shows immediately
2. Process transitions to `running` → streaming starts once and logs appear
3. No wasted backoff attempts before endpoint is ready

* ## Analysis Complete

I found the fork's enum attribute: **`#[ts(use_ts_enum)]`**

**Current state:**
- Rust: `ExecutionProcessStatus` enum with values `Running`, `Completed`, `Failed`, `Killed`
- TypeScript: `type ExecutionProcessStatus = "running" | "completed" | "failed" | "killed"`

**Important finding:** The Oracle identified a bug in our recent changes - we're checking for `['created', 'queued', 'running']` but `ExecutionProcessStatus` doesn't have `created` or `queued` values. Those don't exist in the enum.

## Proposed Changes

1. **Add `#[ts(use_ts_enum)]` to Rust enum** in [crates/db/src/models/execution_process.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/91b8-adjust-useconver/crates/db/src/models/execution_process.rs#L31-L39)
2. **Regenerate TypeScript types** with `npm run generate-types`
3. **Fix the bug in useConversationHistory.ts** - remove `'created', 'queued'` from the check (they don't exist)
4. **Update frontend to use enum** instead of string literals

**Proceed with this plan?**

* Cleanup script changes for task attempt 91b81dd2-0f76-48f7-a309-683373d87d0d

* Done! All changes complete:

**Changes made:**
1. ✅ Added `#[ts(use_ts_enum)]` to Rust enum
2. ✅ Regenerated TypeScript types - now `export enum ExecutionProcessStatus`
3. ✅ Fixed bug: removed non-existent `'created', 'queued'` from status checks
4. ✅ Updated all frontend code to use `ExecutionProcessStatus.running` instead of string literals

**Result:** TypeScript now has a proper enum with type safety and autocomplete, and the bug with checking for non-existent statuses is fixed.

* remove unnecessary path
 2025-10-10 09:57:16 +01:00
Alex Netsch
cd06bf01b0 File search in approval text box (vibe-kanban) (#966) 
* Perfect! The implementation is complete. Let me create a summary of what was changed:

## Summary

Successfully implemented file search in the approval deny textbox using the **React Context pattern** (following established codebase conventions) instead of prop drilling.

### Changes Made:

**1 file modified** (vs 5 files with prop drilling approach):

**`PendingApprovalEntry.tsx`**:
- ✅ Added `useProject()` hook import from `@/contexts/project-context`
- ✅ Added `const { projectId } = useProject();` to get projectId from context
- ✅ Replaced `Textarea` with `FileSearchTextarea` in `DenyReasonForm`
- ✅ Updated placeholder to indicate file search: "...type @ to search files"
- ✅ Pass `projectId` to `FileSearchTextarea`

### How It Works:

1. User clicks "Deny" button on an approval request
2. Deny reason form appears with `FileSearchTextarea`
3. User types `@` to trigger file search dropdown
4. `FileSearchTextarea` uses `projectId` to search files via API
5. User can select files from dropdown to reference them in denial reason

### Why This Approach:

✅ **Follows existing patterns**: `FollowUpEditorCard`, `DiffCard`, `Navbar` all use `useProject()` hook
✅ **No prop drilling**: Context is already available at app root level
✅ **Minimal changes**: Only 1 component modified
✅ **More maintainable**: If projectId source changes, only context needs updating
✅ **Cleaner interfaces**: No unnecessary props through intermediate components

The feature is now ready to test!

* Perfect! I've fixed the styling issue. The changes I made:

**Updated `className` from:**
```
className="text-sm"
```

**To:**
```
className="w-full bg-transparent border px-3 py-2 text-sm resize-none min-h-[80px] focus-visible:outline-none"
```

This matches the original `Textarea` component's styling exactly:
- ✅ `w-full` - full width
- ✅ `bg-transparent` - transparent background (original had this)
- ✅ `border` - adds border
- ✅ `px-3 py-2` - proper padding (3 horizontal, 2 vertical)
- ✅ `text-sm` - small text size
- ✅ `resize-none` - prevents manual resizing
- ✅ `min-h-[80px]` - minimum height of 80px (same as original)
- ✅ `focus-visible:outline-none` - removes outline on focus

Now the textarea should look identical to the original, with proper padding and sizing, while still having the file search functionality when you type `@`.

* Perfect! Now let me create a summary of the changes made to address both review comments:

## Summary of Changes

### Addressing Review Comment 1: "Do we still need inputRef?"

**Yes, we still need it!**

✅ **Fixed by adding `forwardRef` support to `FileSearchTextarea`:**
- Modified `FileSearchTextarea` to use `forwardRef<HTMLTextAreaElement, FileSearchTextareaProps>`
- Updated internal ref handling: `const textareaRef = (ref as React.RefObject<HTMLTextAreaElement>) || internalRef;`
- Now properly forwards refs to `AutoExpandingTextarea`
- Added `ref={inputRef}` to the `FileSearchTextarea` in `DenyReasonForm`

**Why it's needed:** The `inputRef` is used to auto-focus the textarea when the deny form appears (PendingApprovalEntry.tsx:308-311):
```tsx
useEffect(() => {
  if (!isEnteringReason) return;
  const id = window.setTimeout(() => denyReasonRef.current?.focus(), 0);
  return () => window.clearTimeout(id);
}, [isEnteringReason]);
```

---

### Addressing Review Comment 2: "Why do we need explicit className now?"

✅ **Added documentation comment explaining the difference:**

**Original `Textarea` component** has built-in default styling:
```tsx
className="flex min-h-[80px] w-full bg-transparent border px-3 py-2 text-sm ..."
```

**`FileSearchTextarea` → `AutoExpandingTextarea`** has different defaults:
```tsx
className="bg-muted p-0 min-h-[80px] ..."  // Note: p-0 (no padding!), bg-muted
```

**Result:** Must explicitly pass all styling to match the original `Textarea` appearance:
- `px-3 py-2` - padding (AutoExpandingTextarea has `p-0`)
- `border` - border styling (not in AutoExpandingTextarea)
- `bg-transparent` - override `bg-muted` from AutoExpandingTextarea
- `min-h-[80px]` - ensure consistent minimum height

**Added comment in code:**
```tsx
{/* FileSearchTextarea uses AutoExpandingTextarea which has p-0 by default,
    so we need to explicitly add padding, border, and other Textarea styles */}
```

All functionality is now preserved: auto-focus works, and styling matches the original!

* Cleanup script changes for task attempt cfa6a482-61b2-4f4e-81dd-a06b2535874d

* Done! Comments removed.

* Perfect! All changes complete. Here's a summary of what was done:

## Summary of Changes

### Question 1: Why specify `rows={3}` if it equals the default?
**Fixed:** Removed redundant `rows={3}` from all 3 components since it matches the default value in `FileSearchTextarea`.

### Question 2: Is forwardRef the best way to get the ref for focus?
**Answer:** Yes! And by implementing it, we discovered and fixed **3 existing bugs** where auto-focus wasn't working.

### Changes Made:

**1. `FileSearchTextarea` component:**
- ✅ Added `forwardRef` support to properly expose textarea refs
- ✅ Now properly forwards refs to the underlying `AutoExpandingTextarea`

**2. `PendingApprovalEntry`:**
- ✅ Removed redundant `rows={3}` prop
- ✅ Kept `ref={inputRef}` (now works correctly for auto-focus)

**3. `ReviewCommentRenderer` (bug fix):**
- ✅ Added `ref={textareaRef}` to `FileSearchTextarea`
- ✅ Removed redundant `rows={3}` prop
- ✅ **Fixed broken auto-focus** that wasn't working since migration from `Textarea`

**4. `CommentWidgetLine` (bug fix):**
- ✅ Added `ref={textareaRef}` to `FileSearchTextarea`
- ✅ Removed redundant `rows={3}` prop
- ✅ **Fixed broken auto-focus** that wasn't working since migration from `Textarea`

### Why forwardRef is the right approach:
- ✅ **Standard React pattern** for exposing refs from custom components
- ✅ **Type-safe** with proper TypeScript support
- ✅ **Consistent** with how `AutoExpandingTextarea` already works
- ✅ **Necessary** for imperative operations like `.focus()`, `.blur()`, `.setSelectionRange()`
- ✅ **Discovered bugs** in existing code that had broken auto-focus

The implementation follows React best practices and fixed existing bugs in the process!

* Done! Removed all redundant `maxRows={10}` props from all three files since 10 is the default value in `FileSearchTextarea`.

* Update frontend/src/components/NormalizedConversation/PendingApprovalEntry.tsx

Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai>

---------

Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai>
 2025-10-08 11:23:57 +01:00
Britannio Jarrett
52dcbf1fd7 replace folder icon with IDE icon in the nav bar (#969) 2025-10-08 09:26:47 +01:00
Louis Knight-Webb
36587766d6 Setting to override branch prefix (vibe-kanban) (#949) 
* ## ✅ Implementation Complete

Successfully added customizable git branch prefix setting:

### Changes Made

**Backend:**
1. [v7.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/services/src/services/config/versions/v7.rs) - Added `git_branch_prefix` field with default "vk"
2. [git.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/utils/src/git.rs) - Created validation function with tests
3. [container.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/services/src/services/container.rs#L229-L240) - Updated branch creation to use config value
4. [local container](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/local-deployment/src/container.rs#L897-L901) - Implemented `git_branch_prefix()` method

**Frontend:**
5. [GeneralSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/pages/settings/GeneralSettings.tsx#L452-L480) - Added UI input in GitHub card with preview

### Features
- Default prefix: `vk` (maintains backward compatibility)
- Empty prefix supported (branches without prefix)
- Validation ensures git-compliant names
- Preview shows branch format: `{prefix}/{uuid}-{slug}` or `{uuid}-{slug}`
- All checks passed ✓

* Cleanup script changes for task attempt 8921b110-a98c-4968-9908-c710615a968e

* ## ✅ Fixed Async Runtime Panic

Successfully converted blocking methods to async:

### Changes Made

1. **[container.rs trait](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/services/src/services/container.rs#L229-L240)** - Made both methods async, added `.await` to prefix call
2. **[LocalContainerService](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/local-deployment/src/container.rs#L898-L900)** - Changed to `config.read().await`
3. **[tasks.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/server/src/routes/tasks.rs#L167-L170)** - Added `.await` to method call
4. **[task_attempts.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/server/src/routes/task_attempts.rs#L155-L158)** - Added `.await` to method call

All checks passed ✓. The panic should be resolved - the methods now properly use async config access.

* Cleanup script changes for task attempt 8921b110-a98c-4968-9908-c710615a968e

* ## ✅ Moved to New Git Section

Created a separate Git card in [GeneralSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/pages/settings/GeneralSettings.tsx#L528-L571) positioned between GitHub and Notifications sections, with:
- Title: "Git"
- Description: "Configure git branch naming preferences"
- Branch Prefix setting with preview

All checks passed ✓

* Cleanup script changes for task attempt 8921b110-a98c-4968-9908-c710615a968e

* ## ✅ i18n Integration Complete

Added translations for the Git section in all supported languages:

### Translation Files Updated
1. **[English](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/i18n/locales/en/settings.json)** - Added `git` section with complete translations
2. **[Spanish](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/i18n/locales/es/settings.json)** - Spanish translations
3. **[Japanese](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/i18n/locales/ja/settings.json)** - Japanese translations

### Component Updated
- [GeneralSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/pages/settings/GeneralSettings.tsx#L528-L575) - Now uses `t()` for all text with dynamic preview translation

All checks passed ✓

* Commit changes from coding agent for task attempt 8921b110-a98c-4968-9908-c710615a968e

* Cleanup script changes for task attempt 8921b110-a98c-4968-9908-c710615a968e

* ## ✅ Validation Implementation Complete

Successfully addressed PR feedback by implementing comprehensive validation:

### 1. Backend: Using `git2::Branch::name_is_valid` ✅
- **[git.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/utils/src/git.rs)** - Replaced manual validation with `git2::Branch::name_is_valid`
- Uses authoritative libgit2 validation with `"{prefix}/x"` format
- Added git2 dependency to utils crate
- Updated tests (removed tests for behaviors that differ from git2)

### 2. Frontend: Real-time Validation with Error Display ✅
- **[GeneralSettings.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/pages/settings/GeneralSettings.tsx)** - Added validation logic
- Error state shows inline message below input
- Red border on invalid input (`border-destructive`)
- Save button disabled when validation fails
- Validates on input change (real-time feedback)

### 3. i18n Error Messages ✅
Added translations in all languages:
- [English](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/i18n/locales/en/settings.json#L82-L90)
- [Spanish](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/i18n/locales/es/settings.json#L79-L87)
- [Japanese](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/frontend/src/i18n/locales/ja/settings.json#L86-L94)

### 4. Backend Enforcement ✅
- **[config.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8921-setting-to-overr/crates/server/src/routes/config.rs#L104-L108)** - Validates on config save
- Returns 400 error if invalid prefix
- Backend remains source of truth

All checks passed ✓

* ✅ Fixed linting error - removed unnecessary escape character in regex. All checks now pass.

* ## ✅ Simplified Validation Text

Removed verbose rules text and made error messages more concise:

### Changes:
1. **Removed** the detailed "Allowed: letters, numbers..." rules line
2. **Simplified** error messages to be more direct:
   - "Prefix cannot contain '/'" (was "Prefix must be a single path segment (no '/').")
   - "Contains invalid sequence (.., @{)" (was "Prefix contains invalid sequence (.., @{, or @)")
   - etc.

3. **Updated all 3 languages** (English, Spanish, Japanese)

### Result:
- Helper text + preview on same line (cleaner)
- Real-time validation shows specific errors when needed
- Much less copy while maintaining clarity

All checks passed ✓

* Cleanup script changes for task attempt 8921b110-a98c-4968-9908-c710615a968e
 2025-10-07 16:33:36 +01:00
Gabriel Gordon-Hall
41eaa061fe fix: create multiple tasks bug (#958) 
* fix create multi task bug

(cherry picked from commit e44bf08cd16bf9f93ce8e774c5e8ccea782e8b55)

* fmt
 2025-10-07 14:56:56 +01:00
Louis Knight-Webb
e17de68547 Check i18n consistency (vibe-kanban) (#960) 
* ## Done! ✅

The [check-i18n.sh](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/a6aa-check-i18n-consi/scripts/check-i18n.sh) script has been extended with key consistency checking:

**What was added:**
- `get_json_keys()` - Extracts all nested keys from translation JSON files
- `check_key_consistency()` - Validates that all languages have the same keys as English
- Both checks now run in sequence with aggregated exit status

**Features:**
- Auto-discovers languages and namespaces from the filesystem
- Reports missing keys as errors (script fails)
- Reports extra keys as warnings (optional strict mode with `I18N_FAIL_ON_EXTRA=1`)
- Verbose mode available with `I18N_VERBOSE=1`

**Current issues detected:**
- Spanish translations missing 13 keys across common.json and settings.json
- Japanese translations appear to be up to date

* Perfect! All missing Spanish translations have been added and the script now passes ✅

**Added translations:**
- [es/common.json](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/a6aa-check-i18n-consi/frontend/src/i18n/locales/es/common.json): 8 conversation-related keys
- [es/settings.json](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/a6aa-check-i18n-consi/frontend/src/i18n/locales/es/settings.json): 5 settings-related keys
 2025-10-07 14:26:50 +01:00
Gabriel Gordon-Hall
0c8426ce72 Removed the diff view toggle from conversation diff entries so they always render inline, simplifying the conversation log UI. (#959) 
**Changes**
- `frontend/src/components/NormalizedConversation/EditDiffRenderer.tsx:14` drops the global diff-mode store and toggle import so the conversation view no longer renders the inline/split selector bar.
- `frontend/src/components/NormalizedConversation/EditDiffRenderer.tsx:119` locks `DiffView` to `DiffModeEnum.Unified`, guaranteeing inline diffs regardless of other toggles elsewhere.

**Tests**
- `pnpm run frontend:check` (fails: repository missing `node_modules`; `tsc` command unavailable).

**Next Steps**
1. Reinstall frontend dependencies and rerun `pnpm run frontend:check` to verify the TypeScript build.
 2025-10-07 14:24:49 +01:00
Louis Knight-Webb
5b930d9a59 Refactor branch selector (vibe-kanban) (#939) 
* Done. The input now stops keyboard events from bubbling to the DropdownMenu, and explicitly maintains focus when the menu opens.

* Done. Arrow keys, Enter, Escape, and Tab now work for navigation while typing maintains focus in the input.

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done. The component now handles all keyboard navigation manually:
- Arrow keys move the highlight without moving cursor
- Enter selects the highlighted item
- Escape closes the dropdown
- Typing maintains focus and filters the list
- Highlighted items auto-scroll into view

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done. The BranchSelector is now optimized - only rows with changed props re-render, making arrow key navigation instant even with many branches.

* Done. I've added `transition-none` to the BranchRow items to disable CSS transitions.

**Findings:**
- No global transition rules with long durations found
- The DropdownMenuItem component (line 84 in [dropdown-menu.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/fff8-typing-in-the-br/frontend/src/components/ui/dropdown-menu.tsx#L84)) has `transition-colors` in its base styles
- This transition applies to background/color changes on focus/hover

The `transition-none` class I added should override this. Please test if the arrow key navigation is now instant. If it is, we've confirmed it was the CSS transitions causing the lag.

* Done. The BranchSelector now uses react-virtuoso to render only visible items. This will make navigation instant even with thousands of branches - only ~10-20 DOM nodes are rendered at any time instead of the full list.

* Done. Fixed both issues:
- Mouse hover no longer triggers scrolling (only keyboard navigation scrolls)
- Highlighted items now have a visible accent background with a subtle ring for clear visual feedback

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done. Increased the highlight background opacity to 70% and made the ring stronger (ring-2) for much clearer visibility.

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done. The list now only scrolls when the highlighted item would go out of view, not on every arrow key press.

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done! Cleanup complete. The component is now cleaner and more maintainable:

**Changes made:**
1. ✅ Removed data-attribute handlers, replaced with direct closures
2. ✅ Changed `onClick` to `onSelect` (more correct for Radix)
3. ✅ Removed redundant `key` prop, using `computeItemKey` instead
4. ✅ Fixed tooltip on disabled items (wrapped in span for pointer events)
5. ✅ Clear search/highlight when dropdown closes
6. ✅ Renamed `highlighted` → `highlightedIndex` for clarity
7. ✅ Factored out `isBranchDisabled` helper to reduce duplication
8. ✅ Removed redundant `autoFocus` on Input

The code is now simpler (-30 lines), more readable, and follows Radix best practices. Ready for PR!

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done! i18n implementation complete for all supported languages:

**Translations added:**
- English (en) ✅
- Spanish (es) ✅
- Japanese (ja) ✅

**Component updates:**
- Added `useTranslation(['common'])` hook
- New optional `disabledTooltip` prop for workflow-specific messages
- All hardcoded strings now use translation keys
- Placeholder defaults to translated value if not provided by parent
- Disabled tooltip defaults to generic message, but can be overridden

Parents (like RebaseDialog) can now provide workflow-specific tooltips from the `tasks` namespace while the component remains generic and reusable.

* Cleanup script changes for task attempt fff8d7a8-5b6d-4410-9bd6-71130db5b91c

* Done. Removed the `onOpenAutoFocus` handler. The component is now ready for PR.

* style
 2025-10-07 11:10:00 +01:00
Alex Netsch
eb1d9ce275 Done! I've added the blue ExternalLink icon to the PR link in frontend/src/components/tasks/Toolbar/GitOperations.tsx:402. The icon will appear after the PR number text and inherit the text-info (blue) color from the parent button's className. (#951) 2025-10-06 17:48:09 +01:00
Alex Netsch
e863e2c8b9 No user deny messages in history (vibe-kanban) (#928) 
* Perfect! The implementation is clean and follows the existing patterns. Let me create a summary:

I've successfully implemented the backend solution for displaying user denial messages in the conversation history.

**File: `crates/services/src/services/approvals.rs`**

1. **Added import** (line 8):
   - Imported `EntryIndexProvider` from `executors::logs::utils`

2. **Modified `respond()` method** (lines 153-166):
   - After updating the tool status to `Denied`
   - Check if the `ApprovalStatus::Denied` variant has a `Some(reason)`
   - If yes:
     - Create an `EntryIndexProvider` initialized from the message store to get the next available index
     - Create a `NormalizedEntry` with `UserMessage` type containing the denial reason
     - Add it to the conversation using `ConversationPatch::add_normalized_entry()`

1. **Backend owns the state**: The conversation history lives in `MsgStore` on the backend - this is the proper source of truth
2. **Follows existing patterns**: Uses the same pattern as Claude executor (claude.rs:508-527) for adding user messages
3. **Proper indexing**: `EntryIndexProvider::start_from(&store)` ensures correct sequence numbering
4. **No frontend hackery**: Frontend just renders what backend provides
5. **Type safe**: Uses existing `NormalizedEntryType::UserMessage` - no new types needed
6. **Clean separation**: Backend manages state, frontend displays it

When a user denies an approval with feedback like "Please try a different approach":
1. Backend receives the denial in `approvals.rs:respond()`
2. Updates the tool entry status to `Denied { reason }`
3. Immediately adds a new `UserMessage` entry with the denial text to the conversation stream
4. Frontend receives this as a normal user message patch and displays it
5. The agent sees it as a user message in the conversation history

- ✅ TypeScript compilation passes
- ✅ Rust compilation passes
- ✅ No breaking changes
- ✅ Follows existing architectural patterns

Cleanup script changes for task attempt 8122f303-889b-4333-8024-e79b9ea7dc7e

Great question! Let me explain how a new `UserFeedback` variant would work - it might actually be cleaner. Let me check what that would look like:

A new variant would mean:
1. Add `UserFeedback` to `NormalizedEntryType` enum in `crates/executors/src/logs/mod.rs`
2. Backend uses `NormalizedEntryType::UserFeedback` instead of `UserMessage`
3. Frontend displays it like a user message (same UI component)
4. No filtering issues - it's a distinct type that won't be filtered
5. TypeScript types auto-generated, so frontend gets the type

Let me show you what this would look like:

**Pros:**
- Type-safe, explicit intent
- No filtering workarounds needed
- Clear semantic meaning
- Auto-generates TypeScript types

**Cons:**
- Larger change (need to update Rust enum, regenerate types, update frontend display logic)
- Need to run `npm run generate-types`

Let me present both options clearly so you can choose:

Perfect! Both frontend and backend compile successfully. Let me create a summary of what was implemented:

I've successfully implemented **Option 2: New `UserFeedback` Variant** to display denial messages in the conversation history.

**1. Backend: Added `UserFeedback` entry type** (`crates/executors/src/logs/mod.rs`)
- Added `UserFeedback` variant to `NormalizedEntryType` enum
- Marked with `#[ts(export)]` for TypeScript generation

**2. Backend: Use `UserFeedback` for denial messages** (`crates/services/src/services/approvals.rs`)
- When a denial has a reason, create a `NormalizedEntry` with type `UserFeedback`
- Add it to the conversation stream after the denied tool
- Removed unused metadata structs (cleaner than Option 1)

**3. TypeScript Types: Regenerated** (`shared/types.ts`)
- Ran `npm run generate-types`
- New type `{ "type": "user_feedback" }` added to `NormalizedEntryType`

**4. Frontend: Display `UserFeedback` as user message** (`DisplayConversationEntry.tsx`)
- Check for both `user_message` and `user_feedback` types
- Render both with the same `<UserMessage>` component
- Use same User icon for both types

1. **No filtering issues**: `UserFeedback` is a distinct type, won't be filtered by the user message filter
2. **Type-safe**: Explicit enum variant with auto-generated TypeScript types
3. **Semantic clarity**: Clear distinction between initial prompts and feedback
4. **Natural display**: Appears as a user message in the conversation flow
5. **Extensible**: Can be used for other user feedback scenarios in the future

When a user denies an approval with feedback like "Please try a different approach":
1. Backend creates a `UserFeedback` entry with that text
2. Frontend receives it and displays it as a user message
3. It appears in the conversation history naturally, right after the denied tool
4. The agent sees it in the context as user input

- ✅ Backend (Rust) compiles
- ✅ Frontend (TypeScript) compiles
- ✅ Types regenerated successfully
- ✅ Clean, type-safe implementation

Perfect! So the tool result IS processed. But looking at the log entry you provided, the denial message appears in a `tool_result` with `is_error: true`. Let me check what tool this corresponds to:

Perfect! Both backend and frontend compile successfully. Let me create a summary of the complete solution:

I implemented a **normalization-based approach** that works with both live sessions and old logs by extracting denial reasons from the tool_result that's already in the raw logs.

**1. Added `UserFeedback` Entry Type** (`crates/executors/src/logs/mod.rs:56`)
- New variant in `NormalizedEntryType` enum
- Represents user feedback during execution (like denial reasons)
- Auto-exported to TypeScript types

**2. Added Denial Reason Extraction** (`crates/executors/src/executors/claude.rs:316-339`)
- New function `extract_denial_reason()` that parses hook denial messages
- Pattern: `"operation blocked by hook:\n- {user's reason}"`
- Extracts the text after `"- "`

**3. Create UserFeedback During Normalization** (`crates/executors/src/executors/claude.rs:598-612` and `717-731`)
- When processing tool_result with `is_error: true`
- Call `extract_denial_reason()` to check for denial pattern
- If found, create a `UserFeedback` entry with the extracted reason
- Add it right after the denied tool
- Applies to both command tools and other tools (MCP, etc.)

**4. Display UserFeedback in Frontend** (`frontend/src/components/NormalizedConversation/DisplayConversationEntry.tsx`)
- Handle `user_feedback` type same as `user_message`
- Display with `<UserMessage>` component
- Use User icon

**5. Cleaned Up Approvals Service** (`crates/services/src/services/approvals.rs`)
- Removed the live-session-only code that added UserFeedback
- Removed unused `EntryIndexProvider` import
- Let normalization handle everything

1. **Denial reason IS in raw logs**: The hook sends denial as tool_result with `is_error: true` containing the user's feedback
2. **Survives restarts**: Raw logs are persisted to DB, including the tool_result
3. **Works for old logs**: When logs are re-normalized after restart, the extraction logic runs and creates the UserFeedback entry
4. **Type-safe**: New enum variant with proper TypeScript types
5. **No filtering issues**: `UserFeedback` is a distinct type, won't be filtered out

- ✅ Live sessions: Denial feedback appears as user message
- ✅ After restart: Old logs show denial feedback when re-normalized
- ✅ Type-safe: Proper enum variant, auto-generated TypeScript types
- ✅ Both compilations pass

When a user denies a tool with feedback like "Please try a different approach", it now appears as a separate user message in the conversation history, immediately after the denied tool.

Cleanup script changes for task attempt 8122f303-889b-4333-8024-e79b9ea7dc7e

Perfect! Both backend and frontend compile successfully. Let me create a final summary of all the changes:

1. ✅ **Duplicate code block removed** - Consolidated denial detection into one place after both command/non-command branches
2. ✅ **Pattern matching improved** - Changed from `"operation blocked by hook:"` to `"blocked by hook:"` to match both "Edit operation blocked by hook" and "operation blocked by hook"
3. ✅ **Magic strings replaced with constants** - Added `HOOK_DENIAL_PATTERN` and `HOOK_DENIAL_REASON_PREFIX` constants

**1. Added `UserFeedback` Entry Type** (`crates/executors/src/logs/mod.rs:56`)
- New variant in `NormalizedEntryType` enum for user feedback during execution

**2. Added Constants for Hook Patterns** (`crates/executors/src/executors/claude.rs:42-45`)
```rust
const HOOK_DENIAL_PATTERN: &str = "blocked by hook:";
const HOOK_DENIAL_REASON_PREFIX: &str = "- ";
```

**3. Added Denial Extraction Function** (`crates/executors/src/executors/claude.rs:321-345`)
- Detects hook denial messages in tool_result content
- Extracts user's reason from lines starting with `"- "`
- Uses constants for maintainability

**4. Create UserFeedback During Normalization** (`crates/executors/src/executors/claude.rs:703-717`)
- After processing any tool_result with `is_error: true`
- Extract denial reason and create `UserFeedback` entry
- Add it immediately after the denied tool
- **Single consolidated check** for both command and non-command tools

**5. Display UserFeedback in Frontend** (`frontend/src/components/NormalizedConversation/DisplayConversationEntry.tsx`)
- Handle `user_feedback` type same as `user_message`
- Display with `<UserMessage>` component
- Use User icon

**6. Regenerated TypeScript Types** (`shared/types.ts:287`)
- Added `{ "type": "user_feedback" }` to `NormalizedEntryType`

**7. Cleaned Up Approvals Service** (`crates/services/src/services/approvals.rs`)
- Removed unused live-session code
- Let normalization handle everything

1. **Works with old logs**: Denial reason is in persisted tool_result, extracted during re-normalization
2. **Works with live sessions**: Denial extracted during initial normalization
3. **No magic strings**: Uses constants for pattern matching
4. **No duplication**: Single denial check after tool processing
5. **Flexible pattern**: Matches "Edit operation blocked by hook" and "operation blocked by hook"
6. **Type-safe**: Proper enum variant with TypeScript types

- ✅ Backend compiles
- ✅ Frontend compiles
- ✅ No duplicate code
- ✅ Pattern improved to match your example

Cleanup script changes for task attempt 8122f303-889b-4333-8024-e79b9ea7dc7e

Perfect! Everything compiles. Let me create a summary of the final solution:

**1. Python Hook - Natural Language Marker** (`crates/executors/src/executors/hooks/confirm.py:14`)
- Prefix denial reason with `"User feedback: {reason}"`
- Natural language format that's both readable to LLM and parseable
- Example output: `"User feedback: Could you add something about a goose?"`

**2. Rust Constant** (`crates/executors/src/executors/claude.rs:44`)
```rust
const USER_FEEDBACK_MARKER: &str = "User feedback: ";
```

**3. Robust Extraction Function** (`crates/executors/src/executors/claude.rs:320-340`)
- Search for `USER_FEEDBACK_MARKER` in tool_result content
- Extract everything after the marker
- No dependency on Claude Code's error message format

**4. Added `UserFeedback` Entry Type** (`crates/executors/src/logs/mod.rs:56`)
- New variant for user feedback during execution

**5. Create UserFeedback During Normalization** (`crates/executors/src/executors/claude.rs:703-717`)
- When tool_result has `is_error: true`, check for user feedback
- Create `UserFeedback` entry with extracted text
- Works for both live sessions and old logs (persisted in raw logs)

**6. Frontend Display** (`frontend/src/components/NormalizedConversation/DisplayConversationEntry.tsx`)
- Render `user_feedback` same as `user_message`

1. ✅ **We control the format**: The `"User feedback: "` prefix is added by OUR Python script
2. ✅ **Claude Code independent**: Works regardless of how Claude Code formats hook errors
3. ✅ **Natural language**: Reads naturally - LLM sees "User feedback: {reason}" which is clear
4. ✅ **Survives restarts**: Tool_result is in persisted raw logs, re-extracted on normalization
5. ✅ **Backward compatible**: Old logs without marker simply won't match (no errors)
6. ✅ **Simple**: One constant, one natural prefix

**User denies with**: `"Could you add something about a goose?"`

**Raw log contains**:
```json
{"type":"tool_result","content":"Edit operation blocked by hook:\nUser feedback: Could you add something about a goose?","is_error":true}
```

**Extraction**: Finds `"User feedback: "`, extracts `"Could you add something about a goose?"`

**Display**: Shows as user message in conversation history

**Result**: User's feedback is visible to both user and LLM, survives restarts!

Perfect! The solution is complete. Let me create a final summary:

**Single Source of Truth:** The marker `"User feedback: "` is defined ONLY in Rust and injected into Python at runtime.

**1. Rust Constant** (`crates/executors/src/executors/claude.rs:44`)
```rust
const USER_FEEDBACK_MARKER: &str = "User feedback: ";
```

**2. Python Script Placeholder** (`crates/executors/src/executors/hooks/confirm.py:15-16`)
```python
USER_FEEDBACK_MARKER = "{{USER_FEEDBACK_MARKER}}"
formatted_reason = f"{USER_FEEDBACK_MARKER}{reason}" if reason else None
```

**3. Template Replacement** (`crates/executors/src/executors/claude.rs:241-244`)
```rust
let script_content = CONFIRM_HOOK_SCRIPT.replace(
    "{{USER_FEEDBACK_MARKER}}",
    USER_FEEDBACK_MARKER,
);
file.write_all(script_content.as_bytes()).await?;
```

**4. Extraction Function** (`crates/executors/src/executors/claude.rs:320-340`)
- Searches for `USER_FEEDBACK_MARKER` in tool_result content
- Extracts feedback text after the marker

**5. UserFeedback Entry Creation** (`crates/executors/src/executors/claude.rs:703-717`)
- During normalization, detects denials and creates UserFeedback entries

**6. Frontend Display** (`frontend/src/components/NormalizedConversation/DisplayConversationEntry.tsx`)
- Renders UserFeedback as user messages

**7. TypeScript Types** (`shared/types.ts`)
- `user_feedback` variant generated

**At deployment time:**
1. Rust defines `USER_FEEDBACK_MARKER = "User feedback: "`
2. Python script has placeholder `{{USER_FEEDBACK_MARKER}}`
3. When writing hook, Rust replaces `{{USER_FEEDBACK_MARKER}}` → `"User feedback: "`
4. Python script executes with actual value

**When user denies:**
1. Python outputs: `"User feedback: Could you add something about a goose?"`
2. This goes into tool_result in raw logs (persisted)
3. During normalization, Rust finds `"User feedback: "` and extracts the text after it
4. Creates UserFeedback entry
5. Frontend displays it as a user message

✅ **Single source of truth**: Marker defined only in Rust constant
✅ **No duplication**: Python gets value via template replacement
✅ **Format independent**: Works regardless of Claude Code's error format
✅ **Natural language**: LLM sees readable "User feedback: {text}"
✅ **Survives restarts**: Tool_result persisted in DB, re-extracted on normalization
✅ **Maintainable**: Change constant in one place, both Rust and Python updated

- ✅ Backend compiles
- ✅ Frontend compiles
- ✅ Single source of truth maintained

Cleanup script changes for task attempt 8122f303-889b-4333-8024-e79b9ea7dc7e

Perfect! Everything compiles. Let me create a final summary:

**1. Backend: Added Tool Name to UserFeedback** (`crates/executors/src/logs/mod.rs:55-57`)
```rust
UserFeedback {
    denied_tool: String,
}
```

**2. Backend: Capture Display Tool Name** (`crates/executors/src/executors/claude.rs:573-589`)
- Extract tool name before processing branches
- For MCP tools, format as `mcp:server:tool` instead of `mcp__server__tool`
- Store in `display_tool_name` variable

**3. Backend: Include Tool Name in UserFeedback** (`crates/executors/src/executors/claude.rs:734-735`)
```rust
entry_type: NormalizedEntryType::UserFeedback {
    denied_tool: display_tool_name.clone(),
},
```

**4. Backend: Single Source of Truth for Marker** (`crates/executors/src/executors/claude.rs:44`)
```rust
const USER_FEEDBACK_MARKER: &str = "User feedback: ";
```

**5. Python: Placeholder Template** (`crates/executors/src/executors/hooks/confirm.py:15-16`)
```python
USER_FEEDBACK_MARKER = "{{USER_FEEDBACK_MARKER}}"
formatted_reason = f"{USER_FEEDBACK_MARKER}{reason}" if reason else None
```

**6. Backend: Template Replacement** (`crates/executors/src/executors/claude.rs:241-244`)
```rust
let script_content = CONFIRM_HOOK_SCRIPT.replace(
    "{{USER_FEEDBACK_MARKER}}",
    USER_FEEDBACK_MARKER,
);
```

**7. Frontend: Custom Red Accent Display** (`DisplayConversationEntry.tsx:648-666`)
- Red background (`bg-red-50 dark:bg-red-950/20`)
- Red border (`border-red-400/40`)
- Bold header showing: `"{ToolName} denied by user"`
- Red text for the feedback content
- **NO** edit/retry buttons (read-only display)

**8. TypeScript Types Regenerated** (`shared/types.ts`)
```typescript
{ "type": "user_feedback", denied_tool: string }
```

When user denies "Edit" tool with "Could you add something about a goose?":

```
┌─────────────────────────────────────────┐
│ Edit denied by user                     │  ← Bold red text
│ Could you add something about a goose?  │  ← Red feedback text
└─────────────────────────────────────────┘  ← Red border/background
```

✅ **Single source of truth**: Marker defined only in Rust, injected into Python
✅ **Tool name included**: Shows which tool was denied
✅ **Distinct styling**: Red accent makes it clear this is a denial
✅ **No edit/retry**: Simple read-only display, no complex user message features
✅ **Works with old logs**: Tool_result persisted, re-extracted on normalization
✅ **Type-safe**: Tool name field in enum, auto-generated TypeScript types

- ✅ Backend compiles
- ✅ Frontend compiles
- ✅ Types regenerated
- ✅ No duplication

Cleanup script changes for task attempt 8122f303-889b-4333-8024-e79b9ea7dc7e

Perfect! The new styling should be much more subtle and blend better with the existing UI:

- **Background**: Same as user messages (no bright red)
- **Border**: Dashed like user messages, with subtle red tint (30% opacity)
- **Header**: Small text (`text-xs`), muted red, 80% opacity
- **Content**: Same font-light styling as regular user messages

This keeps the denial feedback visible but not overwhelming, similar to how the regular user message integrates into the conversation flow.

Perfect! The new styling is much more subtle:

- **Background**: Same `bg-background` as user messages (no bright red)
- **Border**: Standard dashed border (no red tint)
- **Header**: Uses semantic `--destructive` color with 70% opacity for subtlety
- **Content**: Standard user message styling (no red text)

This approach:
- ✅ Uses semantic CSS variables for proper dark mode support
- ✅ Much less visually intense - just a subtle red label
- ✅ Blends better with the conversation flow
- ✅ The small "denied by user" label provides context without overwhelming

The visual hierarchy is now: subtle header hint → main content, which matches the rest of the UI better.

* Tool denial feedback (vibe-kanban 35abbc86)

The last commit implement log entries for tool denials, it has some problems though:
Update json_error in crates/executors/src/executors/hooks/confirm.py so the marker is only prefixed when an actual user denial reason is passed—fallback errors (network failure, invalid JSON, timeouts) must keep their original text to avoid generating fake user_feedback entries.
Adjust the hook deployment in write_python_hook (crates/executors/src/executors/claude.rs) to refresh existing confirm.py files when the bundled script changes: either always rewrite, compare hashes/timestamps, or at least overwrite when the placeholder is still present. Without that, previously installed hooks never get the marker update.
Refine extract_denial_reason in claude.rs to support the real payloads coming back from Claude: preserve multi-line feedback (don’t stop at the first newline) and handle array/object forms such as [{"type":"text","text":"…"}] so the full user message survives.

lets fix these!

* Clippy

* Perfect! All changes are complete. Here's the summary:

**1. Added i18n Hook** (`DisplayConversationEntry.tsx:603`)
```typescript
const { t } = useTranslation('common');
```

**2. Used Translation Key** (`DisplayConversationEntry.tsx:661`)
```typescript
{t('conversation.deniedByUser', { toolName: feedbackEntry.denied_tool })}
```

**3. Added English Translation** (`frontend/src/i18n/locales/en/common.json:38`)
```json
"deniedByUser": "{{toolName}} denied by user"
```

**4. Added Spanish Translation** (`frontend/src/i18n/locales/es/common.json:26`)
```json
"deniedByUser": "{{toolName}} denegado por el usuario"
```

**5. Added Japanese Translation** (`frontend/src/i18n/locales/ja/common.json:38`)
```json
"deniedByUser": "{{toolName}} がユーザーによって拒否されました"
```

**6. Used Semantic Color** (`DisplayConversationEntry.tsx:658-659`)
```typescript
style={{ color: 'hsl(var(--destructive))' }}
```

The UserFeedback display now:
- ✅ Uses semantic `--destructive` color (adapts to light/dark mode automatically)
- ✅ Supports i18n for English, Spanish, and Japanese
- ✅ Subtle styling that blends with conversation flow
- ✅ Maintains tool name context

The visual is now much more subtle with proper semantic colors and internationalization support!

* Perfect! Everything compiles. Let me create a summary of the final solution:

**1. Python: Added Argument Parser** (`confirm.py:96-102`)
```python
parser.add_argument(
    "-m",
    "--feedback-marker",
    type=str,
    required=True,
    help="Marker prefix for user feedback messages.",
)
```

**2. Python: Updated json_error to Accept Marker** (`confirm.py:11`)
```python
def json_error(reason: Optional[str], feedback_marker: Optional[str] = None) -> None:
    formatted_reason = reason
    if reason and feedback_marker:
        formatted_reason = f"{feedback_marker}{reason}"
```

**3. Python: Pass Marker When Denying** (`confirm.py:162`)
```python
json_error(reason, args.feedback_marker)
```

**4. Rust: Pass Marker as CLI Arg** (`claude.rs:283`)
```rust
format!("... --feedback-marker {}", shlex::try_quote(USER_FEEDBACK_MARKER)...)
```

**5. Rust: Removed String Replacement** (`claude.rs:236-238`)
- No longer need to replace placeholders
- Just write the script as-is

✅ **Cleaner**: No template placeholder magic, just a regular CLI arg
✅ **Standard**: Follows same pattern as other args (timeout, port, etc.)
✅ **Explicit**: Marker is passed explicitly each time hook runs
✅ **Flexible**: Easy to change or extend with more parameters
✅ **Single source of truth**: Still only defined in Rust constant

**Rust defines**:
```rust
const USER_FEEDBACK_MARKER: &str = "User feedback: ";
```

**Rust invokes Python with**:
```bash
confirm.py --timeout-seconds 3605 --poll-interval 5 --backend-port 8080 --feedback-marker "User feedback: "
```

**Python receives and uses**:
```python
args.feedback_marker  # "User feedback: "
formatted_reason = f"{args.feedback_marker}{reason}"
```

No template replacement needed - clean and straightforward!

Excellent! Everything compiles. The solution is now complete and much cleaner:

**Single Source of Truth:**
```rust
const USER_FEEDBACK_MARKER: &str = "User feedback: ";
```

**How it flows:**

1. **Rust → Python** (via CLI arg):
   ```bash
   confirm.py ... --feedback-marker 'User feedback: '
   ```

2. **User denies → Python formats**:
   ```python
   formatted_reason = f"User feedback: Could you add something about a goose?"
   ```

3. **Goes into raw logs → Rust extracts**:
   ```rust
   extract_denial_reason() // finds "User feedback: " and extracts what follows
   ```

4. **Creates UserFeedback entry**:
   ```rust
   NormalizedEntryType::UserFeedback {
       denied_tool: "Edit"
   }
   content: "Could you add something about a goose?"
   ```

5. **Frontend displays with red accent**:
   ```
   Edit denied by user          ← Small red text
   Could you add something about a goose?  ← Normal text
   ```

✅ **No string replacement** - just a CLI argument
✅ **No sketchy fallbacks** - simple, direct constant usage
✅ **Single source of truth** - marker only defined in Rust
✅ **Type-safe** - `denied_tool` field in enum
✅ **i18n support** - translatable display text
✅ **Semantic colors** - uses `--destructive` CSS variable
✅ **Works with old logs** - survives restarts via raw log persistence

The implementation is now straightforward with no unnecessary complexity!

* Simplify marker parsing
 2025-10-06 15:38:18 +01:00
Alex Netsch
adc362955a Add variant/config cycle keyboard shortcut (vibe-kanban) (#922) 
* Perfect! I've successfully implemented the Shift+Tab keyboard shortcut to cycle between agent configurations. Here's a summary of the changes:

Added Shift+Tab keyboard shortcut to cycle through agent configuration variants when editing the follow-up textbox.

1. **TaskFollowUpSection.tsx** (frontend/src/components/tasks/TaskFollowUpSection.tsx:125-136, 400)
   - Added `cycleVariant` function that cycles to the next variant in the current profile
   - Passed `onShiftTab={cycleVariant}` to `FollowUpEditorCard`

2. **FollowUpEditorCard.tsx** (frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx:17, 31, 50)
   - Added `onShiftTab?: () => void` prop to component interface
   - Passed through to `FileSearchTextarea`

3. **file-search-textarea.tsx** (frontend/src/components/ui/file-search-textarea.tsx:25, 40, 294)
   - Added `onShiftTab?: () => void` prop to component interface
   - Passed through to `AutoExpandingTextarea`

4. **auto-expanding-textarea.tsx** (frontend/src/components/ui/auto-expanding-textarea.tsx:8, 21, 62-65, 77)
   - Added `onShiftTab?: () => void` prop to component interface
   - Implemented Shift+Tab handler in `handleKeyDown` that prevents default behavior and calls the callback
   - Added to useCallback dependencies

- When the user presses **Shift+Tab** while editing the follow-up textbox, it cycles to the next agent configuration variant
- The `VariantSelector` component already has bump animation implemented (TaskFollowUpSection.tsx line 23-30 in VariantSelector.tsx) which will trigger on variant change
- The shortcut only works when the textbox is editable and active

The fix ensures that when `selectedVariant` is `null`, the first press of Shift+Tab will explicitly set the variant to the first one in the list (index 0), making the cycling work correctly from the start.

Perfect! I've updated the `cycleVariant` function to treat "DEFAULT" as a regular variant in the cycle. Here's what the fix does:

**The fix ensures that:**
1. When `selectedVariant` is `null`, it's treated as `"DEFAULT"` for lookup purposes
2. All variants including "DEFAULT" are included in the cycling
3. The cycle works: DEFAULT → variant1 → variant2 → ... → DEFAULT
4. When cycling lands on "DEFAULT", it converts back to `null` (since that's what the backend/API expects)

**Why this works:**
- First press from `null` (DEFAULT): Cycles to the first non-DEFAULT variant ✓
- Provides keyboard access to cycle back to DEFAULT ✓
- Treats "DEFAULT" as what it truly is: a configured variant, not a special case ✓
- No hacky filters or special-casing needed ✓

The implementation is clean and treats "DEFAULT" as a first-class variant in the cycling logic, while maintaining the existing API contract where `null` represents DEFAULT.

Perfect! Now the Shift+Tab interception only happens when `onShiftTab` is actually provided. This ensures:

1. **Follow-up text box**: Shift+Tab cycles through variants (has `onShiftTab` handler)
2. **All other textareas**: Shift+Tab works normally for browser focus navigation (no `onShiftTab` handler)

The fix preserves the default browser behavior for all existing uses of `AutoExpandingTextarea` while enabling the variant cycling feature only where it's needed.

Refactor keyboard shortcuts (vibe-kanban 67d268cf)

We did this in the last 4 commits:
Add a shortcut to cycle between agent configurations (previously called profile variants) when typing a follow up. Should be active when the user is editing the follow-up text box.
User shift tab to trigger the shortcut.

However this doesnt use the current pattern we want to use for shortcuts. Figure out the correct way and migrate.

Refactor keyboard shortcuts (vibe-kanban 4d35f44f)

Your colleague already handled one:
Refactoring Summary
The Shift+Tab shortcut was refactored from a prop-drilling approach (passing onShiftTab through multiple components) to the centralized keyboard system using the semantic hook pattern. The new implementation:

Registered the shortcut in registry.ts as CYCLE_VARIANT action bound to shift+tab in the FOLLOW_UP scope
Created a semantic hook useKeyCycleVariant for type-safe usage
Used scope management with enableScope(Scope.FOLLOW_UP) to control when the shortcut is active (only when textarea is focused AND editable)
Removed prop drilling - deleted onShiftTab props from FollowUpEditorCard, FileSearchTextarea, and AutoExpandingTextarea
Pattern for other shortcuts: Add the action/keys to registry.ts, create a semantic hook in hooks.ts, use the hook in your component with appropriate scope, and manage scope activation with enableScope/disableScope based on when the feature should be available. The when clause is only for additional runtime conditions beyond what scope controls.

Can we mirgate the rest of the shortcuts in frontend/src/components/tasks/TaskFollowUpSection.tsx

Fix shortcut regressions (vibe-kanban c07e229f)

To‑Do For Shortcuts

Restore submit shortcut in task dialog (frontend/src/components/dialogs/tasks/TaskFormDialog.tsx:491): reintroduce Cmd+Enter / Cmd+Shift+Enter when focus is in the description FileSearchTextarea. Prefer the new keyboard system—add a semantic hook (likely useKeySubmitTask) scoped appropriately, or, if we don’t have one yet, bind via useKeySubmit while the dialog is active. The binding must only be enabled when the form can submit and the textarea is focused.
Re-enable Cmd+Enter save in inline review comments (frontend/src/components/diff/CommentWidgetLine.tsx:69): same story—bring back the shortcut using our keyboard hooks so reviewers can submit without leaving the textarea.
Fix FileSearchTextarea event propagation (frontend/src/components/ui/file-search-textarea.tsx:12, :235): the component still lists onKeyDown but never calls it. Destructure onKeyDown from props and invoke it at the end of handleKeyDown so parent components can layer their own key handling again.

Fix shortcut regressions (vibe-kanban c07e229f)

To‑Do For Shortcuts

Restore submit shortcut in task dialog (frontend/src/components/dialogs/tasks/TaskFormDialog.tsx:491): reintroduce Cmd+Enter / Cmd+Shift+Enter when focus is in the description FileSearchTextarea. Prefer the new keyboard system—add a semantic hook (likely useKeySubmitTask) scoped appropriately, or, if we don’t have one yet, bind via useKeySubmit while the dialog is active. The binding must only be enabled when the form can submit and the textarea is focused.
Re-enable Cmd+Enter save in inline review comments (frontend/src/components/diff/CommentWidgetLine.tsx:69): same story—bring back the shortcut using our keyboard hooks so reviewers can submit without leaving the textarea.
Fix FileSearchTextarea event propagation (frontend/src/components/ui/file-search-textarea.tsx:12, :235): the component still lists onKeyDown but never calls it. Destructure onKeyDown from props and invoke it at the end of handleKeyDown so parent components can layer their own key handling again.

Fmt

* Perfect! I've added the `isComposing` check to `useKeyboardShortcut.ts` at line 68. This fix ensures that:

## What Was Fixed

The `isComposing` check that was lost during the rebase has been restored, but in the new architecture's proper location:

**Before the rebase (old architecture):**
- Each component (`AutoExpandingTextarea`, `Input`) had its own keyboard handlers
- The `isComposing` check was added to these handlers: `if (e.key === 'Enter' && !e.nativeEvent.isComposing)`

**After the rebase (new architecture):**
- All keyboard shortcuts centralized through `useKeyboardShortcut.ts` → `react-hotkeys-hook`
- The check needed to move to the central handler

**The fix:**
- Added `if (event.isComposing) return;` at line 68 in `useKeyboardShortcut.ts`
- This protects **all** keyboard shortcuts (not just Enter) from firing during IME composition
- Covers all actions: `SUBMIT_FOLLOW_UP`, `SUBMIT_TASK`, `CYCLE_VARIANT`, etc.

## Impact

Now when users input text using IME (Japanese, Chinese, Korean, etc.):
- Pressing Enter to confirm text conversion won't accidentally trigger shortcuts
- Pressing Shift+Tab during composition won't cycle variants
- All keyboard shortcuts properly respect IME composition state

This is actually **better** than the old fix because it applies universally to all shortcuts, not just the ones that were manually checked before.
 2025-10-06 14:11:33 +01:00
Louis Knight-Webb
7bf4b12ddb Can't retry a user message when dev server is running (vibe-kanban) (#937) 
* Done! The fix is complete and all checks pass. Here's what changed:

**Summary:**
- Replaced local `anyRunning` check with `isAttemptRunning` from `useAttemptExecution`
- Removed unused `useMemo` import
- Updated tooltip text for clarity

The retry button now correctly allows retrying when only the dev server is running, while still blocking during actual task executions (codingagent, setupscript, cleanupscript).

* Cleanup script changes for task attempt 80246ab7-5ae8-4b09-8020-839cca417fb6

* Update frontend/src/hooks/useProcessRetry.ts

Co-authored-by: Solomon <abcpro11051@disroot.org>

---------

Co-authored-by: Solomon <abcpro11051@disroot.org>
 2025-10-06 12:49:20 +01:00
Louis Knight-Webb
73f49cae9f Merged tasks are endlessly re-rendering (vibe-kanban) (#938) 
* ## ✅ Fix Complete

**Problem:** Merged tasks caused endless WebSocket reconnections because `useJsonPatchWsStream` incorrectly treated `{finished: true}` messages as signals to reconnect.

**Solution:** Modified [useJsonPatchWsStream.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/0f2d-merged-tasks-are/frontend/src/hooks/useJsonPatchWsStream.ts) to treat "finished" as terminal:

1. Added `finishedRef` to track when stream completes
2. On `{finished: true}`: set flag, close cleanly (code 1000), **no reconnect**
3. On socket close: skip reconnection if finished flag is set or clean close
4. Reset flag on cleanup and new connections

**Result:**
- Merged tasks connect once, receive final state, and stop cleanly
- Active tasks still reconnect on network errors
- Aligned behavior with existing `streamJsonPatchEntries` utility
- All type checks pass ✅

* Cleanup script changes for task attempt 0f2d0086-1de2-4517-a023-1ee8cf133181
 2025-10-06 12:49:08 +01:00
Louis Knight-Webb
fef06cf00e Done! I've successfully removed arrow key navigation while preserving hjkl shortcuts. Here's what changed: (#946) 
## Changes Made:

1. **[frontend/src/keyboard/registry.ts](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/155e-remove-keyboard/frontend/src/keyboard/registry.ts)**
   - Removed arrow keys from navigation bindings, kept only hjkl
   - Fixed Enter key conflict by changing fullscreen toggle to ⌘/Ctrl+Enter

2. **[docs/configuration-customisation/keyboard-shortcuts.mdx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/155e-remove-keyboard/docs/configuration-customisation/keyboard-shortcuts.mdx)**
   - Updated Board Navigation section to show hjkl only
   - Added fullscreen toggle documentation

All type checks pass ✓
 2025-10-06 10:51:26 +01:00
Louis Knight-Webb
f26f70060c Markdown renderer bug (vibe-kanban) (#940) 
* Done! Fixed the markdown renderer bug with a simple one-line change plus typo fix. All type checks pass.

**Changes made:**
1. Added `disableParsingRawHTML: true` to prevent invalid ref attributes from raw HTML
2. Fixed typo: `text-baseleading-tight` → `text-base leading-tight`

* Cleanup script changes for task attempt 67d094ca-1a5f-4713-b595-26fce3aea3ef
 2025-10-04 22:25:35 +01:00
hayato iida
567b4a0411 Fix: Prevent form submission during IME composition (#934) 
This fix addresses issue #919 where pressing Enter during IME (Input Method Editor)
composition incorrectly triggers form submission in task title and description fields.

Changes:
- Add isComposing check to Input component's Enter key handler
- Add isComposing check to AutoExpandingTextarea component's Enter key handler

This ensures that Enter key during IME composition (e.g., Japanese, Chinese, Korean input)
only confirms the text conversion without accidentally submitting the form.

Fixes #919
 2025-10-04 14:30:46 +01:00
Louis Knight-Webb
c45e40717e Close GitHub popup after login (vibe-kanban) (#930) 
* ## Fix Implemented Successfully ✅

I've implemented the GitHub popup auto-close fix with two key changes to [`GitHubLoginDialog.tsx`](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/d872-close-github-pop/frontend/src/components/dialogs/auth/GitHubLoginDialog.tsx):

1. **Auto-close effect**: Added a `useEffect` that automatically closes the dialog when the user becomes authenticated
2. **Reduced flicker**: Reordered the SUCCESS polling case to avoid briefly showing the "Sign in again" prompt

The popup will now automatically close within ~1 second after successful GitHub authentication, eliminating the confusing "sign in again" prompt. Type checks pass successfully.

* ## Fix Implemented Successfully ✅

I've implemented the complete fix for the GitHub popup staying open in the settings page:

**Changes Made:**

1. **Updated [`GitHubLoginDialog.tsx`](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/d872-close-github-pop/frontend/src/components/dialogs/auth/GitHubLoginDialog.tsx#L34-L40)**: Added `modal.resolve(true)` before `modal.hide()` in the auto-close effect to properly settle the Promise

2. **Simplified [`GeneralSettings.tsx`](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/d872-close-github-pop/frontend/src/pages/settings/GeneralSettings.tsx#L489-L491)**: Removed the unnecessary `.finally()` chain since the dialog now manages its own lifecycle

The popup will now automatically close after successful GitHub authentication from both the onboarding flow and the settings page. Type checks pass successfully.

* Cleanup script changes for task attempt d8729f37-551a-4490-a0bd-396032d528ce

* ## Self-Contained Fix Implemented Successfully ✅

I've implemented Option 2 - the most predictable approach that makes the dialog self-contained:

**Changes Made:**

1. **Removed the auto-close effect** that depended on external state changes
2. **Added direct modal close in the SUCCESS case** of the device flow polling:
   - After `await reloadSystem()`, immediately call `modal.resolve(true)` and `modal.hide()`
   - This happens right when we know authentication succeeded

**Benefits of this approach:**
- **Self-contained**: The dialog manages its own lifecycle without depending on external state
- **Predictable**: The flow is linear and obvious: start → poll → success → close
- **Readable**: No complex state dependencies or effects to understand
- **Reliable**: Eliminates the timing issues with stale `githubTokenInvalid` flags

The popup will now automatically close immediately after successful GitHub authentication in both the onboarding and settings flows. Type checks pass successfully.
 2025-10-03 19:23:13 +01:00
Louis Knight-Webb
c8e660c7da Add discord shield to navbar (vibe-kanban) (#927) 
* ✅ Discord shield added to navbar with:

- **Desktop badge**: Discord shield visible on sm+ screens, positioned before the dropdown menu
- **Mobile fallback**: Discord link added to dropdown menu for small screens
- **Consistent styling**: Uses `h-5` height and proper spacing (`ml-2 mr-1`)
- **Accessibility**: Includes proper `aria-label` and `alt` text

The implementation follows the existing code patterns and maintains readability as requested.

* ✅ Fixed both issues:

- **Vertical centering**: Changed from `block` to `flex items-center` to properly align with other navbar buttons
- **Theme adaptation**: Added `dark:brightness-90 dark:contrast-125` to subtly adjust the shield colors in dark mode for better visibility

The Discord shield now properly aligns with other navbar elements and adapts to both light and dark themes.

* ✅ Updated Discord shield with theme colors and positioning:

- **Theme colors**: Custom badge using `bg-background`, `text-foreground` for left side and `bg-success`, `text-success-foreground` for right side
- **Position**: Moved to right of logo (left side of navbar) instead of right side
- **Design**: Clean two-part badge with "discord" label and "online" status that adapts to theme automatically

The Discord badge now uses your app's theme colors and is positioned next to the logo for better visual hierarchy.

* ✅ Discord online count implemented with:

- **Live data**: Fetches real member count from Discord Widget API
- **Auto-refresh**: Updates every 60 seconds for live feel
- **Graceful fallback**: Shows "online" if API unavailable
- **Theme integration**: Maintains your custom success/background colors
- **Accessibility**: Includes `aria-live="polite"` for screen readers
- **Formatted display**: Shows count as "1,234 online" with proper locale formatting

The Discord badge now displays the actual number of online members from your server while maintaining the theme colors and positioning next to the logo.

* Cleanup script changes for task attempt 230fa5cc-96f7-4fdb-a549-c2ea46b9e88e

* ✅ Fixed positioning - Added `flex items-center` to the container so the logo and Discord badge sit side by side horizontally instead of stacking vertically.

* ✅ Added Discord logo from simple-icons:

- **Added simple-icons dependency** via pnpm
- **Imported Discord icon** from `simple-icons` package
- **Replaced "discord" text** with actual Discord SVG logo
- **Maintained theme colors** - icon uses `currentColor` so it adapts to theme automatically
- **Proper sizing** - `h-4 w-4` matches other navbar icons

The Discord badge now displays the official Discord logo instead of text, while maintaining the live member count and theme integration.

* Cleanup script changes for task attempt 230fa5cc-96f7-4fdb-a549-c2ea46b9e88e

* manual style improvement
 2025-10-03 18:52:44 +01:00
Britannio Jarrett
81af7ac36c Add remaining IDE icons (vibe-kanban) (#925) 
* Perfect! All the icons have been successfully added. The implementation is now complete:

✅ **Zed**: Added theme-aware icons (zed-dark.svg, zed-light.svg)
✅ **IntelliJ**: Added single icon (intellij.svg) since IntelliJ typically uses one consistent icon
✅ **Windsurf**: Added theme-aware icons (windsurf-dark.svg, windsurf-light.svg)

The [`IdeIcon` component](file:///private/var/folders/5q/5vgq75y92dz0k7n62z93299r0000gn/T/vibe-kanban/worktrees/2b83-remaining-ide-ic/frontend/src/components/ide/IdeIcon.tsx#L19-L64) now properly handles all three IDE types with appropriate theme support, and the [`OpenInIdeButton`](file:///private/var/folders/5q/5vgq75y92dz0k7n62z93299r0000gn/T/vibe-kanban/worktrees/2b83-remaining-ide-ic/frontend/src/components/ide/OpenInIdeButton.tsx) component already had the correct labels configured.

* Perfect! I've made the following changes:

✅ **Fixed Zed icons**: Now correctly uses light icon on dark theme and dark icon on light theme
✅ **Fixed Windsurf icons**: Now correctly uses light icon on dark theme and dark icon on light theme
✅ **Added Xcode support**: Ready to display Xcode icon when you add `xcode.svg` to the `/ide` directory

The icon mapping now works correctly - dark-colored icons show on light backgrounds, and light-colored icons show on dark backgrounds.

* Perfect! The Xcode icon has been successfully added. Now all IDE icons are in place:

✅ **Xcode**: Added `xcode.svg` icon
✅ **Zed**: Theme-aware icons with correct mapping
✅ **IntelliJ**: Single consistent icon
✅ **Windsurf**: Theme-aware icons with correct mapping

All IDE types from the EditorType enum now have proper icon support in the [`IdeIcon` component](file:///private/var/folders/5q/5vgq75y92dz0k7n62z93299r0000gn/T/vibe-kanban/worktrees/2b83-remaining-ide-ic/frontend/src/components/ide/IdeIcon.tsx).

* format IdeIcon.tsx
 2025-10-03 16:42:02 +01:00
Solomon
a43fa76079 Copilot CLI (#915) 2025-10-03 13:12:53 +01:00
Alex Netsch
8dc297c521 Fix mem leak (#916) 
* Fix mem leak

* Fix cross-platform, fix no error logging
 2025-10-03 09:46:44 +01:00
Solomon
b40b7f21b9 Speed-up running process check (#894) 2025-10-02 15:40:09 +01:00
Alex Netsch
2f2e85b6e0 Disable follow-up textbox during approvals (vibe-kanban) (#914) 
* Perfect! All changes have been implemented successfully. Let me summarize what was done:

## Summary

I've successfully implemented the feature to disable the follow-up textbox during approvals. Here's what was changed:

### Changes Made:

1. **Created `usePendingApproval` hook** (`frontend/src/hooks/usePendingApproval.ts`):
   - This hook checks the conversation entries from `EntriesContext` to detect if any tool use entry has a `pending_approval` status
   - Returns a boolean indicating whether there's a pending approval

2. **Updated `TaskFollowUpSection` component** (`frontend/src/components/tasks/TaskFollowUpSection.tsx`):
   - Imported and used the new `usePendingApproval` hook
   - Updated `canTypeFollowUp` to include the `hasPendingApproval` check, preventing users from typing when an approval is pending
   - Updated `isEditable` to include `!hasPendingApproval`, which disables the textbox UI when there's a pending approval

### How It Works:

- When an agent requests approval for a tool use, the conversation entry will have a `status: 'pending_approval'`
- The `usePendingApproval` hook detects this by checking all entries in the `EntriesContext`
- When a pending approval is detected, the follow-up textbox becomes disabled, preventing users from typing and queueing follow-ups
- Once the approval is resolved (approved/denied), the entry status changes and the textbox becomes enabled again

The implementation follows the existing patterns in the codebase and integrates smoothly with the existing approval UI and context system. TypeScript type checking passes successfully.

* Cleanup script changes for task attempt bd98d75b-12d0-45da-b486-f516b274abff

* Perfect! The refactoring is complete. Here's what I did:

## Changes Made

1. **Deleted** `frontend/src/hooks/usePendingApproval.ts` - the custom hook was unnecessary

2. **Updated** `TaskFollowUpSection.tsx`:
   - Removed import of `usePendingApproval`
   - Added import of `useEntries` from `@/contexts/EntriesContext`
   - Replaced the hook call with inline logic using `useEntries()` and `useMemo()`

## Result

The implementation is now:
- **Simpler** - one less file to maintain
- **More consistent** - follows the same pattern as `TodoPanel.tsx` which also uses `useEntries()` directly
- **Just as efficient** - still memoized, same performance
- **Easier to understand** - all the logic is in one place

The functionality remains exactly the same - the follow-up textbox (and all related buttons) will be disabled when there's a pending approval in the conversation entries. TypeScript type checking passes successfully.
 2025-10-02 15:20:08 +01:00
Alex Netsch
a2153be98c Keep git panel when branchstatus fails (vibe-kanban) (#913) 
* Done! I've updated the code to keep the Git panel visible when `branchStatus` fails:

**Changes made:**

1. **GitOperations.tsx:253-256**: Changed the early return condition to only hide the panel when PR is merged, not when `branchStatus` is null
2. **GitOperations.tsx:438-505**: Wrapped the merge/PR/rebase buttons in a conditional `{branchStatus && ...}` so they only display when branch status is available
3. **TaskDetailsToolbar.tsx:227-238**: Removed the `branchStatus` condition from the parent, so `GitOperations` is always rendered when `selectedAttempt` exists

**Result:**
- The Git panel (showing branch names and the arrow) will now always display when there's a selected attempt
- The merge, PR, and rebase buttons will only show when branch status loads successfully
- The panel still hides completely if the PR has been merged

* Updated! Now the target branch will fallback to `selectedAttempt.target_branch` if `branchStatus` doesn't load, ensuring the target branch label always displays correctly.
 2025-10-02 11:17:18 +01:00
Gabriel Gordon-Hall
d10c37f061 don't show virtuoso loader when pending approval (#909) 2025-10-01 18:16:15 +01:00
Louis Knight-Webb
b631f6fbc6 Improve plan scroll (#908) 
* Done! I've removed the scrolling classes from the plan container. Plans will now use the parent chat history scroll instead of having their own nested scroll behavior.

The fix removes `max-h-[65vh] overflow-y-auto overscroll-contain` while preserving the padding and background styling.

* Cleanup script changes for task attempt 6c65f630-c1bb-4069-b3d8-7d937fc35bf7
 2025-10-01 18:10:45 +01:00
Greg Burch
0e9d10732a Allow image pasting into task field (#883) 
* **Changes**
- Made `ImageUploadSection` ref-aware with an `addFiles` imperative handle and auto-expansion when images appear, enabling non-UI triggers to reuse its validation/upload flow (frontend/src/components/ui/ImageUploadSection.tsx:36-348).
- Captured clipboard image blobs in the shared textarea component and exposed them via a new `onPasteFiles` hook for upstream consumers (frontend/src/components/ui/file-search-textarea.tsx:111-137).
- Task creation dialog now routes pasted images straight into the uploader through the new ref, keeping the description markdown in sync (frontend/src/components/dialogs/tasks/TaskFormDialog.tsx:102-357).
- Follow-up editor keeps the image panel mounted but hidden, reveals it on paste, and forwards the new prop through its wrapper so task attempts accept clipboard images (frontend/src/components/tasks/TaskFollowUpSection.tsx:89-325; frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx:13-47).

**Tests**
- `npm run check` (frontend)
- `pnpm run check` (timed out after backend cargo check kicked off; see log)

**Next Steps**
1. Re-run `pnpm run check` or `npm run backend:check` when you can let Cargo finish to confirm backend continues to build.
2. Manually paste a few image formats/sizes into the task form and follow-up editor to confirm UX and markdown output look right.

* Update frontend/src/components/ui/ImageUploadSection.tsx

Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai>

* fmt

---------

Co-authored-by: Greg Burch <gburch@styleseat.com>
Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai>
Co-authored-by: Gabriel Gordon-Hall <ggordonhall@gmail.com>
 2025-10-01 17:17:51 +01:00
Louis Knight-Webb
2781e3651b Add preview tab + point and click editor (vibe-kanban) (#870) 
* Perfect! The preview tab implementation is complete and all type checks pass. Let me provide a summary of what was implemented:

1. **Updated `TabType`** - Added 'preview' to the union type
2. **Created `useDevserverPreview` hook** - Intelligent devserver URL detection with:
   - Real-time log parsing using the regex `(?:localhost|127\.0\.0\.1|0\.0\.0\.0):(\d+)[^\d]*`
   - Three states: idle/searching/ready
   - URL normalization (0.0.0.0 → localhost)
   - Process monitoring for setup scripts and dev servers

3. **Built `PreviewTab` component** - Full-featured iframe preview with:
   - Proper sandbox settings for security
   - Toolbar with refresh, copy URL, and open external buttons
   - Smart error handling for mixed content/CORS issues
   - Clear empty states and loading indicators

4. **Enhanced `TabNavigation`** - Conditionally shows preview tab with:
   - Monitor icon and spinner when searching
   - Only appears when devserver is detected or likely

5. **Integrated in `TaskDetailsPanel`** - Wires everything together in fullscreen mode

- **Smart Detection**: Parses logs in real-time to find devserver URLs
- **Robust Error Handling**: Graceful fallbacks for iframe loading issues
- **Security**: Proper iframe sandboxing with necessary permissions
- **Performance**: Efficient log processing with deduplication
- **UX**: Clear states (searching/ready/error) with helpful messaging

The implementation follows the Oracle's architectural recommendations with proper separation of concerns and real-time detection capabilities.

* Cleanup script changes for task attempt 4f59c374-1cc5-4b3c-a79a-5f63756a366b

* Perfect! Now the preview tab will use the **first** dev server URL it detects rather than being overwritten by subsequent matches. This means:

- If both backend (e.g., `:3001`) and frontend (e.g., `:5173`) servers start
- The preview tab will show whichever URL appears first in the logs
- Subsequent URLs will be ignored to avoid switching the preview unexpectedly

This provides a more stable preview experience when multiple dev servers are running.

* Cleanup script changes for task attempt 4f59c374-1cc5-4b3c-a79a-5f63756a366b

* add parent lib

* fmt

* Listen for communication from the preview tab (vibe-kanban ace46045)

In frontend/src/components/tasks/TaskDetails/PreviewTab.tsx

We should expect that the iframe will communicate via frontend/src/utils/previewBridge.ts

When a message is received, we should add some details about the clicked element to the follow up textarea

* Component to view clicked element (vibe-kanban e3b90cc1)

frontend/src/components/tasks/TaskDetails/PreviewTab.tsx
frontend/src/components/tasks/TaskFollowUpSection.tsx

When a user clicks on an element, we should display a box in the follow up section similar to how we show reviews or conflicts.

The section should display a summary of each of the elements, the name of the component and the file location.

When the user sends a follow up, a markdown equivalent of the summary should be appended to the top of the follow up message.

* Component to view clicked element (vibe-kanban e3b90cc1)

frontend/src/components/tasks/TaskDetails/PreviewTab.tsx
frontend/src/components/tasks/TaskFollowUpSection.tsx

When a user clicks on an element, we should display a box in the follow up section similar to how we show reviews or conflicts.

The section should display a summary of each of the elements, the name of the component and the file location.

When the user sends a follow up, a markdown equivalent of the summary should be appended to the top of the follow up message.

* Tweaks to component click (vibe-kanban 756e1212)

Preview tab frontend/src/components/tasks/TaskDetails/PreviewTab.tsx
- Preview should remember which URL you were on
- Auto select the follow up box after point and click, so you can type feedback

Clicked elements: frontend/src/components/tasks/ClickedElementsBanner.tsx, frontend/src/contexts/ClickedElementsProvider.tsx
- The list of components should not overflow horizontally, instead we should truncate, omiting components from the left first
- If the user clicks on a component, it should omit the downstream components from the list, they should be displayed disabled and the prompt should start from the selected component

* strip ansi when parsing dev server URL

* cleanup

* cleanup

* improve help copy

* start dev server from preview page

* dev server wip

* restructure

* instructions

* fix

* restructur

* fmt

* i18n

* i18n fix

* config fix

* wip cleanup

* minor cleanup

* Preview tab feedback (vibe-kanban d531fff8)

In the PreviewToolbar, each icon button should have a tooltip

* fix + fmt

* move dev script textarea

* improve when help is shown

* i18n

* improve URL matching

* fix close logs

* auto install companion

* cleanup notices

* Copy tweak
 2025-10-01 17:15:12 +01:00
Gabriel Gordon-Hall
0ace01b55f - remove AbortController in PendingApprovalEntry (#902) 
- fix find execution process check
- force stop process with non-killed status
 2025-10-01 16:51:23 +01:00
Louis Knight-Webb
0bf4733bff ## ✅ Fix Complete! (#892) 
I've successfully implemented the fix for the todos not updating when navigating between task attempts. Here's what I changed:

**File:** [`TaskDetailsPanel.tsx`](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/cf76-todos-do-not-upd/frontend/src/components/tasks/TaskDetailsPanel.tsx#L100)

**Change:** Added `key={selectedAttempt?.id}` to the `EntriesProvider` component

```tsx
// Before
<EntriesProvider>

// After
<EntriesProvider key={selectedAttempt?.id}>
```

**How it works:**
- When `selectedAttempt?.id` changes, React unmounts and remounts the `EntriesProvider` with fresh state
- This immediately clears the entries array and resets the todos to an empty state
- The TodoPanel will hide until new entries arrive for the selected attempt
- No todos from previous attempts can persist

The fix is minimal, readable, and leverages React's built-in key behavior for state management - exactly what the Oracle recommended as the best approach.
 2025-09-30 16:53:40 +01:00
Solomon
f9878e9183 Consolidate Retry and Follow-up (#800) 2025-09-30 13:09:50 +01:00
Louis Knight-Webb
71bfe9ac0b Fix dropdown colours (vibe-kanban) (#891) 
* Done! The dropdown colors are now fixed for dark mode readability:

- **Selected items** now use `bg-accent text-accent-foreground` instead of hardcoded light-theme colors
- **File paths** in selected items use `text-accent-foreground/70` for better contrast
- **Added accessibility** attributes (`aria-selected` and `role="option"`)

The changes maintain your existing design token pattern and will automatically adapt to both light and dark themes.

* Cleanup script changes for task attempt 9dd6bd96-f216-408c-ab42-94eefb1437e1

* Perfect! Now the selected dropdown item uses:

1. **Background:** `bg-primary/10` (subtle primary tint)
2. **Text:** `text-primary` (primary color text)
3. **Left border:** `border-l-2 border-primary` (visual indicator)
4. **File path:** `text-primary/70` (muted primary for secondary info)

This provides much better visual distinction while maintaining theme compatibility and using your existing design token pattern.

* Cleanup script changes for task attempt 9dd6bd96-f216-408c-ab42-94eefb1437e1

* Now the selected item uses `bg-muted text-foreground` which provides proper contrast in both light and dark modes, with a primary-colored left border for visual distinction. The file path uses consistent `text-muted-foreground` in all states.

* Cleanup script changes for task attempt 9dd6bd96-f216-408c-ab42-94eefb1437e1

* Perfect! Now the selected dropdown item simply uses `bg-muted text-foreground` which provides clear contrast and visibility without the border.
 2025-09-30 13:08:06 +01:00
Gabriel Gordon-Hall
6727e2dbb9 feat: keyboard shortcuts for approvals (#869) 
* wip

* cmd click shortcut to deny approval

* cleaner type

* show percentage in progress bar

* improve structure of PendingApprovalComponent

* enter to approve request

* disable kanban scope

* fix approval scope selection
 2025-09-30 11:40:34 +01:00
Louis Knight-Webb
23243dda7a Prevent useConversationHistory conflicts (vibe-kanban) (#872) 
* ## Summary

Successfully implemented the `mergeIntoDisplayed` helper to prevent useConversationHistory conflicts! Here's what was accomplished:

**Changes made to [`frontend/src/hooks/useConversationHistory.ts`](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/5e29-prevent-useconve/frontend/src/hooks/useConversationHistory.ts):**

1. **Added mergeIntoDisplayed helper** that performs in-place mutations instead of reassigning the entire object
2. **Refactored 4 direct assignment locations**:
   - Stream updates in `loadRunningAndEmit`
   - Initial entries loading
   - Batch loading (with function signature improvement)
   - Process removal logic
3. **Maintained the deliberate reset** on attempt change (line 479)

**Key improvements**:
- Prevents race conditions between concurrent async operations
- Eliminates data loss from process log overwrites
- Maintains data integrity during streaming and batch loading
- Passes type checking successfully

The implementation follows the Oracle's recommendations for safe concurrent updates by always reading the latest state and mutating in-place rather than replacing the entire object reference.

* Cleanup script changes for task attempt 5e29a440-f572-406d-9f07-be5f11fd3775
 2025-09-30 11:18:28 +01:00
Alex Netsch
091e903cf6 Alex/refactor bb rebase (#824) 
* Refactor task_attempt branch handling and enforce NOT NULL constraint on branch column

* Change backend rebase to no change base branch, add change target branch api

* Change frontend rebase on branch to change target branch

Change status to show ahead/behind, always show rebase

* Use target branch for everything except rebase

* Remove base_branch

* Remove base branch frontend

* add rebase dialog with target and upstream options

* Fix unused upstream arg

* Add i18n

* Remove stray ts-rs file

* dont show +0, -0

* Move upstream to foldable advanced rebase

* Move buttons around

* Move git state/actions into a component

* Add task/target labels

* Fix action buttons layout

* Fmt

* i18n

* remove branch origin removal

* Remove empty divs

* Remove [1fr_auto_1fr] class in favour if divs

* use theme colours, make gear icon bigger

* Fix plural i18n

* Remove legacy ui reducer
 2025-09-29 19:50:29 +01:00
Solomon
bcd6bdbe05 Make rebase conflict resolution message read-only (#871) 2025-09-29 17:44:16 +01:00
Solomon
6f2d6d4e40 Make diff stats much faster (#866) 2025-09-29 16:16:34 +01:00
Alex Netsch
3299ff1d8a Fix children layout (vibe-kanban) (#873) 
* Perfect! I've updated the child tasks layout to always display horizontally. Here's what changed:

**Before**: Used a responsive CSS grid (`grid-cols-1 md:grid-cols-2 xl:grid-cols-3`) that would stack cards vertically on smaller screens.

**After**: Replaced with a horizontal flexbox layout that:
- Uses `flex` with `gap-4` for consistent spacing
- Adds `overflow-x-auto` to enable horizontal scrolling when needed
- Wraps each card in a `flex-none w-80` container to maintain consistent card width
- Adds `pb-2` for bottom padding to account for the scrollbar

The child tasks will now always be laid out horizontally regardless of screen size, with horizontal scrolling when there are too many cards to fit in the available width.

* Perfect! I've updated the child tasks layout to always display vertically. The changes:

- Used `flex flex-col` to create a vertical flexbox layout
- Removed the responsive grid logic and horizontal overflow handling
- Each card now spans the full width and stacks vertically with consistent `gap-4` spacing

The child tasks will now always be laid out vertically in a single column, regardless of screen size.
 2025-09-29 13:52:30 +01:00
Gabriel Gordon-Hall
dd877eaa51 feat: add task buttons to Kanban headers (#863) 
* wip: add task

* add handler

* i18n

* add button styles

---------

Co-authored-by: Louis Knight-Webb <louis@bloop.ai>
 2025-09-26 16:34:52 +01:00
Louis Knight-Webb
e3727e249d Implement Vibe Kanban Web Companion (#868) 
* add companion

* bump companion version

* update package

* update package

* cleanup

* cleanup
 2025-09-26 16:16:55 +01:00
Louis Knight-Webb
f631c8d6cf Editing task description to remove it doesn't work (vibe-kanban) (#862) 
* Perfect! The fix is implemented and compiles successfully.

**What I fixed:**
- Replaced the simple `.or()` fallback with proper empty string handling
- Empty strings (including whitespace-only) now clear the description field
- Non-empty strings update the description as before
- Omitted fields still preserve existing values

**How it works:**
- `{"description": "new text"}` → updates description to "new text"
- `{"description": ""}` → clears description (sets to NULL)
- `{"description": "   "}` → clears description (whitespace trimmed)
- `{}` (field omitted) → keeps existing description unchanged

The fix is simple, backwards-compatible, and handles the exact issue you described without requiring API changes or type modifications.

* Cleanup script changes for task attempt 42e1596a-5b1a-4061-b704-1a30d09f8192

* Perfect! The fix is complete and both frontend and backend checks pass.

**What I fixed:**
- **Frontend**: Changed `description || null` to `description` in all 3 places (edit, create, create-and-start)
- **Backend**: Already handles empty strings as clearing (from previous fix)

**How it works now:**
- When users clear a task description, frontend sends `""` (empty string)
- Backend detects `s.trim().is_empty()` and sets description to `None` (NULL in database)
- Description gets properly cleared after saving

The simple frontend change aligns both systems perfectly. Users can now clear task descriptions by editing them to be empty and saving.

* Cleanup script changes for task attempt 42e1596a-5b1a-4061-b704-1a30d09f8192
 2025-09-26 11:56:46 +01:00
Solomon
bfb0c3f2ea migrate /diff endpoint to websocket (#851) 2025-09-26 10:10:44 +01:00
Louis Knight-Webb
4f343fdb8f fix multi-shortcut issue (#856) 2025-09-25 19:53:32 +01:00
Louis Knight-Webb
4f7351ce16 Louis/keyboard shortcut improve (#847) 
* Scroll card into view when opened

* improve positioning

* More shortcuts (vibe-kanban 9f9f5c89)

Let's add some more shortcuts:
- When in fullscreen mode, 'j' should navigate to the previous task and 'k' to the next
- 'd' should trigger the delete task dialog

* More shortcuts (vibe-kanban 9f9f5c89)

Let's add some more shortcuts:
- When in fullscreen mode, 'j' should navigate to the previous task and 'k' to the next
- 'd' should trigger the delete task dialog

* More shortcuts (vibe-kanban 9f9f5c89)

Let's add some more shortcuts:
- When in fullscreen mode, 'j' should navigate to the previous task and 'k' to the next
- 'd' should trigger the delete task dialog

* Add h/l for column navigation (vibe-kanban eade645d)

Similar to how we have j and k for next/previous can we add h and l for next/previous column
 2025-09-25 18:28:18 +01:00