c861de8b2958c3097b119b6235d192bd70884d08
157 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
William Reed
|
4a48233cff |
perf: fix database query performance bottlenecks (#1982)
* perf: fix database query performance bottlenecks - Add composite index on workspace_repos(workspace_id, repo_id) to optimize lookup queries that were taking up to 5 seconds - Add composite index on merges(merge_type, pr_status) to optimize status filtering queries that were taking 2+ seconds - Fix N+1 query pattern in workspace_repos.create_many by wrapping inserts in a transaction - Fix N+1 query pattern in get_task_attempt_branch_status by batch fetching all merges upfront instead of querying per repo These changes address significant performance bottlenecks identified in production logs where simple lookup queries were experiencing multi-second latencies. * cargo fmt * run sqlx prepare --------- Co-authored-by: Solomon <abcpro11051@disroot.org> |
||
Gabriel Gordon-Hall
|
8244308835 | fix compile error (#2019) | ||
Alex Netsch
|
08a466c1d4 |
Fix VSCode extension by restoring /containers/info endpoint (Vibe Kanban) (#1884)
* The code compiles. The fix is complete. Here's a summary of what was changed:
**File: `crates/server/src/routes/containers.rs`**
1. Added `use uuid::Uuid;` import
2. Added `ContainerInfo` struct with `project_id`, `task_id`, and `attempt_id` fields
3. Added `get_container_info` handler that resolves the container reference and maps `workspace_id` → `attempt_id` for VSCode extension compatibility
4. Registered the `/containers/info` route
The VSCode extension can now call `GET /api/containers/info?ref={folder_path}` to auto-detect workspaces when opening a folder.
* Moved the doc comment to the route registration where it's more visible.
* Everything compiles. Let me summarize the logic:
**How the fix works:**
| Scenario | `container_ref` in DB | Path VSCode opens | Lookup method |
|----------|----------------------|-------------------|---------------|
| Multi-repo | `/workspaces/abc123` | `/workspaces/abc123` | Exact match ✓ |
| Single-repo | `/workspaces/abc123` | `/workspaces/abc123/my-repo` | Prefix match ✓ |
The `resolve_container_ref_by_prefix` method:
1. First tries exact match (handles multi-repo case)
2. Falls back to prefix match using SQLite GLOB: `path GLOB container_ref || '/*'` (handles single-repo case where path is a subfolder)
This should handle both cases correctly. The confidence is higher now because we've accounted for how "Open in IDE" behaves differently based on repo count.
* Everything compiles. Now the query handles both:
- Unix paths: `/workspaces/abc123/repo-name` matches `/workspaces/abc123` via `/*`
- Windows paths: `C:\workspaces\abc123\repo-name` matches `C:\workspaces\abc123` via `\*`
* Use std::path for cross-platform parent directory lookup
Instead of doing path prefix matching in SQL (which doesn't handle
Windows backslashes), we now:
1. Try exact match on the path
2. If not found, try the parent directory (handles single-repo case)
This uses std::path::Path::parent() which handles path separators
correctly on all platforms.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
||
|
Gabriel Gordon-Hall
|
7bc8ece068 | workspace file search (#2002) | ||
Louis Knight-Webb
|
82a4e0fccf |
Workspace onboarding (#2013)
* cleanup navbar * re-enable dev server from command bar * Add the ability to open the command bar from the `NavbarContainer.tsx` : (vibe-kanban 58189151) - dots-three-outline icon - position next to settings `vibe-kanban/frontend/src/components/ui-new/containers/NavbarContainer.tsx` * `NavbarContainer.tsx` button to go back to old UI should navigate back to task rather than attempt (vibe-kanban 2b6f4c76) `index.ts` `vibe-kanban/frontend/src/components/ui-new/containers/NavbarContainer.tsx` `vibe-kanban/frontend/src/components/ui-new/actions/index.ts` * Add new setting: beta\_workspaces, and beta\_workspaces\_invitation\_sent (vibe-kanban e2e73cb9) - Stored in the `mod.rs` - This defaults to 'false' - If a user is considered an active user (they have created more than 50 task attempts), they should be proactively invited to join the beta of workspaces - The invite will be displayed as dialog in the old UI, triggered when the user opens the `TaskAttemptPanel.tsx` - The setting can be changed later in the `GeneralSettings.tsx` , right at the bottom in a section for beta features - When the user has beta\_workspaces set to true: - Previously when they open a task in the `TaskKanbanBoard.tsx` it would open a task attempt or task, now it will always open a task - And when clicking on a task attempt in the `TaskPanel.tsx` it will open in the new workspaces view (/workspaces/[WORKSPACE\_ID]) `vibe-kanban/frontend/src/components/panels/TaskAttemptPanel.tsx` `vibe-kanban/frontend/src/pages/settings/GeneralSettings.tsx` `vibe-kanban/crates/services/src/services/config/mod.rs` `vibe-kanban/frontend/src/components/tasks/TaskKanbanBoard.tsx` `vibe-kanban/frontend/src/components/panels/TaskPanel.tsx` * Introduce a way to give feedback (vibe-kanban 463fbf1d) - Icon in `NavbarContainer.tsx` next to settings - Also triggerable from command bar - Using posthog client, already installed `vibe-kanban/frontend/src/components/ui-new/containers/NavbarContainer.tsx` * Create a new dialog that shows when users use workspaces (ui-new) for the first time. It should (vibe-kanban b0e8344a) explain the features of workspaces. The component will consist of a popup with topics in a sidebar on the left and content (text and images) in a main section to the right. It does not use the existing Dialog component. It is accessible by clicking a help icon in the `NavbarContainer.tsx` and from the command bar via `pages.ts` Create the component and some seed content that I will edit: 1. Welcome to workspaces, here are some tips to get started 2. Use the command bar to navigate 3. Create workspaces in the sidebar, also view all your workspaces and the status of each here 4. Workspaces can be created with multiple repos 5. You can create multiple sessions for each workspace 6. Preview changes 7. View diffs, comment on them 8. If any any point you want to go back to the old UI, you can turn off workspaces in settings `vibe-kanban/frontend/src/components/ui-new/containers/NavbarContainer.tsx` `vibe-kanban/frontend/src/components/ui-new/actions/pages.ts` * Update `WorkspacesGuideDialog.tsx` : (vibe-kanban b4c5d731) - Make 600px height - Add new section: Context Bar > The context bar lets you switch between panes quickly. Drag it wherever works best for you. `vibe-kanban/frontend/src/components/ui-new/dialogs/WorkspacesGuideDialog.tsx`  * The `WorkspacesGuideDialog.tsx` appears every time I reload the page, it doesn't seem that we're (vibe-kanban 7fd9e0c8) saving that the user has already seen it once and it should no longer be auto shown `vibe-kanban/frontend/src/components/ui-new/dialogs/WorkspacesGuideDialog.tsx` * Please run `check-i18n.sh` and fix the issue (vibe-kanban d3323397) `vibe-kanban/scripts/check-i18n.sh` |
||
|
Gabriel Gordon-Hall
|
cdfb081cf8 |
feat: copy-file autocomplete (#2004)
* add repo file search endpoint and use for copy-file autocomplete * address feedback and fix i18n errors * remove unused i18n |
||
|
Louis Knight-Webb
|
33419c95f7 |
Improve the preview functionality (vibe-kanban) (#2010)
* preview styles
* All tasks are complete. Let me provide a summary of the changes made:
## Summary
I've implemented the preview functionality improvements as requested:
### Changes Made
**1. Rust Types (`crates/db/src/models/scratch.rs`)**
- Renamed `PreviewUrlOverrideData` → `PreviewSettingsData`
- Added new fields: `screen_size`, `responsive_width`, `responsive_height`
- Updated `ScratchPayload` and `ScratchType` enum to use `PreviewSettings`
**2. New Hook (`frontend/src/hooks/usePreviewSettings.ts`)**
- Created new `usePreviewSettings` hook (replaced `usePreviewUrlOverride`)
- Manages both URL override and screen size settings
- Persists screen size via the scratch system (per-workspace)
- Exports `ScreenSize` and `ResponsiveDimensions` types
**3. PreviewBrowserContainer (`frontend/src/components/ui-new/containers/PreviewBrowserContainer.tsx`)**
- Added URL controls (input, copy, open in new tab, refresh, clear override)
- Added stop button and related handlers
- Added screen size state management
- Added responsive dimensions resize handlers
**4. PreviewBrowser View (`frontend/src/components/ui-new/views/PreviewBrowser.tsx`)**
- Added floating toolbar above the iframe with:
- URL input with action buttons
- Screen size toggle (Desktop/Mobile/Responsive icons)
- Dimensions display for responsive mode
- Stop button
- Implemented three screen modes:
- **Desktop**: Full width/height (current behavior)
- **Mobile**: 390×844px centered with shadow
- **Responsive**: Draggable resize handles on right, bottom, and corner edges
**5. PreviewControls View (`frontend/src/components/ui-new/views/PreviewControls.tsx`)**
- Simplified to show only logs
- Removed URL input row and all control buttons
- Renamed section header to "Dev Server Logs"
**6. PreviewControlsContainer (`frontend/src/components/ui-new/containers/PreviewControlsContainer.tsx`)**
- Removed all URL-related state and handlers
- Now only manages logs display and process tab switching
All type checks pass. The screen size preference is persisted per-workspace using the existing scratch system.
* Cleanup script changes for workspace dd65dbe3-2e31-4897-8aa4-b2f8f7971ab7
* All ESLint and TypeScript checks pass. The implementation is complete.
## Summary of Changes
**Files Modified:**
1. **`crates/db/src/models/scratch.rs`** - Renamed `PreviewUrlOverrideData` → `PreviewSettingsData` with new fields for screen size persistence
2. **`crates/server/src/bin/generate_types.rs`** - Updated type export to use new name
3. **`shared/types.ts`** - Regenerated with new types (`PreviewSettingsData`, `ScratchType.PREVIEW_SETTINGS`)
4. **`frontend/src/hooks/usePreviewSettings.ts`** (new) - Replaces `usePreviewUrlOverride.ts`, adds screen size management
5. **`frontend/src/hooks/usePreviewUrlOverride.ts`** - Deleted
6. **`frontend/src/components/ui-new/containers/PreviewBrowserContainer.tsx`** - Added URL controls, stop button, and resize state management
7. **`frontend/src/components/ui-new/views/PreviewBrowser.tsx`** - Added floating toolbar with:
- URL input with copy/open/refresh/clear buttons
- Screen size toggle (Desktop/Mobile/Responsive icons)
- Responsive resize handles
- Stop button
8. **`frontend/src/components/ui-new/containers/PreviewControlsContainer.tsx`** - Simplified to logs only
9. **`frontend/src/components/ui-new/views/PreviewControls.tsx`** - Simplified to logs only
* Cleanup script changes for workspace dd65dbe3-2e31-4897-8aa4-b2f8f7971ab7
* All checks pass. Here's a summary of the changes made:
## Summary of Changes
### 1. Fixed infinite loop bug (`usePreviewSettings.ts`)
- Added `useMemo` to stabilize the `responsiveDimensions` object reference
- This prevents the useEffect in the container from re-triggering on every render
### 2. Updated toolbar to always show with floating style (`PreviewBrowser.tsx`)
- Toolbar is now always visible (not conditional on `isServerRunning && hasUrl`)
- Changed styling from `border-b border-border` to `rounded-md shadow-md m-base` for a floating appearance
- URL input and action buttons are disabled (with `opacity-50 cursor-not-allowed`) when no URL is available
- Start/Stop button in toolbar changes based on server state:
- Shows "Start" button when server is not running
- Shows "Stop" button when server is running
- Simplified the empty state content area to just show a message pointing to the toolbar's Start button
* All checks pass. The fix:
1. **Changed from state to refs** for `isResizing` and `resizeDirection` - these now don't trigger re-renders when they change
2. **Added `localDimensionsRef`** to capture the current dimensions for the `handleEnd` callback without adding it to the effect's dependency array
3. **Effect now only depends on `setResponsiveDimensions`** (a stable callback), so event listeners are registered once on mount and cleaned up on unmount
4. **No more race conditions** - the same event handlers persist throughout the entire drag operation
The resize should now:
- Stop immediately when you release the mouse
- Be smooth without choppiness (no effect re-runs during drag)
* The responsive resize fix is complete. Here's a summary of the changes made:
**In `PreviewBrowserContainer.tsx`:**
1. Added `isResizing` state to track when resizing is active (for UI purposes)
2. Added `setResponsiveDimensionsRef` to store the callback in a ref, preventing the resize effect from re-running when the callback identity changes
3. Changed the resize effect to use an empty dependency array (`[]`) since all external values are now accessed via refs
4. Updated `handleResizeStart` to set `isResizing(true)`
5. Updated `handleEnd` to set `isResizing(false)` and use `setResponsiveDimensionsRef.current`
6. Passed `isResizing` prop to the `PreviewBrowser` view
**In `PreviewBrowser.tsx`:**
1. Added `isResizing` prop to the interface and destructured it
2. Applied `pointer-events-none` class to the iframe when `isResizing` is true - this prevents the iframe from capturing mouse events during resize, ensuring smooth dragging
These changes fix both issues:
- **Resize not stopping**: The effect no longer re-registers listeners when `setResponsiveDimensions` changes
- **Choppy dragging**: The iframe no longer captures mouse events during resize
* All checks pass. The fix is complete. The resize now uses delta-based calculation:
1. **`startPosRef`**: Captures the mouse position when resize starts
2. **`startDimensionsRef`**: Captures the iframe dimensions when resize starts
3. **`handleMove`**: Calculates delta (current position - start position) and applies it to the starting dimensions
4. **`handleEnd`**: Clears both refs when resize ends
This approach works regardless of where the iframe is positioned in the container, fixing both:
- The mouse jump offset (no longer tries to position based on container edge)
- The 50% distance issue (delta is 1:1 with mouse movement)
* Cleanup script changes for workspace dd65dbe3-2e31-4897-8aa4-b2f8f7971ab7
* Done. The resize should now move at 1:1 with the cursor. Since the centered element grows on both sides equally, doubling the delta ensures the edge under the cursor moves the full distance you drag.
* Done! I've added a minimal dark phone frame around the iframe when in mobile mode. The changes:
- **Mobile mode** now wraps the iframe in a phone skeleton with:
- Dark bezel (`bg-gray-900`)
- Rounded outer corners (`rounded-[3rem]`)
- Padding for bezel width (`p-3`)
- Shadow (`shadow-xl`)
- Rounded inner screen area (`rounded-[2.5rem]`)
- **Desktop and responsive modes** remain unchanged
You can test it by running `pnpm run dev:qa` and switching to mobile view in the preview browser.
* styles
* I've completed the implementation. Here's a summary of the changes:
## Summary
Created two new reusable button components and updated PreviewBrowser.tsx to standardize button styles:
### New Components
1. **`IconButton.tsx`** (`frontend/src/components/ui-new/primitives/IconButton.tsx`)
- Standalone icon button with consistent styling
- Supports `default` and `tertiary` variants
- Includes proper hover states (`bg-secondary/50`), disabled states, and transitions
2. **`IconButtonGroup.tsx`** (`frontend/src/components/ui-new/primitives/IconButtonGroup.tsx`)
- Container component for grouped icon buttons with shared border
- `IconButtonGroupItem` for individual buttons with `active` state support
- Consistent styling with border, padding, and hover/active states
### Updated PreviewBrowser.tsx
- **URL action buttons** (Clear, Copy, Open in new tab, Refresh): Now use `IconButton` component with consistent hover backgrounds
- **Screen size toggle** (Desktop, Mobile, Responsive): Now uses `IconButtonGroup` and `IconButtonGroupItem` with proper active state styling
- **Start/Stop button**: Kept using `PrimaryButton` (already consistent)
### Visual Consistency Achieved
All toolbar buttons now share:
- Consistent padding (`p-half`)
- Consistent hover states (`bg-secondary/50` background)
- Consistent active states (`bg-secondary` background) for toggles
- Consistent disabled states (`opacity-40 cursor-not-allowed`)
- Consistent icon sizing (`size-icon-sm`) with `weight="bold"`
- Consistent border radius (`rounded-sm`)
* Done. The URL action buttons (Copy, Open in new tab, Refresh) are now grouped in an `IconButtonGroup` with a shared border, matching the visual style of the screen size toggle group.
The toolbar now has three visually consistent button groups:
1. **URL input** with optional clear override button
2. **URL actions group** (Copy, Open in new tab, Refresh) - bordered group
3. **Screen size toggle group** (Desktop, Mobile, Responsive) - bordered group
4. **Start/Stop button** (PrimaryButton)
* Done. All changes have been implemented:
1. **Added `iconClassName` prop to `IconButtonGroupItem`** - Supports passing custom classes to the icon (e.g., `animate-spin` for the spinner)
2. **Moved Clear button into URL Actions group** - The Clear Override button (X icon) is now inside the `IconButtonGroup` with Copy, Open, and Refresh buttons
3. **Replaced Pause button with `IconButtonGroupItem`** - The stop/pause button now uses the same `IconButtonGroup` styling as the other toolbar buttons, with spinner animation support when stopping
The toolbar now has consistent visual styling with three button groups:
- **URL Actions**: Clear (conditional), Copy, Open in new tab, Refresh
- **Screen Size Toggle**: Desktop, Mobile, Responsive
- **Stop button**: Pause icon (when server is running)
- **Start button**: Kept as `PrimaryButton` since it has a text label
* Cleanup script changes for workspace dd65dbe3-2e31-4897-8aa4-b2f8f7971ab7
* Done. The Start/Stop button is now a single `IconButtonGroup` with one `IconButtonGroupItem` that:
- Shows Play icon when server is stopped, Pause icon when running
- Shows Spinner icon with animation when starting or stopping
- Has the same size as all other toolbar button groups
* Cleanup script changes for workspace dd65dbe3-2e31-4897-8aa4-b2f8f7971ab7
* Done. Fixed the spinning Play icon bug by making the `iconClassName` logic match the icon selection logic exactly. Now `animate-spin` is only applied when actually showing the `SpinnerIcon`.
* Done. The entire toolbar (URL input, URL actions, screen size toggle) is now disabled when the dev server isn't running. Only the Play/Start button remains enabled so users can start the server.
* The changes compile correctly. Here's a summary of what was fixed:
## Summary
Fixed the "Fix Script" button showing at the wrong time in `PreviewBrowser.tsx`.
**Changes made:**
1. **`PreviewBrowser.tsx`** - Added `hasFailedDevServer?: boolean` prop and updated the condition on line 345 from `{handleFixDevScript && (` to `{hasFailedDevServer && handleFixDevScript && (`
2. **`PreviewBrowserContainer.tsx`** - Added failed dev server detection logic (lines 45-51) that checks for processes with `status === 'failed'` or `status === 'completed'` with non-zero exit code, and passed the `hasFailedDevServer` prop to the view
The "Fix Script" button will now only appear when the last dev server process actually failed, not when it was successful or killed.
* update styles
* All tasks completed. Here's a summary of the changes made:
## Summary
### 1. `IconButtonGroup.tsx` (lines 3, 50-65)
- Added import for `Tooltip` component
- Modified `IconButtonGroupItem` to wrap buttons with `<Tooltip>` when `title` prop is provided
- Removed native `title` attribute from button (tooltip handles it now)
### 2. `en/tasks.json` (lines 125-134)
Added new i18n keys under `preview.toolbar`:
- `clearUrlOverride`: "Clear URL override"
- `desktopView`: "Desktop view"
- `mobileView`: "Mobile view (390x844)"
- `responsiveView`: "Responsive view (resizable)"
- `startDevServer`: "Start dev server"
Added new `preview.loading` section:
- `startingServer`: "Starting dev server..."
- `waitingForServer`: "Waiting for server..."
### 3. `PreviewBrowser.tsx` (lines 160-254, 342-344)
Replaced all hardcoded strings with i18n translations using `t()`:
- URL action buttons (clear override, copy, open in tab, refresh)
- Screen size toggle buttons (desktop, mobile, responsive)
- Start/stop server button
- Loading state messages
All icon buttons now have proper accessible tooltips via the `Tooltip` component instead of native browser `title` attributes, and all strings are internationalized.
* style
* All i18n issues have been fixed. Here's a summary of the changes made:
**1. Added missing translation keys to all non-English locales (es, ja, ko, zh-Hans, zh-Hant):**
- `preview.loading.startingServer`
- `preview.loading.waitingForServer`
- `preview.toolbar.clearUrlOverride`
- `preview.toolbar.desktopView`
- `preview.toolbar.mobileView`
- `preview.toolbar.responsiveView`
- `preview.toolbar.startDevServer`
**2. Fixed hardcoded strings in `PreviewBrowser.tsx`:**
- Replaced dimension separator `x` with HTML entity `×`
- Internationalized the "no dev script" setup message with 3 new i18n keys:
- `preview.noServer.setupTitle`
- `preview.noServer.editDevScript`
- `preview.noServer.learnMore`
**3. Added the 3 new keys to all locale files (en, es, ja, ko, zh-Hans, zh-Hant)**
The `check-i18n.sh` script now passes with:
- 128 violations (down from 131 on main - a net improvement!)
- No duplicate keys
- Translation keys consistent across all locales
|
||
|
Louis Knight-Webb
|
c7cf72a57f |
Allow manual URL override in dev server preview (Vibe Kanban) (#1989)
* The implementation is complete and tested. Here's a summary of the changes made: I've implemented an editable URL bar in the Preview Controls that allows users to override the auto-detected dev server URL on a per-workspace basis. | File | Changes | |------|---------| | `crates/db/src/models/scratch.rs` | Added `PreviewUrlOverrideData` struct and `PreviewUrlOverride` variant to `ScratchPayload` enum | | `crates/server/src/bin/generate_types.rs` | Registered `PreviewUrlOverrideData::decl()` for TypeScript type generation | | `shared/types.ts` | Auto-generated with new `PreviewUrlOverrideData` type and updated `ScratchPayload` union | | `frontend/src/hooks/usePreviewUrlOverride.ts` | **New file** - Custom hook for managing URL override persistence via scratch system | | `frontend/src/components/ui-new/containers/PreviewControlsContainer.tsx` | Added URL override hook integration, merged auto-detected with override URL | | `frontend/src/components/ui-new/views/PreviewControls.tsx` | Replaced static `<span>` with editable `<input>`, added clear override button (X icon) | - **Editable URL bar**: Users can type a custom URL to override the auto-detected one - **Per-workspace persistence**: Override URL saved in the scratch system using workspace ID - **Debounced saves**: Changes are debounced (300ms) before saving to avoid excessive API calls - **Clear override button**: X button appears when override is active, allowing revert to auto-detected URL - **Visual distinction**: Override URLs show in normal text color, auto-detected in dim text * Cleanup script changes for workspace 3f3c315d-5cc2-43b0-9043-117c857f38b4 * The URL input fix is complete. Here's a summary of what was implemented: **Feature: Editable URL bar with per-workspace persistence** 1. **New scratch type** - Added `PreviewUrlOverride` to the Rust scratch system for persisting URL overrides per workspace 2. **New hook** - Created `usePreviewUrlOverride.ts` that wraps the scratch system with debounced saves (300ms delay) 3. **Container integration** - Updated `PreviewControlsContainer.tsx` to use the override URL when set, falling back to auto-detected URL 4. **View updates** - Updated `PreviewControls.tsx` with: - Editable input field instead of read-only display - Clear button (X icon) to revert to auto-detected URL - Local state management to prevent WebSocket updates from disrupting typing **Bug fix for typing issue:** - Added local state (`localValue`) and ref (`inputRef`) to track input value locally - The effect only syncs from server when input is not focused, preventing cursor jumping and character loss during typing * ESLint and Clippy both pass now. The fix moved the state management from the presentational view component (`PreviewControls.tsx`) to the container component (`PreviewControlsContainer.tsx`), which aligns with the codebase's architecture pattern of keeping views stateless. * I can see projects now. Let me click on the first project to access a workspace where I can test the URL override feature: * TypeScript check passes now. The fix was changing `RefObject<HTMLInputElement | null>` to `RefObject<HTMLInputElement>` in the props interface - the `null` is already implied in how React refs work. |
||
|
Alex Netsch
|
20b99300fe |
Add session-level review endpoint with StartReviewDialog (Vibe Kanban) (#1849)
* All checks pass. Let me provide a summary of what was implemented:
I've implemented the review endpoint as planned. Here's what was created:
1. **`crates/executors/src/actions/review.rs`** - New action type with:
- `RepoReviewContext` struct (repo_id + commit_hashes)
- `ReviewRequest` struct (executor_profile_id, context, additional_prompt, working_dir)
- `Executable` trait impl that calls `executor.spawn_review()`
2. **`crates/server/src/routes/task_attempts/review.rs`** - Endpoint handler with:
- `StartReviewRequest` for the API
- `RepoReviewContext` (endpoint-specific copy)
- `ReviewError::ProcessAlreadyRunning`
- `start_review` handler that:
- Verifies no running processes on workspace
- Creates fresh session
- Builds ReviewRequest action
- Starts execution with `ExecutionProcessRunReason::CodingAgent`
1. **`crates/executors/src/executors/mod.rs`**:
- Added `spawn_review()` to `StandardCodingAgentExecutor` trait with default prompt-based implementation
- Added `build_review_prompt()` helper function
2. **`crates/executors/src/actions/mod.rs`**:
- Added `pub mod review;`
- Added `ReviewRequest` to `ExecutorActionType` enum
- Updated `base_executor()` match
3. **`crates/services/src/services/container.rs`**:
- Updated match in `try_start_next_action` to handle `ReviewRequest`
4. **`crates/server/src/routes/task_attempts.rs`**:
- Added `pub mod review;`
- Added `.route("/review", post(review::start_review))`
5. **`crates/server/src/bin/generate_types.rs`**:
- Added new types to export list
**`POST /task-attempts/{id}/review`**
Request:
```json
{
"executor_profile_id": { "executor": "CLAUDE_CODE", "variant": null },
"context": [{ "repo_id": "uuid", "commit_hashes": ["abc123"] }],
"additional_prompt": "Focus on security issues"
}
```
Response: `ExecutionProcess` on success, `ReviewError` on failure.
To add native review for an executor (e.g., Codex), just override `spawn_review()` in that executor's `StandardCodingAgentExecutor` impl. No changes needed to action or endpoint.
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
All checks pass now. The duplicate type issue is fixed - we're using a single `RepoReviewContext` type from the executors crate.
All checks pass now. Both frontend lint (ESLint) and backend lint (Clippy) are passing.
Found and fixed the real issue. The problem was in `crates/services/src/services/container.rs` - the log normalization was only set up for `CodingAgentInitialRequest` and `CodingAgentFollowUpRequest`. `ReviewRequest` was falling through to the default case and returning `None`, so no normalizer was started for review processes.
Fixed in two places:
1. **Line 787-791**: Added `ReviewRequest` handling in `stream_normalized_logs` (for historic logs)
2. **Line 1149-1151**: Added `ReviewRequest` handling in `start_execution` (for live logs)
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Backend changes for the `use_all_workspace_commits` flag are complete. Here's what was implemented:
Added `use_all_workspace_commits` flag to `StartReviewRequest` for automatically populating review context.
1. **`crates/db/src/models/execution_process_repo_state.rs`**
- Added `find_initial_commits_for_workspace()` - query to get the earliest `before_head_commit` for each repo in a workspace
2. **`crates/server/src/routes/task_attempts/review.rs`**
- Added `use_all_workspace_commits: bool` field to `StartReviewRequest` (defaults to `false`)
- When flag is `true` and `context` is `None`, auto-populates context with initial commits from workspace execution processes
3. **`crates/executors/src/executors/mod.rs`**
- Updated `build_review_prompt()` to detect single-commit context (indicating initial commit)
- When single commit per repo, prompts agent to "Review all changes made since the following base commit(s)" with git diff hint
4. **`crates/services/src/services/git.rs`**
- Added `get_commits_since_branch()` method (may be useful for future use)
5. **`shared/types.ts`**
- Generated TypeScript type includes `use_all_workspace_commits: boolean`
When frontend calls `POST /task-attempts/{id}/review` with:
```json
{
"executor_profile_id": { "executor": "CLAUDE_CODE", "variant": null },
"use_all_workspace_commits": true
}
```
The backend will:
1. Find the earliest execution process for the workspace
2. Get the `before_head_commit` for each repo (the commit before agents started making changes)
3. Pass that to the prompt builder which tells the agent to review all changes since that commit
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Frontend UI implementation is complete. Here's a summary of what was added:
Added simple frontend UI to test the review endpoint.
1. **`frontend/src/lib/api.ts`**
- Added `startReview` method to `attemptsApi`
- Imports `StartReviewRequest`, `ReviewError` types
2. **`frontend/src/hooks/useStartReview.ts`** (NEW)
- Hook that calls `attemptsApi.startReview` with `use_all_workspace_commits: true`
- Invalidates `processes` and `branchStatus` queries on success
3. **`frontend/src/hooks/index.ts`**
- Exports `useStartReview`
4. **`frontend/src/components/ui/actions-dropdown.tsx`**
- Added "Start Review" menu item in the attempt actions section
- Uses the user's default executor profile from config
- Shows loading state while starting review
5. **`frontend/src/i18n/locales/en/tasks.json`**
- Added translation keys: `startReview`, `startingReview`
From the workspace actions dropdown (three dots menu), click "Start Review" to start a code review session using all workspace commits as context.
Done! The fix has been implemented. The review endpoint now uses `Session::find_latest_by_workspace_id` to find an existing session for the workspace, and only creates a new session if none exists. This means review logs will now appear in the same conversation view as other coding agent runs.
**Change summary:**
- Modified `crates/server/src/routes/task_attempts/review.rs` (lines 79-93)
- Instead of always creating a new session, it now checks for an existing session first using `Session::find_latest_by_workspace_id`
- This matches the pattern used by dev server, setup scripts, and other similar endpoints
Done! The fix is now in place. The change adds `ReviewRequest` to the action type filter in `useConversationHistory.ts` so review processes are included in the conversation view, and handles the content extraction appropriately (using `additional_prompt` for reviews instead of `prompt`).
**Change summary:**
- Modified `frontend/src/hooks/useConversationHistory.ts` (lines 226-244)
- Added `ReviewRequest` to the action type filter
- Used conditional to extract content from `additional_prompt` for reviews (with fallback "Review the code changes") vs `prompt` for coding agent requests
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
Done! All fixes are now in place:
1. **`useConversationHistory.ts` - `flattenEntries()`** (line 177-184): Added `ReviewRequest` to the filter so review processes are included in the flattened entries
2. **`useConversationHistory.ts` - `flattenEntriesForEmit()`** (line 226-244): Already fixed earlier - handles `ReviewRequest` and extracts `additional_prompt` for user message content
3. **`ProcessesTab.tsx`** (line 223-228): Added `ReviewRequest` to the ProfileVariantBadge conditional so the agent badge shows for review processes
* Done. Changes made:
1. **`crates/executors/src/actions/review.rs`**: Added `prompt: String` field to `ReviewRequest`
2. **`crates/server/src/routes/task_attempts/review.rs`**:
- Import `build_review_prompt`
- Build the full prompt from context and additional_prompt before creating the action
3. **`frontend/src/hooks/useConversationHistory.ts`**: Simplified content extraction to just use `actionType.prompt` for all action types (since `ReviewRequest` now has a prompt field too)
4. **Regenerated TypeScript types** - `ReviewRequest` in `shared/types.ts` now includes the `prompt` field
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Done. Here's a summary of the changes:
**Backend:**
1. **`crates/executors/src/actions/review.rs`**:
- Added `CommitRange` enum with three variants: `FromBase`, `Specific`, and `Range`
- Updated `RepoReviewContext` to use `repo_name: String` and `commits: CommitRange` instead of `commit_hashes`
2. **`crates/executors/src/executors/mod.rs`**:
- Updated `build_review_prompt` to format output with repo names and handle all `CommitRange` variants
3. **`crates/server/src/routes/task_attempts/review.rs`**:
- Simplified `StartReviewRequest` (removed `context` field, kept `use_all_workspace_commits`)
- Updated handler to look up repo names via `Repo::find_by_ids` and use `CommitRange::FromBase`
4. **`crates/server/src/bin/generate_types.rs`**: Added `CommitRange` to exported types
**Frontend:**
- **`frontend/src/hooks/useStartReview.ts`**: Removed `context: null` since that field no longer exists
The prompt will now look like:
```
Please review the code changes.
Repository: vibe-kanban
Review all changes from base commit abc123 to HEAD.
Use `git diff abc123..HEAD` to see the changes.
```
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Codex review support (vibe-kanban e7996a18)
## Context
We've added a review endpoint (\`POST /task-attempts/{id}/review\`) that starts a code review session. Currently it uses a default prompt-based implementation via \`spawn\_review()\` on \`StandardCodingAgentExecutor\`, which builds a prompt and delegates to \`spawn()\`.
## Goal
Implement native Codex review support by overriding \`spawn\_review()\` in the Codex executor to use Codex's native review mechanism instead of the prompt-based approach.
## Current Implementation
### Backend Types
\*\*\`CommitRange\` enum\*\* (\`crates/executors/src/actions/review.rs\`):
\`\`\`rust
pub enum CommitRange {
FromBase { commit: String },
Specific { commits: Vec<String> },
Range { from: String, to: String },
}
\`\`\`
\*\*\`RepoReviewContext\`\*\*:
\`\`\`rust
pub struct RepoReviewContext {
pub repo\_id: Uuid,
pub repo\_name: String,
pub commits: CommitRange,
}
\`\`\`
### Trait Method
\*\*\`spawn\_review()\`\*\* in \`StandardCodingAgentExecutor\` trait (\`crates/executors/src/executors/mod.rs\`):
\`\`\`rust
async fn spawn\_review(
&self,
current\_dir: &Path,
context: Option<&[RepoReviewContext]>,
additional\_prompt: Option<&str>,
env: &ExecutionEnv,
) -> Result<SpawnedChild, ExecutorError> {
// Default: build prompt and delegate to spawn()
let prompt = build\_review\_prompt(context, additional\_prompt);
self.spawn(current\_dir, &prompt, env).await
}
\`\`\`
## Tasks
1. Research Codex's native review API/mechanism (if it has one)
2. Override \`spawn\_review()\` in \`CodexExecutor\` to use native review if available
3. Fall back to prompt-based approach if native review isn't supported
* Done. Here's a summary of the changes:
1. **Removed dead code** from `crates/executors/src/executors/codex/review.rs`:
- Deleted the `map_to_review_target()` function (was ~120 lines)
- Removed unused imports (`CommitRange`, `RepoReviewContext`)
2. **Codex now uses `ReviewTarget::Custom`** with the pre-built prompt, which ensures the displayed prompt matches what Codex actually receives.
The build passes and TypeScript types have been regenerated.
* Use custom review target for codex
* Done. Here's a summary of the changes:
## Summary
Moved the review endpoint from workspace-level to session-level:
### Changes
1. **Created `crates/server/src/routes/sessions/review.rs`**
- New review endpoint at `POST /sessions/{id}/review`
- Takes `Extension<Session>` instead of `Extension<Workspace>`
- Looks up `agent_session_id` from previous executions using `find_latest_coding_agent_turn_session_id()`
- Passes `agent_session_id` to `ReviewAction` for session resumption
2. **Updated `crates/server/src/routes/sessions/mod.rs`**
- Added `pub mod review;`
- Added route `.route("/review", post(review::start_review))`
3. **Updated `crates/server/src/routes/task_attempts.rs`**
- Removed `pub mod review;`
- Removed `.route("/review", post(review::start_review))`
4. **Deleted `crates/server/src/routes/task_attempts/review.rs`**
5. **Updated `crates/server/src/bin/generate_types.rs`**
- Changed path from `task_attempts::review` to `sessions::review`
### API Change
- **Old**: `POST /api/task-attempts/{workspace_id}/review`
- **New**: `POST /api/sessions/{session_id}/review`
This ensures vk sessions and agent sessions are 1:1:
- Existing session → resumes agent session if available
- New session → fresh agent session
* Done! Here's a summary of all the frontend changes:
- Added `startReview` to `sessionsApi` using new endpoint `POST /api/sessions/${sessionId}/review`
- Removed `startReview` from `attemptsApi`
- Changed parameter from `attemptId` to `sessionId` and added optional `workspaceId` for query invalidation
- Changed API call from `attemptsApi.startReview` to `sessionsApi.startReview`
- Added `MagnifyingGlassIcon` import
- Added `onStartReview` and `isReviewStarting` to `SessionProps` interface
- Added "Start Review" menu item in the session dropdown
- Added `useStartReview` hook import and usage
- Added `handleStartReview` callback function
- Passed `onStartReview` and `isReviewStarting` to `SessionChatBox`
- Removed `useStartReview` import
- Removed `useUserSystem` import (now unused)
- Removed `startReview` hook usage
- Removed `handleStartReview` function
- Removed "Start Review" menu item from the dropdown
* Done. The fix adds the `ReviewRequest` case to `latest_executor_profile_for_session()` in `crates/db/src/models/execution_process.rs:688-690`.
The backend check passes. Follow-ups after reviews should now work correctly since the executor profile can be extracted from `ReviewRequest` just like from the other request types.
* Done. Removed `CommitRange` enum entirely. Changes:
1. **`crates/executors/src/actions/review.rs`** - Deleted `CommitRange` enum, changed `RepoReviewContext.commits` to `RepoReviewContext.base_commit: String`
2. **`crates/server/src/routes/sessions/review.rs`** - Updated construction to use `base_commit: initial_commit` instead of `commits: CommitRange::FromBase { commit: initial_commit }`
3. **`crates/executors/src/executors/mod.rs`** - Simplified `build_review_prompt()` to directly use `repo.base_commit` instead of matching on the enum
4. **`crates/server/src/bin/generate_types.rs`** - Removed `CommitRange::decl()` from type exports
5. **`shared/types.ts`** - Regenerated, `CommitRange` type is now gone
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Done. Simplified the review context building:
**Changes:**
1. **`crates/db/src/models/execution_process_repo_state.rs`** - Replaced `find_initial_commits_for_workspace` with `find_initial_commit_for_repo` that takes a specific repo_id and uses ORDER BY + LIMIT 1 instead of GROUP BY/HAVING.
2. **`crates/server/src/routes/sessions/review.rs`** - Simplified the context building:
- Get workspace repos first (has repo names via `display_name`)
- For each repo, get initial commit
- Build context directly - no more HashMap joining, no more separate `Repo::find_by_ids` call
The new code is much easier to follow: get repos → for each, get initial commit → build context.
* Done. Addressed all 23 review comments:
1. Removed comment from `SessionChatBoxContainer.tsx` (line 161)
2. Removed doc comments from `RepoReviewContext` and `ReviewRequest` structs in `review.rs`
3. Removed module doc comment from `codex/review.rs`
4. Removed comment from `codex.rs` about Custom review target
5. Removed doc comments from `spawn_review` trait method in `mod.rs`
6. Removed doc comment from `build_review_prompt` function
7. Removed all comments from `sessions/review.rs` (doc comments and inline comments)
8. Removed unused `get_commits_since_branch` function from `git.rs` (~45 lines of dead code)
* Done. Added the review toggle button:
**Changes:**
1. **`SessionChatBox.tsx`**
- Added `ReviewModeProps` interface with `isActive`, `onToggle`, `isSubmitting`
- Added `reviewMode` prop to `SessionChatBoxProps`
- Added toggle button next to attach button (MagnifyingGlassIcon) - highlighted when active
- Updated placeholder to show "Enter review instructions..." when in review mode
- Removed old `onStartReview` and `isReviewStarting` from SessionProps
- Removed "Start Review" dropdown menu item
2. **`SessionChatBoxContainer.tsx`**
- Added `useState` for `isReviewMode`
- Updated `handleSend` to call `startReviewMutation` with `additionalPrompt` when in review mode
- Reset review mode after successful review start
- Pass `reviewMode` props to SessionChatBox
- Removed old `handleStartReview` callback
Now the user can:
1. Click the magnifying glass toggle next to attach
2. Enter review instructions in the text area
3. Click send → starts review with the prompt
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
TypeScript and Rust both compile. The changes are:
1. Button shows "Review" when review mode is active
2. Toggle icon uses `!text-accent-foreground` to force override the `text-low` class from the base component, along with `bg-accent rounded-sm` for the background highlight
Done. Changed `!text-accent-foreground` to `!text-normal` which uses the design system's proper text color for active/selected states. The `!` prefix forces the override of the base `text-low` class. Both TypeScript and Rust compile successfully.
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
All done. TypeScript and Rust compile successfully. Here's a summary of the changes:
**Created:**
- `frontend/src/components/dialogs/tasks/StartReviewDialog.tsx` - New dialog with:
- Agent/variant selection (using ExecutorProfileSelector)
- Review comments preview (if any)
- Additional instructions textarea
- Start Review / Cancel buttons
**Modified:**
- `frontend/src/components/dialogs/index.ts` - Added export for StartReviewDialog
- `frontend/src/components/ui-new/primitives/SessionChatBox.tsx`:
- Changed `ReviewModeProps` from toggle state to simple callback (`onReviewClick`, `isDisabled`)
- Removed toggle styling and review mode button text
- Button now just opens the dialog
- `frontend/src/components/ui-new/containers/SessionChatBoxContainer.tsx`:
- Removed `isReviewMode` state and `startReviewMutation`
- Added `handleReviewClick` callback that opens `StartReviewDialog`
- Disabled review button when in new session mode or no session exists
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
Done. TypeScript and Rust compile successfully. Summary of changes:
**`StartReviewDialog.tsx`:**
- Added "New Session" toggle (defaults ON when no session exists, disabled when no session to toggle from)
- Added conditional `AgentSelector` - only shown when creating a new session
- Always shows `ConfigSelector` for variant selection
- Handles session creation inline when toggle is on or no session exists
- Updated `onSuccess` callback to return new session ID when created
**`SessionChatBox.tsx`:**
- Removed `isDisabled` from `ReviewModeProps` interface
- Removed `reviewMode.isDisabled` from button disabled logic
**`SessionChatBoxContainer.tsx`:**
- Updated `handleReviewClick` to allow opening dialog without sessionId
- Updated `onSuccess` callback to select the new session if one was created
- Removed `isDisabled` from reviewMode prop
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
Done. Made `reviewMode` required and removed the conditional - the review button is now always shown.
Done. Now the StartReviewDialog:
- Shows `ExecutorProfileSelector` (Agent + Configuration side by side, like CreateAttemptDialog) when "New Session" toggle is ON
- Shows just `ConfigSelector` (variant only) when "New Session" toggle is OFF
TypeScript and Rust compile successfully. The Switch layout has been fixed to match the TaskFormDialog pattern:
- Switch is now on the LEFT of the label
- Uses `gap-2` instead of `justify-between`
- Has proper dark mode styling with `data-[state=checked]:bg-gray-900 dark:data-[state=checked]:bg-gray-100`
- Label has `cursor-pointer` for better UX
Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
Done. The Switch is now moved to the footer (bottom of the dialog), matching the TaskFormDialog pattern:
- Switch on the left side of the footer
- Cancel and Start Review buttons on the right side
- Added `disabled:opacity-50` for better visibility when disabled in dark mode
Done. All changes complete:
1. **Removed header** - No more "Start Review" title or description
2. **Removed labels from selectors** - `showLabel={false}` for both `ExecutorProfileSelector` and `ConfigSelector`
3. **Fixed footer layout** - Cancel button on left, Switch + "New Session" + "Start Review" button grouped on right (matching TaskFormDialog)
4. **TypeScript compiles** - Both frontend and backend checks pass
Done. Changes made:
1. **Moved selector to bottom** - Now the order is: Additional Instructions textarea → Review comments preview → Error → Profile/Config selector → Footer
2. **Fixed Switch visibility** - Changed from `data-[state=checked]:bg-gray-900 dark:data-[state=checked]:bg-gray-100` to `bg-muted-foreground/30 data-[state=checked]:bg-foreground` using semantic colors
3. **TypeScript compiles** - Both frontend and backend checks pass
Done. The Switch className now uses `!` important modifiers to override the component's hardcoded background colors:
- `!bg-muted-foreground/30` - visible gray background when unchecked (overrides `bg-input`)
- `data-[state=checked]:!bg-foreground` - foreground color when checked (overrides `bg-foreground`)
Done. Changed the Switch className to use `!bg-muted` which should provide better contrast against the dialog's `bg-primary` background.
Done. Changed the Switch className to use `!bg-border` which should provide some contrast against the dialog's `bg-primary` background (25% lightness vs 18% lightness).
* Fix duplicate routes
* I've analyzed the problem. Here's my understanding:
**The issue:** After rebasing, stored commit SHAs (`after_head_commit`) become invalid because rebasing rewrites history with new SHAs.
**Your suggestion (`git diff A^..B`):** This still has the same problem - after rebase, commit `A` doesn't exist with that SHA anymore. `A^` requires resolving commit `A` first.
**My recommended fix:** Instead of using stored commit SHAs, use the **branch name** as the base:
- `git diff {target_branch}..HEAD` instead of `git diff {commit_sha}..HEAD`
- This is always valid regardless of rebasing
- Matches user intent: "show all changes on this workspace branch vs base"
This would require changes to:
1. `review.rs` - use `workspace.target_branch` instead of querying `find_first_commit_for_repo`
2. `build_review_prompt` - update to use branch name
3. `RepoReviewContext` - change `base_commit` to `base_branch`
**Questions:**
1. Is using `target_branch` the right base? Or do you need something more granular like "changes since session X"?
2. Should we keep `before_head_commit`/`after_head_commit` for per-execution tracking, or simplify?
* Done. Here's a summary of the changes:
## Changes Made
### 1. `crates/services/src/services/git/cli.rs`
- Made `merge_base` method public (was `fn`, now `pub fn`)
### 2. `crates/services/src/services/git.rs`
- Added new public method `get_fork_point()` that wraps the CLI `merge_base` function
- This method uses `git merge-base --fork-point` which survives rebasing by consulting the reflog
### 3. `crates/server/src/routes/sessions/review.rs`
- Removed import of `ExecutionProcessRepoState` (no longer needed)
- Added `PathBuf` import
- Changed from querying stored `after_head_commit` SHAs to computing fork-point dynamically
- Now uses `WorkspaceRepo::find_repos_with_target_branch_for_workspace` to get per-repo target branches
- Computes `get_fork_point(repo_path, target_branch, workspace.branch)` for each repo
## How It Works Now
Instead of storing commit SHAs that become invalid after rebasing:
```rust
// Old (broken after rebase):
let base_commit = ExecutionProcessRepoState::find_first_commit_for_repo(...)
```
We now compute the fork-point dynamically:
```rust
// New (survives rebasing):
let base_commit = deployment.git().get_fork_point(
&repo_path,
&repo.target_branch, // e.g., "main"
&workspace.branch, // e.g., "vk/task-123"
)
```
This uses `git merge-base --fork-point` which consults the reflog to find where the branch originally diverged, regardless of subsequent rebases.
* Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Removed the unused `find_first_commit_for_repo` function. Everything still compiles.
* All comments removed and code still compiles.
* Fixed. The changes:
1. Added `effective_dir` method to `ReviewRequest` in `crates/executors/src/actions/review.rs`
2. Updated `container.rs` to use `request.effective_dir(&workspace_root)` instead of `workspace_root.clone()` for `ReviewRequest`
Now the log normalization for reviews will use the correct working directory, matching how the agent is actually spawned.
* Fixed. Now the workspace is re-fetched after `ensure_container_exists` to get the updated `container_ref`.
* Fixed. Now using the `container_ref` returned directly from `ensure_container_exists` instead of re-fetching the workspace.
* Fixed the naming:
- `workspace_path` - the container_ref path containing all repos
- `worktree_path` - the path to a specific repo's worktree within the workspace
* Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Done. I've added an "Include git context" checkbox to the StartReviewDialog:
- Added state `includeGitContext` defaulting to `true`
- Added a checkbox UI with label "Include git context"
- The checkbox value is passed to the API as `use_all_workspace_commits`
The checkbox appears after the error message area and before the executor profile selector. Users will see it checked by default, making it clear that git context is being included without needing to add it themselves in the prompt.
* I've completed the i18n task. Here's a summary of what was done:
1. **Added i18n support to `StartReviewDialog.tsx`**:
- Imported `useTranslation` from `react-i18next`
- Replaced all hardcoded strings with translation keys:
- "Additional Instructions (optional)" → `t('startReviewDialog.additionalInstructions')`
- "Review Comments (...)" → `t('startReviewDialog.reviewComments', { count: ... })`
- "Include git context" → `t('startReviewDialog.includeGitContext')`
- "New Session" → `t('startReviewDialog.newSession')`
- "Cancel" → `t('common:buttons.cancel')`
- "Starting..." / "Start Review" → `t('actionsMenu.startingReview')` / `t('actionsMenu.startReview')`
2. **Added translations to all locale files** (`en`, `es`, `ja`, `ko`, `zh-Hans`, `zh-Hant`):
- Added `startReviewDialog` object with `additionalInstructions`, `reviewComments`, `includeGitContext`, and `newSession` keys
- Added `actionsMenu.startReview` and `actionsMenu.startingReview` to all non-English locales
3. **Verified with i18n check script**: All checks pass - no new literal strings introduced, no duplicate keys, and translation keys are consistent across all locales.
* Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* All checks pass. I've added a description below the "Include git context" checkbox:
**English:** "Tells the agent how to view all changes made on this branch"
The description appears as smaller muted text below the checkbox, explaining to users what the option does - it instructs the agent how to see all the changes on this branch (via the git diff command we inject). This helps users understand they don't need to manually ask the agent about branch changes.
* Done. Here's a summary of the changes:
1. **Replaced conditional rendering** with always showing both `AgentSelector` and `ConfigSelector`
2. **Agent selector is disabled** when `createNewSession` is false (locked to the session's executor)
3. **Fixed the variant retention bug** by adding `handleNewSessionChange` that resets `selectedProfile` to `defaultProfile` when toggling "New Session" off - this ensures the variant matches the locked executor
* Types
* Removed the unused `useStartReview` hook and its export from `hooks/index.ts`.
* All checks pass. Here's a summary of the changes made:
**`frontend/src/components/ui-new/actions/index.ts`:**
1. Added `HighlighterIcon` to the Phosphor icons import (line 33)
2. Added `StartReviewDialog` import (line 49)
3. Added `StartReview` action definition (lines 293-304) with:
- `id: 'start-review'`
- `label: 'Start Review'`
- `icon: HighlighterIcon`
- `requiresTarget: true`
- Visibility when workspace exists
- Execute function that opens `StartReviewDialog`
**`frontend/src/components/ui-new/actions/pages.ts`:**
1. Added `{ type: 'action', action: Actions.StartReview }` as the first item in the `workspaceActions` page group (line 105)
The "Start Review" action with the highlighter icon will now appear in the workspace actions menu (accessed via CMD+K or the three-dots menu on a workspace).
* All checks pass. Done. Here's a summary of the additional change:
**`frontend/src/components/ui-new/primitives/SessionChatBox.tsx`:**
- Changed `MagnifyingGlassIcon` to `HighlighterIcon` in the import (line 12)
- Updated the `ToolbarIconButton` to use `HighlighterIcon` instead of `MagnifyingGlassIcon` (line 635)
The review button in the text input now shows the highlighter icon instead of the magnifying glass.
* All checks pass. Here's a summary of the changes:
**`frontend/src/components/ui-new/primitives/Toolbar.tsx`:**
- Added proper disabled styling to `ToolbarIconButton` (`opacity-40 cursor-not-allowed`)
**`frontend/src/components/ui-new/primitives/SessionChatBox.tsx`:**
- Removed `HighlighterIcon` import (no longer hardcoded)
- Added `Icon` type import
- Replaced `ReviewModeProps` with generic `ToolbarActionProps` interface (`icon`, `label`, `onClick`)
- Changed `reviewMode` prop to `toolbarActions?: ToolbarActionProps[]`
- Updated footer to render toolbar actions dynamically from the array
**`frontend/src/components/ui-new/containers/SessionChatBoxContainer.tsx`:**
- Added `HighlighterIcon` import
- Changed `reviewMode` prop to `toolbarActions` array with the review action
The button is now:
1. Generic - accepts any action with icon/label/onClick
2. Shows proper disabled state (opacity + cursor)
3. Extensible - you can add more toolbar actions by adding to the array
* All checks pass. Now toolbar actions work identically to navbar actions:
**Summary of changes:**
1. **`SessionChatBox.tsx`**:
- Changed `toolbarActions` prop from simple `{icon, label, onClick}[]` to `{actions, context, onExecuteAction}` structure
- Uses `ActionDefinition[]` from the actions system
- Uses `isActionEnabled()` to derive disabled state from action context
- Uses `isSpecialIcon()` to filter out non-standard icons
- Handles `label` being either a string or function
2. **`SessionChatBoxContainer.tsx`**:
- Added `useActions()` and `useActionVisibilityContext()` hooks
- Created `handleToolbarAction` callback that routes actions through `executeAction`
- Created `toolbarActionsList` array containing `Actions.StartReview`
- Passes the full action context to `SessionChatBox`
Now adding a new action to the conversation input works the same as navbar:
```typescript
// Just add to the array
const toolbarActionsList = useMemo(
() => [Actions.StartReview, Actions.SomeOtherAction],
[]
);
```
The action's `isVisible`, `isEnabled`, icon, label, and execute logic all come from the central `Actions` definition in `index.ts`.
* Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Done. The "Start Review" action with the highlighter icon now appears in both the navbar (left side) and the chat input toolbar.
* Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Done. Removed `StartReview` from the navbar and added `ToggleChangesMode` to the conversation input toolbar alongside `StartReview`.
* Done.
* Removed the review-specific branch so the handler is generic, matching other containers. The toolbar action now just respects `requiresTarget`.
Details and context:
- Simplified the action handler in `frontend/src/components/ui-new/containers/SessionChatBoxContainer.tsx:444` to rely solely on the generic `action.requiresTarget` path.
- This aligns with `frontend/src/components/ui-new/containers/NavbarContainer.tsx:66`, where all actions flow through the same generic logic.
Next steps:
1) If you want, I can run a quick lint/typecheck on the frontend (`pnpm run check`) to confirm.
* Aligned the chatbox to use the shared visibility system, like the navbar, so action availability is handled by the same logic and execution stays generic.
Details and context:
- Filtered `toolbarActionsList` through `isActionVisible` with the shared `actionCtx` so Start Review only appears when it’s supposed to.
- Kept the execution handler generic so it just respects `requiresTarget`.
Files:
- `frontend/src/components/ui-new/containers/SessionChatBoxContainer.tsx`
Next steps:
1) If you want me to run a quick frontend typecheck (`pnpm run check`), say the word.
* Cleanup script changes for workspace 38f8b607-9fdc-43dc-afa3-16e8f5e9cbd3
* Updated the Start Review dialog so it derives the active session and a default executor profile from workspace context + config, which restores preselection and enables the “new session” toggle when a session exists. This keeps the chatbox action generic while fixing the dialog behavior.
Details and context:
- Added workspace context awareness and default profile derivation (mirrors Create Attempt’s logic).
- Uses the resolved session id to enable/disable the toggle and to decide whether a new session is required.
- Keeps user selection override behavior intact.
File:
- `frontend/src/components/dialogs/tasks/StartReviewDialog.tsx`
If you want, I can also add a quick regression check or walk through the UI flow with you.
* Fixed the lint issue and clippy qa-mode compile warning, then reran the requested commands. The Start Review dialog now uses `resolvedSessionId` consistently in its callback, and review log normalization handles qa-mode without unused vars.
Files updated:
- `frontend/src/components/dialogs/tasks/StartReviewDialog.tsx`
- `crates/services/src/services/container.rs`
Commands run:
- `npm run lint`
- `npm run format`
- `npm run check`
* Renamed the match binding to `_request` so we don’t need the no-op line, and removed the comment you flagged.
Notes:
- The `let _ = request;` was only there to silence an unused-var warning under the `qa-mode` cfg. Using `_request` is the standard way to mark it intentionally unused.
Files:
- `crates/services/src/services/container.rs`
- `frontend/src/components/ui-new/containers/SessionChatBoxContainer.tsx`
Want me to rerun `npm run lint` since this touched the linted files?
* Split the `ReviewRequest` arm by cfg so qa-mode uses `_request` and non-qa uses `request` normally—no dummy line needed.
File:
- `crates/services/src/services/container.rs`
* Done. The fix adds `ReviewRequest` to the match statement that creates `CodingAgentTurn` records. Now when a review is started, a `coding_agent_turn` row will be created with the review prompt, and the `agent_session_id` will be stored when Codex reports it. Subsequent follow-ups will find this session ID and correctly use `CodingAgentFollowUpRequest` instead of starting a fresh session.
* Done. Now if a new `ExecutorActionType` variant is added, the compiler will error on this match and force the developer to decide whether it should create a `CodingAgentTurn` record.
* Adjusted `sessionsApi.startReview` to return the unwrapped payload like other session calls, and aligned the `handleApiResponse` generic so callers get an `ExecutionProcess` instead of a misleading `ApiResponse`. This fixes the runtime mismatch and keeps the API consistent.
Updated `frontend/src/lib/api.ts`.
If you want, I can:
1) run `pnpm run check` to validate types, or
2) scan for any other session APIs with inconsistent `handleApiResponse` generics.
* All checks pass. Summary of changes:
1. **Removed tooltip from dialog button** - Dialog buttons don't use tooltips in this codebase
2. **Added `getTooltip` to the `StartReview` action definition** in `actions/index.ts` - This is the pattern used for action tooltips ("Ask the agent to review your changes")
3. **Removed `submitTooltip` from all locale files** since it's no longer used
4. **Added missing `title` and `description` to zh-Hant locale**
* Done. Now when a new session is created, the dialog will call `selectSession(targetSessionId)` to switch to the newly created session before closing.
|
||
|
Gabriel Gordon-Hall
|
8fa5b9d098 |
feat: remove agent_working_dir from settings (#1874)
* remove configurable agent_working_dir (cherry picked from commit 285b3e04abceeb8e4a4ee1be16e3de97a8f32299) * calculate agent_working_dir on create and start task * i18n |
||
|
Gabriel Gordon-Hall
|
c5554610a9 |
feat: Repo level management (#1828)
* move dev server scripts onto project repos * wip: move scripts onto Repo structs * wip: repo settings page * i18n and fixes * fix refresh * i18n * nits * clickable repo cards * view logs for all dev servers * updates to workspaces * Let's make some changes to the way applications are tested: (vibe-kanban 4592de6c) - When the user starts a dev server, we should automatically open the `PreviewPanel.tsx` - In the preview panel, if no dev server script is set for any of the repos in the workspace show a message along these lines: Vibe Kanban can run dev servers to help you test your changes. You can set this up in the repo settings area. You can learn more about testing applications here: https://www.vibekanban.com/docs/core-features/testing-your-application - We should also not show the `PreviewControlsContainer.tsx` if none of the repos have a dev server script `vibe-kanban/frontend/src/components/panels/PreviewPanel.tsx` `vibe-kanban/frontend/src/components/ui-new/actions/index.ts` `vibe-kanban/frontend/src/components/ui-new/containers/PreviewControlsContainer.tsx` --------- Co-authored-by: Louis Knight-Webb <louis@bloop.ai> |
||
|
Alex Netsch
|
29595c1929 |
Add Azure DevOps repository support for PR operations (Vibe Kanban) (#1808)
* All tasks are complete. Let me summarize what was implemented:
I've successfully implemented Azure DevOps repos support alongside the existing GitHub integration. Here's what was done:
- **`mod.rs`** - Defines the `GitHostService` trait and factory functions for creating services
- **`types.rs`** - Unified types: `GitHostProvider`, `RepoInfo`, `GitHostError`, `CreatePrRequest`, `UnifiedPrComment`
- **`detection.rs`** - URL pattern matching for auto-detecting GitHub (including Enterprise) and Azure DevOps
- **`github/mod.rs`** - `GitHubHostService` implementing the trait
- **`github/cli.rs`** - `GhCli` wrapper (moved from old location)
- **`azure/mod.rs`** - `AzureHostService` implementing the trait
- **`azure/cli.rs`** - `AzCli` wrapper for Azure DevOps CLI commands
1. **Auto-detection**: The system detects the provider from the git remote URL:
- `github.com` → GitHub
- `github.*.com` → GitHub Enterprise
- `dev.azure.com`, `*.visualstudio.com`, or URLs with `/_git/` → Azure DevOps
2. **Unified trait interface**: Both providers implement `GitHostService` with methods for:
- `get_repo_info()` - Get repository identification
- `check_auth()` - Verify CLI authentication
- `create_pr()` - Create pull requests
- `get_pr_status()` - Get PR status by URL
- `list_prs_for_branch()` - List PRs for a branch
- `get_pr_comments()` - Get PR comments
3. **Azure CLI commands supported**:
- `az repos pr create` - Create PRs
- `az repos pr show` - View PR details
- `az repos pr list` - List PRs
- `az repos pr list-threads` - Get PR comments
- `az account show` - Auth check
- `pr.rs` - Uses auto-detection for PR creation
- `pr_monitor.rs` - Uses provider detection from PR URL
- `task_attempts.rs` - Uses git_host for push auth checking
- `error.rs` - Updated `GitHost` error variant
- `share.rs` - Updated `GitHost` error variant
- `generate_types.rs` - Updated type exports
- Old `crates/services/src/services/github.rs` module and directory (replaced by git_host)
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
All tests pass, including the new URL decoding tests. The fix is complete - the URL-encoded components (like `Vibe%20Kanban%20Test`) will now be properly decoded to `Vibe Kanban Test` before being passed to the Azure CLI.
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
All done! Here's a summary of the changes:
Updated `get_repo_info()` to use the Azure CLI's `az repos show --detect true` command instead of manual URL parsing, similar to how GitHub uses `gh repo view --json owner,name`.
1. **Added `extract_repo_name_from_url()`** - A simple helper that extracts just the repository name from Azure DevOps URLs (looks for `/_git/{repo}` pattern). This is still needed because `az repos show` requires the `--repository` parameter.
2. **Updated `get_repo_info()`** - Now uses `az repos show --repository {name} --detect true --output json` which:
- Auto-detects organization and project from git config
- Returns canonical names (properly decoded)
- Validates the repo exists
3. **Added `extract_org_from_response()`** - Extracts the organization from the `remoteUrl` field in the CLI response, with fallback to URL parsing.
4. **Fixed `run()` method** - Now properly passes the `dir` parameter to `Command::current_dir()` so the `--detect` flag works correctly.
5. **Kept `parse_azure_remote_url()`** - Still used as a fallback for organization extraction and for PR URL parsing.
6. **Added tests** - New tests for `extract_repo_name_from_url()` covering various URL formats.
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
Done! The cleanup is complete. Here's what was removed:
Removed the brittle `parse_azure_remote_url()` function and related code:
1. **Removed `AzureRepoInfo` struct** - No longer needed
2. **Removed `parse_azure_remote_url()` function** - The ~90-line function that manually parsed various Azure DevOps URL formats
3. **Updated `get_repo_info()`** - Changed from fallback (`unwrap_or_else`) to error (`ok_or_else`) when organization can't be extracted from the CLI response
4. **Removed 4 tests** - `test_parse_azure_remote_url_https`, `test_parse_azure_remote_url_visualstudio`, `test_parse_azure_remote_url_ssh`, `test_parse_azure_remote_url_with_spaces`
The code now relies entirely on:
- `extract_repo_name_from_url()` - Simple helper to get repo name from URL (for passing to `az repos show`)
- `az repos show --detect true` - Azure CLI command that auto-detects org/project from git config
- `extract_org_from_response()` - Extracts org from the CLI's `remoteUrl` JSON field
The implementation is complete. Here's a summary of the changes:
Simplified the Azure DevOps integration by using the CLI's `--detect` flag instead of parsing URLs to extract org/project/repo.
1. **`types.rs`** - Changed `RepoInfo::AzureDevOps` to store just `repo_path: PathBuf` instead of `organization`, `project`, and `repo_name`. Removed the unused `repo_name()` method.
2. **`cli.rs`** - Major simplification:
- Removed URL parsing helpers: `decode_url_component()`, `extract_repo_name_from_url()`, `extract_org_from_response()`
- `get_repo_info()` now just verifies it's a valid Azure repo via `az repos show --detect true` and returns the path
- `create_pr()` now takes `repo_path` and uses `--detect true` instead of explicit org/project/repo
- `list_prs_for_branch()` now takes `repo_path` and uses `--detect true`
- `get_pr_threads()` now takes `repo_path` and uses `--detect true`
- `view_pr()` now takes the full PR URL and parses org + PR ID internally
- `parse_pr_url()` simplified to return just `(org, pr_id)` instead of 4 values
- Parsing functions simplified to extract URLs from response's `repository.webUrl` field
- Updated tests for the new API
3. **`mod.rs`** - Updated `AzureHostService` to:
- Extract `repo_path` from `RepoInfo::AzureDevOps`
- Pass `repo_path` to CLI methods that need it
- Pass the PR URL directly to `view_pr()` for `get_pr_status()`
- URL parsing reduced to minimal extraction of org + PR ID from PR URLs (only needed for `get_pr_status()`)
- Repo-based operations don't parse URLs at all - CLI auto-detects via git config
- Much cleaner, less brittle code
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
All done. The implementation is complete:
**Summary of changes:**
1. **`types.rs`**: Updated `RepoInfo::AzureDevOps` to store `organization_url`, `project`, `repo_name` instead of `repo_path`
2. **`cli.rs`**:
- `get_repo_info()` now parses the JSON response from `az repos show --detect true` to extract repo name, project name, and organization URL
- Added `extract_org_url()` helper to extract the base org URL from the API URL
- Updated `create_pr()`, `list_prs_for_branch()`, `get_pr_threads()` to take explicit `organization_url`, `project`, `repo_name` params
3. **`mod.rs`** (`AzureHostService`):
- `create_pr()`, `list_prs_for_branch()`, `get_pr_comments()` all now extract org/project/repo from `RepoInfo` and pass them to the CLI methods
The key insight was that the `url` field from `az repos show` (e.g., `https://dev.azure.com/{org}/.../_apis/...`) can be truncated to `https://dev.azure.com/{org}` and used directly with the `--organization` flag — minimal URL parsing needed.
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
* Done. Refactored all 4 `serde_json::Value` parsing sites to use typed structs:
**Changes to `cli.rs`:**
1. **Added typed response structs** with `#[derive(Deserialize)]`:
- `AzRepoShowResponse`, `AzProject` - for `az repos show`
- `AzPrResponse`, `AzRepository`, `AzCommit` - for PR responses
- `AzThread`, `AzThreadContext`, `AzFilePosition`, `AzThreadComment`, `AzAuthor` - for thread comments
2. **Updated parsing functions**:
- `get_repo_info()` - now deserializes into `AzRepoShowResponse`
- `parse_pr_response()` - now deserializes into `AzPrResponse`
- `parse_pr_list_response()` - now deserializes into `Vec<AzPrResponse>`
- `parse_pr_threads()` - now deserializes into `Vec<AzThread>`
3. **Replaced `extract_pr_info()`** with `az_pr_to_info()` that takes the typed struct directly
4. **Removed `serde_json::Value` import** - no longer needed
The code is now cleaner with no `.get().and_then().as_str()` chains, and serde provides better error messages on parse failures.
* Done. Added the missing `--repository` parameter to `get_pr_threads()`:
1. **`cli.rs`**: Added `repo_name: &str` parameter and `--repository` flag to the CLI command
2. **`mod.rs`**: Updated `get_pr_comments()` to extract both `organization_url` and `repo_name` from `RepoInfo` and pass them to the CLI
Done. Here's a summary of the changes:
**Changes made to `crates/services/src/services/git_host/azure/cli.rs`:**
1. **Removed git2 dependency** - No longer imports `git2::Repository`
2. **Added new typed structs** for `az repos list` response:
- `AzRepoListItem` - with `name`, `project`, and `remote_url` fields
- `AzRepoProject` - with `name` field
3. **Rewrote `get_repo_info()`** to use `az repos list --detect true`:
- Runs CLI command from the repo directory to auto-detect org/project
- Takes the first repo from the list (assuming single repo per directory)
- Extracts org from `remoteUrl` field
4. **Replaced `parse_azure_remote_url()`** with simpler `extract_org_from_remote_url()`:
- Only extracts the organization name from the URL
- Handles both `dev.azure.com` and `visualstudio.com` formats
- Much simpler than the previous 3-tuple URL parser
5. **Updated tests** - Replaced the old URL parsing tests with new `extract_org_from_remote_url` tests
The key improvement is that `az repos list --detect true` uses the Azure CLI's built-in detection (from git config) to find the org and project, then returns all repo info including project name. This avoids git2 library usage and complex URL parsing entirely.
Done. Here's a summary of all changes:
**Summary of Changes**
1. **`crates/services/src/services/git_host/types.rs`**:
- Added `project_id` and `repo_id` fields to `RepoInfo::AzureDevOps` enum variant
2. **`crates/services/src/services/git_host/azure/cli.rs`**:
- Added `id` field to `AzRepoListItem` struct
- Added `id` field to `AzRepoProject` struct
- Added `AzThreadsResponse` struct to wrap the `{ "value": [...] }` REST API response
- Updated `get_repo_info()` to return `project_id` and `repo_id` from `az repos list` output
- Updated `get_pr_threads()` to:
- Accept `project_id` and `repo_id` instead of names
- Use `az rest` with REST API URL instead of non-existent `az repos pr list-threads`
- Updated `parse_pr_threads()` to unwrap the `value` field from REST API response
3. **`crates/services/src/services/git_host/azure/mod.rs`**:
- Updated `create_pr` and `list_prs_for_branch` to use `..` pattern for new fields
- Updated `get_pr_comments()` to extract and pass `project_id` and `repo_id` to CLI
**Key Improvements**:
- Uses UUIDs (`project_id`, `repo_id`) instead of names for REST API calls, avoiding URL encoding issues with names containing spaces like "Vibe Kanban Test"
- Fixed `get_pr_threads()` to use `az rest` since `az repos pr list-threads` doesn't exist as an Azure CLI command
- All unit tests pass
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
Done. The fix adds `--resource 499b84ac-1321-427f-aa17-267ca6975798` to the `az rest` command, which tells it to request an Azure DevOps token instead of a generic Azure token. This should now properly authenticate to the Azure DevOps REST API.
Done. The fix replaces `az rest` with `az devops invoke --area git --resource pullRequestThreads`. This uses the same authentication as other `az repos pr` commands, so it should work without requiring the separate "identity materialization" step.
Done. The fix replaces the single combined string for `--route-parameters` with individual arguments for each `key=value` pair. This matches how the Azure CLI expects the parameters to be passed - each route parameter should be a separate shell argument after the `--route-parameters` flag.
Done. Removed all the requested comments from:
- `crates/server/src/routes/task_attempts.rs` (lines 451, 490)
- `crates/server/src/routes/task_attempts/pr.rs` (lines 283, 516)
- `crates/services/src/services/git_host/azure/cli.rs` (section header comment, doc comments on structs and methods)
* Done. Removed the module-level doc comment and all the method doc comments from the `GitHostService` trait and public functions in `mod.rs`.
Done. Removed the obvious/redundant comments from `types.rs`.
Done. Removed the unnecessary `Arc` usage from all three functions in `mod.rs`. The strings are already cloned when extracted from `RepoInfo`, so we can just clone them directly in the retry closure.
* All tests pass. Fixed the `npm run check` and `npm run lint` issues by:
1. Regenerated TypeScript types from Rust
2. Updated `frontend/src/lib/api.ts` to use `CreatePrApiRequest` instead of `CreateGitHubPrRequest`
3. Updated `CreatePRDialog.tsx` to handle the new error types (`cli_not_installed`/`cli_not_logged_in` with a `provider` field instead of `github_cli_not_installed`/`github_cli_not_logged_in`)
4. Fixed clippy warnings about collapsible if statements in `parse_pr_url()`
* Done. I've made `url`, `diff_hunk`, and `author_association` optional in the `UnifiedPrComment` type:
**Changes made:**
1. **`crates/services/src/services/git_host/types.rs`** - Changed the `UnifiedPrComment` enum:
- `url: String` → `url: Option<String>`
- `diff_hunk: String` → `diff_hunk: Option<String>`
- `author_association: String` → `author_association: Option<String>`
2. **`crates/services/src/services/git_host/azure/cli.rs`** - Updated Azure comment creation to use `None` instead of empty strings
3. **`crates/services/src/services/git_host/github/mod.rs`** - Wrapped GitHub values in `Some()`
4. **`frontend/src/components/ui/github-comment-card.tsx`** - Updated interface to allow `url?: string | null` and `diffHunk?: string | null`
5. **`frontend/src/components/ui/wysiwyg/nodes/github-comment-node.tsx`**:
- Updated `NormalizedComment` interface
- Fixed click handler to check `if (data.url)` before opening
- Removed `data.url` from validation (only `id`, `comment_type`, `author`, `body` required)
All checks pass (`pnpm run check`, `pnpm run lint`, `cargo test --workspace`).
* Done. All three changes are complete:
1. **Removed unnecessary temp file** in `azure/cli.rs:create_pr()` - was writing body to temp file then immediately reading it back. Now just passes `body` directly to `OsString`.
2. **Added structs for JSON parsing** in `github/cli.rs:parse_pr_comments()` - replaced manual `item.get("field")...` parsing with `GhCommentsWrapper` and `GhCommentResponse` structs using serde.
3. **Added structs for JSON parsing** in `github/cli.rs:parse_pr_review_comments()` - replaced manual parsing with `GhReviewCommentResponse` struct.
All checks pass (`pnpm run check`, `pnpm run lint`, `cargo test --workspace`).
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
Done. Both changes are complete:
1. **Inlined single-field structs** - Consolidated `GhCommentAuthor` and `GhReviewCommentUser` into a single `GhUserLogin` struct that's reused by both `GhCommentResponse` and `GhReviewCommentResponse`.
2. **Converted `extract_pr_info` to struct parsing** - Added `GhPrResponse` and `GhMergeCommit` structs. Replaced the manual `Value::get()` parsing with serde deserialization. The new `pr_response_to_info()` helper converts the parsed struct to `PullRequestInfo`. Also removed the now-unused `serde_json::Value` import.
All checks pass (`pnpm run check`, `pnpm run lint`, `cargo test --workspace`).
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
* Done. I've updated `detection.rs` to use `GitCli` instead of `git2`:
1. **Added `get_remote_url` method to `GitCli`** (`git/cli.rs`) - Uses `git remote get-url <remote>` to get the URL
2. **Updated `detect_provider`** (`git_host/detection.rs`) - Now uses `GitCli::get_remote_url()` instead of `git2::Repository`
This keeps the codebase consistent with the pattern of using `GitCli` for git operations rather than mixing `git2` directly in various modules.
All checks pass (`pnpm run check`, `pnpm run lint`, `cargo test --workspace`).
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
* Done! The refactor is complete. Here's a summary of the changes:
**New Architecture:**
1. **`ProviderKind` enum** (was `GitHostProvider`) - The discriminant for provider types (GitHub, AzureDevOps, Unknown)
2. **`GitHostProvider` trait** (was `GitHostService`) - The interface that provider implementations must satisfy
3. **`GitHubProvider` struct** (was `GitHubHostService`) - GitHub implementation
4. **`AzureDevOpsProvider` struct** (was `AzureHostService`) - Azure DevOps implementation
5. **`GitHostService` struct** (new) - Main entry point that:
- Holds repo context (`repo_path`, `GitCli`)
- Provides `provider_for_remote(remote_name)` to get a provider for a specific remote
- Provides `provider_from_url(url)` for URL-based detection (e.g., PR URLs)
- Provides `provider_for_kind(kind)` for direct provider construction
**Benefits:**
- Provider detection is now contextual - callers specify which remote they want
- The service struct encapsulates provider detection logic
- Cleaner separation: `GitHostService` is the facade, `GitHostProvider` trait is the contract
- Ready for multi-remote support (different providers for different remotes)
All checks pass (`pnpm run check`, `pnpm run lint`, `cargo test --workspace`).
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
All the call sites have been updated to use the new cleaner `GitHostService` facade API. Here's a summary of the changes:
**Changes made:**
1. **`pr.rs:414-418` (`attach_existing_pr`)**: Simplified from:
```rust
let git_host = git_host::GitHostService::new(&repo.path);
let git_host_provider = git_host.provider_for_remote("origin")?;
let repo_info = git_host_provider.get_repo_info(&repo.path).await?;
let prs = git_host_provider.list_prs_for_branch(&repo_info, &workspace.branch).await?;
```
To:
```rust
let git_host = git_host::GitHostService::new(&repo.path);
let prs = git_host.list_prs_for_branch(&workspace.branch).await?;
```
2. **`pr.rs:511-525` (`get_pr_comments`)**: Simplified from provider-based pattern to:
```rust
let git_host = git_host::GitHostService::new(&repo.path);
let provider = git_host.provider_kind()?;
match git_host.get_pr_comments(pr_info.number).await { ... }
```
3. **`task_attempts.rs:451-453` (`push_task_attempt_branch`)**: Removed explicit `check_auth()` call since auth is now checked during the actual operation. Just verify provider is supported:
```rust
let git_host = git_host::GitHostService::new(&worktree_path);
git_host.provider_kind()?;
```
4. **`task_attempts.rs:490-492` (`force_push_task_attempt_branch`)**: Same simplification.
The new API is much cleaner - call sites just create a `GitHostService::new(path)` and call methods directly without dealing with providers, repo info, or explicit auth checks.
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
The refactoring is complete. Here's a summary of what was done:
**Changes made:**
1. **`crates/services/Cargo.toml`** - Added `enum_dispatch` dependency
2. **`crates/services/src/services/git_host/mod.rs`** - Completely rewritten:
- `GitHostProvider` is now a public trait with `#[enum_dispatch(GitHostService)]`
- `GitHostService` is now an enum with `GitHub` and `AzureDevOps` variants
- Constructors: `from_pr_url(url)` and `from_remote_url(url)` - no `new()` method
- Methods now take `repo_path` as a parameter where needed
3. **`crates/services/src/services/git_host/github/mod.rs`** - Updated to match new trait signature (methods take `repo_path`, `check_auth` called inside `create_pr`)
4. **`crates/services/src/services/git_host/azure/mod.rs`** - Updated similarly
5. **`crates/services/src/services/git.rs`** - Added `get_remote_url()` method to `GitService`
6. **Call site updates:**
- `pr_monitor.rs` - Uses `from_pr_url`
- `pr.rs` - Uses `get_remote_name_from_branch_name` + `get_remote_url` + `from_remote_url`
- `task_attempts.rs` - Same pattern for push functions
**New API usage:**
```rust
// From a PR URL (e.g., for checking PR status)
let git_host = GitHostService::from_pr_url(&pr_url)?;
let status = git_host.get_pr_status(&pr_url).await?;
// From a remote URL (e.g., for creating PRs)
let remote_name = git_service.get_remote_name_from_branch_name(&repo_path, &branch)?;
let remote_url = git_service.get_remote_url(&repo_path, &remote_name)?;
let git_host = GitHostService::from_remote_url(&remote_url)?;
let pr_info = git_host.create_pr(&repo_path, &pr_request).await?;
// Get provider kind (infallible since already constructed)
let provider = git_host.provider_kind();
```
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
All cleaned up. Here's the final architecture:
**`git_host/mod.rs`:**
```rust
pub trait GitHostProvider: Send + Sync {
async fn create_pr(&self, repo_path: &Path, request: &CreatePrRequest) -> Result<PullRequestInfo, GitHostError>;
async fn get_pr_status(&self, pr_url: &str) -> Result<PullRequestInfo, GitHostError>;
async fn list_prs_for_branch(&self, repo_path: &Path, branch_name: &str) -> Result<Vec<PullRequestInfo>, GitHostError>;
async fn get_pr_comments(&self, repo_path: &Path, pr_number: i64) -> Result<Vec<UnifiedPrComment>, GitHostError>;
fn provider_kind(&self) -> ProviderKind;
}
pub enum GitHostService {
GitHub(GitHubProvider),
AzureDevOps(AzureDevOpsProvider),
}
impl GitHostService {
pub fn from_url(url: &str) -> Result<Self, GitHostError>
}
```
**Changes made:**
1. Removed `check_auth` and `get_repo_info` from the public trait - they're now private methods on each provider
2. Consolidated `from_pr_url` and `from_remote_url` into a single `from_url` constructor
3. The trait now has exactly 5 methods - the minimal public API needed by call sites
**Call site usage is clean:**
```rust
// From any URL (PR URL or remote URL)
let git_host = GitHostService::from_url(&url)?;
// Use the trait methods
let pr_info = git_host.create_pr(&repo_path, &request).await?;
let status = git_host.get_pr_status(&pr_url).await?;
let prs = git_host.list_prs_for_branch(&repo_path, &branch).await?;
let comments = git_host.get_pr_comments(&repo_path, pr_number).await?;
let kind = git_host.provider_kind();
```
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
Done. The refactoring is complete:
1. **Created `GitHubRepoInfo`** in `git_host/github/cli.rs` - a simple struct with `owner` and `repo_name`
2. **Created `AzureRepoInfo`** in `git_host/azure/cli.rs` - a struct with `organization_url`, `project`, `project_id`, `repo_name`, `repo_id`
3. **Updated both providers** to use their respective provider-specific structs directly, removing all the match arms and error cases for "wrong variant" that could never happen
4. **Removed the shared `RepoInfo` enum** from `types.rs` and the public exports
The code is cleaner now - each provider has its own internal representation of repo info, and there's no shared enum that requires impossible error handling paths.
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
The fix compiles. The issue was that `get_remote_name_from_branch_name` was calling `get_remote_from_branch_ref` which uses `repo.branch_remote_name()` - this git2 function requires the branch to have upstream tracking configured. For local branches that haven't been pushed yet (or don't have tracking set), this fails with the error you saw.
The fix changes the behavior to fall back to the default remote (typically "origin") when the branch doesn't have upstream tracking configured. This makes sense because:
1. Most repos only have one remote anyway
2. When creating a PR for a local branch, we need to push to *some* remote - the default is the sensible choice
3. The original code computed `default_remote` but never actually used it as a fallback
Done. Added `get_remote_url_from_branch_or_default` to `GitService` and updated all 4 call sites. The pattern is now:
```rust
let remote_url = deployment
.git()
.get_remote_url_from_branch_or_default(&repo_path, &branch)?;
let git_host = git_host::GitHostService::from_url(&remote_url)?;
```
Two lines instead of four, and the function name makes the fallback behavior explicit.
Done. Removed the unnecessary provider detection checks from both `push_task_attempt_branch` and `force_push_task_attempt_branch`. The push operations now just push directly - git push works with any remote regardless of whether we support it as a PR provider. Auth errors from git push itself (SSH keys, HTTPS credentials) still come through `GitServiceError::GitCLI(...)` and propagate to the frontend the same way.
* All done. Removed the low-value comments:
- "Create git host from the PR URL"
- "Fetch comments"
- "Get the URL for a remote (e.g., "origin")."
- "Azure DevOps-specific repository information"
- "GitHub-specific repository information"
- "Get the remote URL for the branch to detect the provider" (2 places)
- "Get repository info from the GitHub CLI"
- "Get repository info from the Azure CLI"
- "Check authentication status" (2 places)
Kept comments that provide actual value like the fallback behavior explanation on `get_remote_url_from_branch_or_default`.
All done. Removed the low-value comments:
- "Create git host from the PR URL"
- "Fetch comments"
- "Get the URL for a remote (e.g., "origin")."
- "Azure DevOps-specific repository information"
- "GitHub-specific repository information"
- "Get the remote URL for the branch to detect the provider" (2 places)
- "Get repository info from the GitHub CLI"
- "Get repository info from the Azure CLI"
- "Check authentication status" (2 places)
- "Get PR status from URL (auto-detects provider)"
- "High-level errors originating from the Azure CLI."
- "High-level errors originating from the GitHub CLI."
- "Azure DevOps hosting provider implementation"
- "GitHub hosting provider implementation"
- "Newtype wrapper for invoking the `gh` command."
- "Newtype wrapper for invoking the `az` command."
- "Trait for git hosting provider operations (GitHub, Azure DevOps, etc.)"
- All the trait method doc comments (Create a pull request, Get PR status, etc.)
- "Git hosting service - dispatches to the appropriate provider."
- "Create a GitHostService by detecting the provider from a URL."
- Simplified the Azure DevOps pattern comments in detection.rs
* Done. Here's a summary of the fix:
**Problem**: `get_repo_info` used `az repos list --detect true` which returns ALL repos in the Azure DevOps project, then just took the first one. This was wrong for multi-repo projects.
**Solution**:
1. `AzureDevOpsProvider` now stores the remote URL passed to `from_url()`
2. `get_repo_info` now takes the remote URL and filters the repo list to find the matching repo using `remote_urls_match()`
3. Added `remote_urls_match()` helper that normalizes URLs (lowercase, strips trailing `/` and `.git`) for comparison
4. Added `extract_organization_url()` to get the Azure organization URL from a remote URL (supports both `dev.azure.com` and legacy `visualstudio.com` formats)
5. Removed the now-unused `extract_org_from_remote_url()` function
The flow is now:
- Call site gets remote URL via `get_remote_url_from_branch_or_default()`
- Creates `GitHostService::from_url(&remote_url)` which stores the URL on `AzureDevOpsProvider`
- When `get_repo_info` is called, it lists all repos in the project and finds the one matching the stored remote URL
Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
* Done. Summary of changes:
1. **`pr.rs:get_pr_comments`** - Now gets the remote URL from `workspace_repo.target_branch` instead of using the PR URL to create the `GitHostService`
2. **`azure/cli.rs`**:
- Added `ssh_url` field to `AzRepoListItem`
- Updated `get_repo_info` to detect if the input URL is SSH (`starts_with("git@")`) and compare against the appropriate field (`ssh_url` vs `remote_url`)
- Renamed `remote_urls_match` to `urls_match` since it now handles both HTTPS and SSH URLs
- Added SSH URL test case
* Build passes. The simple fix handles both SSH formats without adding a dependency.
* Build passes. Now `ssh_url` is optional - if it's not in the response and the user has an SSH remote configured, they'll get a clear error message ("No repo found matching remote URL: ...").
* Done. The `urls_match` function now normalizes `ssh://` prefix to scp-style before comparing.
* Done. Summary of changes:
1. **Removed `remote_url` field from `AzureDevOpsProvider`** - no longer stored on the struct
2. **Updated `GitHostProvider` trait** - added `remote_url: &str` parameter to:
- `create_pr`
- `list_prs_for_branch`
- `get_pr_comments`
3. **Updated `AzureDevOpsProvider`** - methods now accept `remote_url` and pass it to `get_repo_info`
4. **Updated `GitHubProvider`** - methods accept `_remote_url` (unused, since gh CLI auto-detects)
5. **Updated call sites in `pr.rs`** - all three methods now pass `remote_url`:
- `create_pr` passes `&remote_url`
- `list_prs_for_branch` passes `&remote_url`
- `get_pr_comments` passes `&remote_url`
6. **Fixed `attach_existing_pr`** - now uses `workspace_repo.target_branch` instead of `workspace.branch` when getting the remote URL (consistent with other call sites)
* Cleanup script changes for workspace 28eb9564-f95a-42e0-8cf2-5228c2ffc0bf
* Update frontend remote copy (vibe-kanban a7bf13b6)
We added azure support but in the frontend many things have github specific wording. Please fix!
* Done. I've addressed the PR comment by:
1. **Renamed `CreatePrError` to `PrError`** - A more generic name that works for both `create_pr` and `attach_existing_pr`
2. **Updated `attach_existing_pr`** to mirror the error handling from `create_pr`:
- Changed return type from `ApiResponse<AttachPrResponse>` to `ApiResponse<AttachPrResponse, PrError>`
- Added error handling for `GitHostService::from_url()` - handles `UnsupportedProvider` and `CliNotInstalled`
- Added error handling for `list_prs_for_branch()` - handles `CliNotInstalled` and `AuthFailed`
3. **Updated `generate_types.rs`** to use the renamed `PrError`
4. **Updated `frontend/src/lib/api.ts`** to use `PrError` instead of `CreatePrError`
5. **Regenerated TypeScript types** and verified all checks pass
|
||
|
Louis Knight-Webb
|
af70dd9239 |
The implementation is complete. Here's a summary of the changes made: (#1871)
## Summary
I've implemented the GitHub PR status display on `WorkspaceSummary.tsx`. The changes include:
### Backend Changes
1. **`crates/db/src/models/merge.rs`** - Added a new method `get_latest_pr_status_for_workspaces()` that efficiently queries the latest PR status for all workspaces grouped by archived status.
2. **`crates/server/src/routes/task_attempts/workspace_summary.rs`** - Added `pr_status: Option<MergeStatus>` field to the `WorkspaceSummary` struct and included the PR status query in the summary endpoint.
### Frontend Changes
3. **`frontend/src/components/ui-new/hooks/useWorkspaces.ts`** - Added `prStatus` to the `SidebarWorkspace` interface and mapped it in `toSidebarWorkspace()`.
4. **`frontend/src/components/ui-new/primitives/WorkspaceSummary.tsx`** - Added:
- Import for `GitPullRequestIcon`
- `prStatus` prop to the component
- Display logic showing:
- **PR open**: `GitPullRequestIcon` with `text-brand` (orange) color
- **PR merged**: `GitPullRequestIcon` with `text-success` (green) color
- **No PR/closed/unknown**: No icon displayed
5. **`frontend/src/components/ui-new/views/WorkspacesSidebar.tsx`** - Passed the `prStatus` prop to both active and archived workspace summaries.
### Generated Types
6. **`shared/types.ts`** - Auto-generated to include the new `pr_status` field in `WorkspaceSummary`.
|
||
|
Louis Knight-Webb
|
527febdc52 | Workspaces FE (#1733) | ||
lif
|
dcaa8b8769 |
fix: copy images to agent_working_dir when set (#1752)
* fix: copy images to agent_working_dir when set When agent_working_dir is configured, copy images to <workspace>/<agent_working_dir>/.vibe-images/ instead of <workspace>/.vibe-images/ so that relative paths work correctly for the AI agent. Closes #1727 Signed-off-by: majiayu000 <1835304752@qq.com> * optionally append agent working directory in other image routes --------- Signed-off-by: majiayu000 <1835304752@qq.com> Co-authored-by: Gabriel Gordon-Hall <ggordonhall@gmail.com> |
||
Solomon
|
0f3ee560f3 | Speedup pre-release CI runs (#1804) | ||
|
Alex Netsch
|
0478ce06fc |
Reset workspace cleanup timer at diff view and IDE open (#1654)
* Add workspace.touch to reset cleanup timer at diff view and ide open * Touch at ensure_container_exists, rm comments |
||
|
Alex Netsch
|
147c4fd53d |
Support GitHub Enterprise and SSH aliases via gh CLI (Vibe Kanban) (#1783)
* All changes have been implemented and tested. Here's a summary of what was done:
Updated the PR URL parsing logic to support GitHub Enterprise hostnames by using the `url` crate instead of searching for `"github.com"` as a string token.
1. **`crates/review/Cargo.toml`** - Added `url = "2.5"` dependency
2. **`crates/review/src/github.rs`** - Rewrote `parse_pr_url` function to use `Url::parse()` and `path_segments()` instead of string splitting. Added two new test cases:
- `test_parse_pr_url_github_enterprise` - Tests GitHub Enterprise URLs
- `test_parse_pr_url_any_host` - Tests that any host with the `/pull/` pattern works
3. **`crates/remote/src/routes/github_app.rs`** - Applied the same pattern to the duplicate `parse_pr_url` function
The new implementation:
- Parses the URL with `Url::parse()`
- Extracts path segments directly (e.g., `["owner", "repo", "pull", "123"]`)
- No longer requires `github.com` as a specific hostname
- Works with any hostname including `github.mycompany.com`, `github.enterprise.corp`, etc.
Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
All done! Here's a summary of what was implemented:
This PR adds support for GitHub Enterprise hostnames and SSH hostname aliases by delegating to the `gh` CLI instead of parsing URLs with hardcoded `github.com` patterns.
**1. `crates/services/src/services/github/cli.rs`**
- Added `run_in_dir()` helper method to run `gh` commands in a specific directory
- Added `get_repo_info(repo_path)` - uses `gh repo view --json owner,name` to get repo info from a directory
- Added `view_pr_by_url(pr_url)` - uses `gh pr view <url>` to get PR info directly from a URL
**2. `crates/services/src/services/github.rs`**
- Exported `GhCli` and `GhCliError` for use by other modules
- Added `update_pr_status_by_url(pr_url)` method to `GitHubService`
- Replaced regex-based `from_remote_url()` with hostname-agnostic URL parsing using the `url` crate (kept for backward compatibility)
**3. `crates/services/src/services/git.rs`**
- Updated `get_github_repo_info()` to use `GhCli::get_repo_info()` instead of parsing URLs
**4. `crates/services/src/services/pr_monitor.rs`**
- Updated `check_pr_status()` to use `update_pr_status_by_url()` instead of parsing the PR URL
**5. Tests** (`crates/services/tests/git_workflow.rs`)
- Updated existing tests for hostname-agnostic parsing
- Added new tests for GitHub Enterprise and SSH alias URLs
**6. `crates/review/src/github.rs`** (previously done)
- Already updated to use hostname-agnostic URL parsing
**7. `crates/remote/src/routes/github_app.rs`** (previously done)
- Already updated to use hostname-agnostic URL parsing
- **SSH hostname aliases** (e.g., `github-xxx` in `~/.ssh/config`) now work
- **GitHub Enterprise** instances (e.g., `github.mycompany.com`) now work
- **No regex** - removed regex dependency from `github.rs`, using simple URL parsing and `gh` CLI
- **Robust** - `gh` CLI handles all the complexity of authentication and hostname resolution
Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
Done! I've simplified the API by:
1. **Removed** the old `update_pr_status(&repo_info, pr_number)` method that took repo info and PR number separately
2. **Renamed** `update_pr_status_by_url(pr_url)` → `update_pr_status(pr_url)` for a cleaner API
Now there's just one method that takes the PR URL directly, and the `gh` CLI handles all the complexity of hostname resolution, SSH aliases, and GitHub Enterprise automatically.
All tests pass. The fix is complete - I renamed the test from `test_parse_pr_url_any_host` to `test_parse_pr_url_custom_github_host` and changed the URL from a misleading GitLab example to a realistic GitHub Enterprise URL (`github.acme.com`).
Done! I've removed `from_remote_url()` entirely:
1. **Removed** `GitHubRepoInfo::from_remote_url()` method from `crates/services/src/services/github.rs`
2. **Removed** the `use url::Url;` import from that file (since it's no longer needed there)
3. **Removed** both tests that exercised the now-deleted function from `crates/services/tests/git_workflow.rs`
4. **Updated** the import to remove `GitHubRepoInfo` and `GitHubServiceError` which are no longer used in tests
All tests pass and the workspace compiles cleanly. The `url` crate is still used elsewhere in the services crate, so I left it in Cargo.toml.
Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
Done! I've made both cleanups:
1. **Consolidated `run()` and `run_in_dir()`** - Now there's a single `run()` method with an optional `dir: Option<&Path>` parameter. All callers pass `None` for global commands and `Some(path)` when running in a specific directory.
2. **Renamed `view_pr_by_url()` to `view_pr()`** - Removed the old `view_pr(owner, repo, pr_number)` method and renamed `view_pr_by_url(pr_url)` to just `view_pr(pr_url)` for a cleaner API.
All tests pass and the workspace compiles cleanly.
Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
Done! I've reverted the test change in `crates/review/src/github.rs` back to the original `test_parse_pr_url_any_host` with the GitLab URL. The `crates/remote/src/routes/github_app.rs` file had no changes from my work to revert.
All tests pass and the workspace compiles. The changes in this PR are now scoped to just the `services` crate:
- `cli.rs` - consolidated `run()`, renamed `view_pr()`
- `github.rs` - removed `from_remote_url()` and `url` import
- `git.rs` - uses `GhCli::get_repo_info()`
- `git_workflow.rs` - removed tests for `from_remote_url()`
Done. I've reset the review and remote crate files to `origin/main`. The changes to those crates are now reverted and can be submitted in a separate PR. All tests pass and the workspace compiles.
This PR now only contains the services crate changes:
- `cli.rs` - consolidated `run()`, renamed `view_pr()`
- `github.rs` - removed `from_remote_url()` and `url` import
- `git.rs` - uses `GhCli::get_repo_info()`
- `git_workflow.rs` - removed tests for `from_remote_url()`
All done. All three review comments addressed:
1. Removed comment "Optionally runs in a specific directory..." from `cli.rs`
2. Removed doc comment from `update_pr_status` in `github.rs`
3. Replaced helper structs with `serde_json::Value` parsing (matches existing pattern in the file)
Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
Done. Reverted to the helper structs.
All done. Summary of changes:
1. **Removed 3 comments** as requested:
- `git.rs:1599` - removed "Uses `gh repo view` which handles SSH aliases, GitHub Enterprise, etc."
- `cli.rs:202` - removed "This handles GitHub Enterprise and custom hostnames automatically via the `gh` CLI."
- `pr_monitor.rs:101` - removed "Use the URL directly - gh CLI handles all hostname/SSH alias complexity"
2. **Clone question in `github.rs:210`** - Added a comment explaining why the clone is needed (spawn_blocking requires owned values, each retry needs fresh copies)
3. **Fixed `--head {owner}:{branch}` bug** - Changed to `--head branch` only, since the `{owner}:{branch}` syntax is not supported per gh docs
4. **Added 2 unit tests** for `get_repo_info()` JSON parsing:
- `test_parse_repo_info_valid` - tests successful parsing
- `test_parse_repo_info_invalid` - tests error handling
* Done. Addressed the review comment by:
1. Removed `GitService.get_github_repo_info()` facade from `git.rs`
2. Updated 3 callers in `pr.rs` to use `GhCli::new().get_repo_info()` directly
3. Added `GhCliError` to `ApiError` in `error.rs` for proper error handling
4. Removed unused import in `git.rs`
* Done. Now the architecture is cleaner:
- `GhCli` is an internal implementation detail of `GitHubService`
- Callers use `GitHubService.get_repo_info(&path)` instead of touching `GhCli` directly
- Later, a `GitLabService` could have the same `get_repo_info` interface
- Removed `GhCliError` from `ApiError` since errors are now converted to `GitHubServiceError`
* Done.
* Done. `get_repo_info` is now async with `spawn_blocking`, matching the pattern used by other methods like `check_token`.
* Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
* Done. `GhCli` and `GhCliError` are now private to the `github` module.
* Cleanup script changes for workspace e22082a4-ca31-4754-9c1c-2dc5b6991338
|
||
|
Alex Netsch
|
3c35b92a97 |
Use session IDs for scratches and queued messages (Vibe Kanban) (#1613)
* All changes have been completed. Here's a summary of what was done: ## Summary Changed both scratches and queued messages to use session IDs instead of workspace IDs: ### Files Modified 1. **`frontend/src/components/tasks/TaskFollowUpSection.tsx`** - Changed `useScratch(ScratchType.DRAFT_FOLLOW_UP, workspaceId ?? '')` → `useScratch(ScratchType.DRAFT_FOLLOW_UP, sessionId ?? '')` 2. **`crates/server/src/routes/sessions/queue.rs`** - Changed `session.workspace_id` → `session.id` in all three queue operations (queue, cancel, get status) 3. **`crates/services/src/services/queued_message.rs`** - Renamed `task_attempt_id` → `session_id` in `QueuedMessage` struct - Updated all method parameters and comments 4. **`crates/local-deployment/src/container.rs`** - Changed `ctx.workspace.id` → `ctx.session.id` for queue lookups and scratch deletion - Updated log messages to reference "session" instead of "workspace" 5. **`shared/types.ts`** (auto-generated) - `QueuedMessage.task_attempt_id` → `QueuedMessage.session_id` * Cleanup script changes for task attempt 4df90bcd-f261-41ca-bac3-8f7c2fc576c5 * Build passes. The fix has been applied. Found and fixed one missed instance in `sessions/mod.rs` where `Scratch::delete` was using `workspace.id` instead of `session.id`. |
||
|
Alex Netsch
|
2f5cef2dff |
Add agent working directory setting to run coding agents from repo directory (Vibe Kanban) (#1617)
* Done! The migration has been updated to copy `dev_script_working_dir` values to `agent_working_dir` for existing projects. The change: **`vibe-kanban/crates/db/migrations/20251219000000_add_agent_working_dir_to_projects.sql`**: ```sql -- Add column with empty default first ALTER TABLE projects ADD COLUMN agent_working_dir TEXT DEFAULT ''; -- Copy existing dev_script_working_dir values to agent_working_dir UPDATE projects SET agent_working_dir = dev_script_working_dir WHERE dev_script_working_dir IS NOT NULL AND dev_script_working_dir != ''; ``` This ensures that when the migration runs, existing projects will have their `agent_working_dir` automatically populated from their existing `dev_script_working_dir` setting. * Done! The migration has been updated to only copy `dev_script_working_dir` to `agent_working_dir` for single-repo projects. Multi-repo projects will keep `agent_working_dir` empty (None). The key change in the migration: ```sql UPDATE projects SET agent_working_dir = dev_script_working_dir WHERE dev_script_working_dir IS NOT NULL AND dev_script_working_dir != '' AND (SELECT COUNT(*) FROM project_repos WHERE project_repos.project_id = projects.id) = 1; ``` The subquery `(SELECT COUNT(*) FROM project_repos WHERE project_repos.project_id = projects.id) = 1` ensures only projects with exactly one repository get the default value copied. * Done! All tasks completed: 1. **Resolved the rebase conflict** in `task_attempts.rs` - removed the duplicate `follow_up` function since it was moved to `sessions/mod.rs` on main 2. **Updated `sessions/mod.rs`** with the `working_dir` changes - added the code to get `agent_working_dir` from project settings and pass it to both `CodingAgentFollowUpRequest` and `CodingAgentInitialRequest` 3. **Ran `npm run prepare-db`** - successfully prepared the database and updated sqlx cache 4. **Verified compilation** - all crates compile successfully The migration now only copies `dev_script_working_dir` to `agent_working_dir` for single-repo projects (projects with exactly 1 repo in `project_repos` table). Multi-repo projects will keep `agent_working_dir` empty. * Done. Removed all 6 comments as requested. * Done! The implementation is now complete: 1. **Database migration** - Copies `dev_script_working_dir` to `agent_working_dir` for single-repo projects at migration time 2. **Runtime backfill** - `backfill_repo_names()` in `container.rs` sets `agent_working_dir` for existing single-repo projects where it's still empty 3. **Project creation** - New single-repo projects automatically get `agent_working_dir` set to the repo name All three scenarios are now covered for setting `agent_working_dir` on single-repo projects. * Done! The frontend UI for `agent_working_dir` has been added: 1. Added `agent_working_dir: string` to `ProjectFormState` interface 2. Added `agent_working_dir` to `projectToFormState` function 3. Added `agent_working_dir` to the `handleSave` payload 4. Added the input field after the dev server working directory input * All tasks are complete. The implementation is finished: **Summary of changes:** 1. **Project model**: Renamed `agent_working_dir` to `default_agent_working_dir` - this is now a default value for new workspaces 2. **Workspace model**: Added `agent_working_dir` field - this captures the project's default at workspace creation time 3. **Workspace creation**: Updated `create_task_attempt` to fetch the project's `default_agent_working_dir` and pass it to the workspace 4. **Execution sites**: Updated all 4 locations to use `workspace.agent_working_dir` instead of `project.default_agent_working_dir`: - `container.rs` (start_workspace) - `container.rs` (start_queued_follow_up) - `sessions/mod.rs` (follow_up) - `task_attempts/pr.rs` (trigger_pr_description_follow_up) 5. **Frontend**: Updated `ProjectSettings.tsx` to use `default_agent_working_dir` 6. **Migrations**: Two migrations added - one to rename the project column and one to add the workspace column * Cleanup script changes for workspace a87cad74-ed7c-402b-b3f3-413a939a13a9 * Done. The migrations have been squashed into a single migration file `20251219000000_add_agent_working_dir_to_projects.sql` which now handles both the project and workspace table changes. The separate workspace migration file has been deleted and `npm run prepare-db` completes successfully. * Done. The i18n check passes with all checks passing: - No new literal strings introduced - No duplicate keys found in JSON files - Translation keys are consistent across locales (en, es, ja, ko, zh-Hans) * All checks pass: - `npm run check` ✅ (frontend TypeScript and backend Rust) - `npm run prepare-db` ✅ (migrations and sqlx query cache) * `npm run lint` passes now. * Done. I've added the logic to `crates/services/src/services/project.rs` in the `add_repository()` function. When a second repository is added to a project (repo count becomes exactly 2), the `default_agent_working_dir` field is automatically cleared by setting it to an empty string. * Cleanup script changes for workspace a87cad74-ed7c-402b-b3f3-413a939a13a9 * Both checks pass. The fix now correctly: 1. Counts repos **before** adding the new one 2. Only clears `default_agent_working_dir` if the previous count was exactly 1 (meaning we're going from 1 to 2 repos) * Done. The fix now: 1. Added a dedicated `Project::clear_default_agent_working_dir()` method in `crates/db/src/models/project.rs` that only updates the `default_agent_working_dir` field without touching other fields 2. Updated `add_repository()` in `crates/services/src/services/project.rs` to use this new method when the repo count goes from 1 to 2 |
||
|
Alex Netsch
|
6a129d0fa8 |
Add session-scoped routes for follow-up and queue operations (Vibe Kanban) (#1606)
* Yup, I'll hold off and do nothing for now. Let me know when you're ready to proceed with the session routes task, and I'll start exploring the codebase and planning the implementation. All cherry-pick conflicts resolved: 1. **`sessions/queue.rs`** - Fixed analytics to use `session.id` and `session.workspace_id` (2 locations) 2. **`task_attempts.rs`** - Removed the old `follow_up()` function that was already moved to `sessions/mod.rs` No remaining conflict markers in the routes directory. All fixes complete: 1. **`sessions/queue.rs`** ✓ - Fixed analytics to use `session.id` and `session.workspace_id` 2. **`task_attempts.rs`** ✓ - Removed old `follow_up` function (moved to sessions) 3. **`sessions/mod.rs`** ✓ - Fixed to use `find_latest_coding_agent_turn_session_id(pool, session.id)` instead of non-existent method The session-based `follow_up` now correctly scopes the agent_session_id lookup to the current session rather than across all workspace sessions. * All done: 1. ✓ `container.rs` - Changed to `find_latest_coding_agent_turn_session_id(pool, ctx.session.id)` 2. ✓ `pr.rs` - Changed to `find_latest_coding_agent_turn_session_id(pool, session.id)` 3. ✓ Deleted `find_latest_agent_session_id_by_workspace` from `execution_process.rs` All workspace-scoped `agent_session_id` lookups have been converted to session-scoped lookups and the unused method has been removed. Cleanup script changes for task attempt afc116fb-e639-4150-a299-b05c1f14f61e Done. Removed the unnecessary `Session::create` call and now using `&ctx.session` directly. Lint, db * Done. Simplified the validation: - Removed the extra `Session::find_by_id` DB call - Now directly checks `process.session_id != session.id` - Updated error message to "Process does not belong to this session" |
||
|
Gabriel Gordon-Hall
|
41151bd172 | fix for single file (#1610) | ||
|
Gabriel Gordon-Hall
|
fbffcdc0d2 | special case single repo projects for open IDE operation (#1609) | ||
|
Alex Netsch
|
4188adc2a9 |
Refactor task_attempts to workspaces and sessions (Vibe Kanban) (#1569)
* All tasks are complete. Here's a summary of the refactoring that was done:
The `task_attempts` table has been refactored into `workspaces` and `sessions`:
- Created new migration `20251216142123_refactor_task_attempts_to_workspaces_sessions.sql`
- Renamed `task_attempts` table to `workspaces` (removed `executor` column)
- Created new `sessions` table with `(id, workspace_id, executor, created_at, updated_at)`
- Renamed `executor_sessions` to `coding_agent_turns` (dropped redundant `task_attempt_id`)
- Changed `execution_processes.task_attempt_id` to `session_id`
- Changed `merges.task_attempt_id` to `workspace_id`
- Changed `tasks.parent_task_attempt` to `parent_workspace_id`
- Renamed `crates/db/src/models/task_attempt.rs` → `workspace.rs`
- Created new `crates/db/src/models/session.rs`
- Renamed `executor_session.rs` → `coding_agent_turn.rs`
- Updated `execution_process.rs`:
- Changed `task_attempt_id` field to `session_id`
- Added workspace-level query methods (`find_latest_by_workspace_and_run_reason`, `latest_executor_profile_for_workspace`, `find_latest_external_session_id_by_workspace`, `find_running_dev_servers_by_workspace`, `has_running_non_dev_server_processes_for_workspace`)
- Updated `merge.rs`: Changed `task_attempt_id` to `workspace_id`
- Updated `task.rs`: Changed `parent_task_attempt` to `parent_workspace_id`
- Updated `container.rs`: Changed `start_execution` to take 4 parameters (workspace, session, action, reason)
- Updated `events/`: Changed event types from `TaskAttempt` to `Workspace`
- Updated `pr_monitor.rs`: Changed to use `Workspace` instead of `TaskAttempt`
- Updated `workspace_manager.rs`: Added support for `DbWorkspace` alias
- Updated `task_attempts.rs`: All handlers now create/use sessions for execution processes
- Updated `tasks.rs`: Removed `executor` from `CreateWorkspace`, fixed error type
- Updated setup helpers (codex, cursor, gh_cli) to create sessions
- Updated `error.rs`: Added `SessionError` handling
Cleanup script changes for task attempt 2f672d73-cb46-4515-b1c7-3da8f4402858
Done. All 3 `sqlx::query_scalar()` function calls have been converted to `sqlx::query_scalar!()` macros:
1. `has_running_non_dev_server_processes()` - lines 332-341
2. `has_running_non_dev_server_processes_for_workspace()` - lines 350-361
3. `find_prev_after_head_commit()` - lines 619-634
Key changes:
- Converted `?` placeholders to `$1, $2, $3` positional parameters (sqlx macro style)
- Added `as "count!: i64"` type annotation for COUNT queries
- Used `.flatten()` for the nullable `after_head_commit` column to avoid `Option<Option<String>>`
The one in `crates/remote/src/db/mod.rs` uses dynamic SQL for PostgreSQL's `ALTER ROLE` and cannot be converted to a macro.
Done. Removed the 4 unused functions from `execution_process.rs`:
- `find_running_dev_servers_by_session`
- `has_running_non_dev_server_processes` (the per-session version)
- `delete_by_session_id`
- `latest_executor_profile_for_session`
The workspace-level versions (`has_running_non_dev_server_processes_for_workspace`, `find_running_dev_servers_by_workspace`, `latest_executor_profile_for_workspace`) are still available. Everything builds successfully.
Rewbase
Revert event rename
* All done. Here's a summary of the changes:
Created a `TaskAttempt` helper struct in the backend that maintains backwards compatibility with the frontend:
1. **`crates/db/src/models/workspace.rs`**
- Added `TaskAttempt` struct that combines `Workspace` fields + `executor` from the latest `Session`
- Added `TaskAttempt::from_workspace()` to convert a `Workspace` by fetching its latest session's executor
- Added `TaskAttempt::fetch_all()` for API responses
2. **`crates/db/src/models/task.rs`**
- Changed `TaskRelationships.current_workspace` → `current_attempt: TaskAttempt`
3. **`crates/server/src/routes/task_attempts.rs`**
- Updated `get_task_attempts` to return `Vec<TaskAttempt>`
- Updated `get_task_attempt` to return `TaskAttempt`
- Updated `create_task_attempt` to return `TaskAttempt`
4. **`crates/server/src/bin/generate_types.rs`**
- Added `TaskAttempt::decl()` to the type generation list
Fixed references from `parent_task_attempt` to `parent_workspace_id` in:
- `TaskCard.tsx`
- `NoServerContent.tsx`
- `TaskPanel.tsx`
- `TaskFormDialog.tsx`
- `CreateAttemptDialog.tsx`
- `useTaskMutations.ts`
- `ProjectTasks.tsx`
- Frontend now gets `TaskAttempt` type with the `executor` field
- The `TaskRelationships.current_attempt` field provides `TaskAttempt` with executor
- Backend still uses `Workspace` + `Session` internally
- All type checks pass
Fixed. The issue was that the frontend was sending `task_attempt_id` as the query parameter, but the backend expected `workspace_id`. Now the execution processes WebSocket stream should work correctly and the "Loading History" should resolve.
* All done. Here's a summary of the changes:
1. **Added sessions endpoint** (`GET /api/sessions?workspace_id={uuid}`)
- Created `crates/server/src/routes/sessions.rs`
- Registered in `crates/server/src/routes/mod.rs`
- Added `Session::decl()` to `generate_types.rs`
2. **Removed TaskAttempt from backend**
- Removed `TaskAttempt` struct and methods from `crates/db/src/models/workspace.rs`
- Changed `TaskRelationships.current_attempt` back to `current_workspace: Workspace` in `task.rs`
- Updated route handlers to return `Workspace` instead of `TaskAttempt`
1. **Created `TaskAttempt` type** in `frontend/src/types/attempt.ts`
- Defines `TaskAttempt = Workspace & { executor: string }`
- Exports `createTaskAttempt()` helper function
2. **Updated `api.ts`**
- Added `sessionsApi` for fetching sessions
- Added `workspaceToTaskAttempt()` helper that fetches sessions and constructs TaskAttempt
- Updated `attemptsApi.getAll()`, `get()`, and `create()` to internally convert Workspace → TaskAttempt
3. **Updated 20+ frontend files** to import `TaskAttempt` from `@/types/attempt` instead of `shared/types`
- Backend returns `Workspace` directly (no executor field)
- Backend has new `/api/sessions` endpoint to fetch sessions by workspace
- Frontend constructs `TaskAttempt` by combining `Workspace` + latest `Session.executor`
- All type checks pass
* The refactoring is complete. Here's a summary of what was done:
- `TaskAttempt` is now just a type alias for `Workspace` (no executor needed for most uses)
- Added `WorkspaceWithSession = Workspace & { executor: string }` for components that need executor
- Added `createWorkspaceWithSession()` helper function
- `attemptsApi.get()`, `getAll()`, `create()` now return `Workspace` directly (as `TaskAttempt`)
- Added `attemptsApi.getWithSession()` - fetches workspace + session to get executor
- Added `sessionsApi.getByWorkspace()` for fetching sessions
- Added `useTaskAttemptWithSession()` - for single attempt with executor
- Added `useTaskAttemptsWithSessions()` - for list of attempts with executor
Files that access `.executor` now use `WorkspaceWithSession`:
- `TaskPanel.tsx` - Uses `useTaskAttemptsWithSessions` and `useTaskAttemptWithSession`
- `NextActionCard.tsx` - Uses `attemptsApi.getWithSession()`
- `UserMessage.tsx` - Receives `WorkspaceWithSession` prop
- `RetryEditorInline.tsx` - Receives `WorkspaceWithSession` prop
- `DisplayConversationEntry.tsx` - Passes `WorkspaceWithSession` to children
- `VirtualizedList.tsx` - Receives `WorkspaceWithSession` prop
- `TaskAttemptPanel.tsx` - Receives `WorkspaceWithSession` prop
- `ProjectTasks.tsx` - Uses `useTaskAttemptWithSession`
- `FullAttemptLogs.tsx` - Uses `useTaskAttemptWithSession`
- `CreateAttemptDialog.tsx` - Uses `useTaskAttemptsWithSessions`
The 32 other files that only use Workspace fields continue to use `TaskAttempt` (which is just `Workspace`) without any changes needed.
Done! I've simplified the migration from 191 lines down to 106 lines by:
1. **Removed workspaces table rebuild** → simple `ALTER TABLE workspaces DROP COLUMN executor`
2. **Removed merges table rebuild** → simple `ALTER TABLE merges RENAME COLUMN task_attempt_id TO workspace_id`
3. **Removed tasks table rebuild** → simple `ALTER TABLE tasks RENAME COLUMN parent_task_attempt TO parent_workspace_id`
4. **Removed attempt_repos rebuild entirely** → FK auto-updates when `task_attempts` is renamed to `workspaces`
The only table rebuilds remaining are for:
- `execution_processes` - because the FK target changes from workspaces to sessions
- `executor_sessions` → `coding_agent_turns` - because we're dropping the `task_attempt_id` column
All done:
- **npm run lint** - passed (fixed 4 unused import errors)
- **cargo build** - passed
- **npm run build** - passed
- **tsc --noEmit** - passed
Prep db
* Done. I've renamed `TaskAttempt` to `Workspace` in all places where it was used as a type annotation. Here's the summary:
- `types/attempt.ts` - Removed `export type TaskAttempt = Workspace;`
**API Layer:**
- `lib/api.ts` - Changed return types from `TaskAttempt` to `Workspace`
**Hooks:**
- `hooks/useTaskAttempts.ts` - `TaskAttempt[]` → `Workspace[]`
- `hooks/useAttemptCreation.ts` - `TaskAttempt` → `Workspace`
- `hooks/useConversationHistory.ts` - `TaskAttempt` → `Workspace`
- `hooks/useAttempt.ts` - `TaskAttempt` → `Workspace`
**Components:**
- `contexts/ClickedElementsProvider.tsx`
- `components/DiffCard.tsx`
- `components/panels/AttemptHeaderActions.tsx`
- `components/panels/DiffsPanel.tsx`
- `components/tasks/Toolbar/GitOperations.tsx`
- `components/dialogs/tasks/GitActionsDialog.tsx`
- `components/dialogs/tasks/ViewRelatedTasksDialog.tsx`
- `components/dialogs/tasks/CreatePRDialog.tsx`
- `components/ui/actions-dropdown.tsx`
**Type Definitions:**
- `types/modal-args.d.ts`
- `types/modals.ts`
**Pages:**
- `pages/ProjectTasks.tsx`
TypeScript check passes with no errors.
Cleanup script changes for task attempt 2f672d73-cb46-4515-b1c7-3da8f4402858
* The Session type now has `executor: string | null`, which is correct. All changes are complete:
1. **Migration**: `executor TEXT` (no `NOT NULL`)
2. **Rust model**: `executor: Option<String>`
3. **sqlx queries**: Using just `executor` without type annotation (sqlx infers nullable correctly)
4. **All usages**: Wrapped string values in `Some()` where executor is set
5. **TypeScript types**: `executor: string | null`
Everything builds and lints successfully.
Done. Removed `Session::parent_workspace` and its unused `Workspace` import.
* Done. The migration has been updated with the sqlx workaround:
1. Added `COMMIT TRANSACTION;` after `PRAGMA foreign_keys = OFF;` to end sqlx's auto-transaction
2. Added `BEGIN TRANSACTION;` to start our own controlled transaction
3. Added `PRAGMA foreign_key_check;` before committing to verify FK integrity
4. Added `COMMIT;` to commit our transaction
5. Added final `BEGIN TRANSACTION;` for sqlx to close gracefully
This ensures the `PRAGMA foreign_keys = OFF` actually takes effect, preventing potential cascade deletes of `execution_process_logs` when `DROP TABLE execution_processes` runs on existing databases with data.
Fixed. The migration now has the correct order:
1. `COMMIT TRANSACTION;` - ends sqlx's auto-transaction
2. `PRAGMA foreign_keys = OFF;` - now takes effect (outside transaction)
3. `BEGIN TRANSACTION;` - starts our controlled transaction
This ensures foreign keys are actually disabled before the table operations, preventing potential cascade deletes of `execution_process_logs` when `DROP TABLE execution_processes` runs.
Done. The migration now only disables foreign keys for the section that needs it (steps 7-8, the table rebuilds with DROP TABLE). Steps 1-6 run in sqlx's normal auto-transaction with FK enforcement on.
Fix slow statement (vibe-kanban b695d0ad)
i think we are missing an index on something, seeing these logs:
2025-12-17T15:23:25.297852Z WARN sqlx::query: slow statement: execution time exceeded alert threshold *summary*="SELECT t.id AS \\"id!: …" *db.statement*="\\n\\nSELECT\\n t.id AS \\"id!: Uuid\\",\\n t.project\_id AS \\"project\_id!: Uuid\\",\\n t.title,\\n t.description,\\n t.status AS \\"status!: TaskStatus\\",\\n t.parent\_workspace\_id AS \\"parent\_workspace\_id: Uuid\\",\\n t.shared\_task\_id AS \\"shared\_task\_id: Uuid\\",\\n t.created\_at AS \\"created\_at!: DateTime<Utc>\\",\\n t.updated\_at AS \\"updated\_at!: DateTime<Utc>\\",\\n\\n CASE WHEN EXISTS (\\n SELECT 1\\n FROM workspaces w\\n JOIN sessions s ON s.workspace\_id = w.id\\n JOIN execution\_processes ep ON ep.session\_id = s.id\\n WHERE w.task\_id = t.id\\n AND ep.status = 'running'\\n AND ep.run\_reason IN ('setupscript','cleanupscript','codingagent')\\n LIMIT 1\\n ) THEN 1 ELSE 0 END AS \\"has\_in\_progress\_attempt!: i64\\",\\n\\n CASE WHEN (\\n SELECT ep.status\\n FROM workspaces w\\n JOIN sessions s ON s.workspace\_id = w.id\\n JOIN execution\_processes ep ON ep.session\_id = s.id\\n WHERE w.task\_id = t.id\\n AND ep.run\_reason IN ('setupscript','cleanupscript','codingagent')\\n ORDER BY ep.created\_at DESC\\n LIMIT 1\\n ) IN ('failed','killed') THEN 1 ELSE 0 END\\n AS \\"last\_attempt\_failed!: i64\\",\\n\\n ( SELECT s.executor\\n FROM workspaces w\\n JOIN sessions s ON s.workspace\_id = w.id\\n WHERE w.task\_id = t.id\\n ORDER BY s.created\_at DESC\\n LIMIT 1\\n ) AS \\"executor!: String\\"\\n\\nFROM tasks t\\nWHERE t.project\_id = $1\\nORDER BY t.created\_at DESC\\n" *rows\_affected*=0 *rows\_returned*=202 *elapsed*=1.281210542s *elapsed\_secs*=1.281210542 *slow\_threshold*=1s
2025-12-17T15:23:25.350788Z WARN sqlx::query: slow statement: execution time exceeded alert threshold *summary*="SELECT t.id AS \\"id!: …" *db.statement*="\\n\\nSELECT\\n t.id AS \\"id!: Uuid\\",\\n t.project\_id AS \\"project\_id!: Uuid\\",\\n t.title,\\n t.description,\\n t.status AS \\"status!: TaskStatus\\",\\n t.parent\_workspace\_id AS \\"parent\_workspace\_id: Uuid\\",\\n t.shared\_task\_id AS \\"shared\_task\_id: Uuid\\",\\n t.created\_at AS \\"created\_at!: DateTime<Utc>\\",\\n t.updated\_at AS \\"updated\_at!: DateTime<Utc>\\",\\n\\n CASE WHEN EXISTS (\\n SELECT 1\\n FROM workspaces w\\n JOIN sessions s ON s.workspace\_id = w.id\\n JOIN execution\_processes ep ON ep.session\_id = s.id\\n WHERE w.task\_id = t.id\\n AND ep.status = 'running'\\n AND ep.run\_reason IN ('setupscript','cleanupscript','codingagent')\\n LIMIT 1\\n ) THEN 1 ELSE 0 END AS \\"has\_in\_progress\_attempt!: i64\\",\\n\\n CASE WHEN (\\n SELECT ep.status\\n FROM workspaces w\\n JOIN sessions s ON s.workspace\_id = w.id\\n JOIN execution\_processes ep ON ep.session\_id = s.id\\n WHERE w.task\_id = t.id\\n AND ep.run\_reason IN ('setupscript','cleanupscript','codingagent')\\n ORDER BY ep.created\_at DESC\\n LIMIT 1\\n ) IN ('failed','killed') THEN 1 ELSE 0 END\\n AS \\"last\_attempt\_failed!: i64\\",\\n\\n ( SELECT s.executor\\n FROM workspaces w\\n JOIN sessions s ON s.workspace\_id = w.id\\n WHERE w.task\_id = t.id\\n ORDER BY s.created\_at DESC\\n LIMIT 1\\n ) AS \\"executor!: String\\"\\n\\nFROM tasks t\\nWHERE t.project\_id = $1\\nORDER BY t.created\_at DESC\\n" *rows\_affected*=0 *rows\_returned*=202 *elapsed*=1.333812833s *elapsed\_secs*=1.333812833 *slow\_threshold*=1s
2025-12-17T15:23:25.401326Z WARN sqlx::query: slow statement: execution time exceeded alert threshold *summary*="INSERT INTO execution\_processes ( …" *db.statement*="\\n\\nINSERT INTO execution\_processes (\\n id, session\_id, run\_reason, executor\_action,\\n status, exit\_code, started\_at, completed\_at, created\_at, updated\_at\\n ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)\\n" *rows\_affected*=1 *rows\_returned*=0 *elapsed*=1.383690208s *elapsed\_secs*=1.383690208 *slow\_threshold*=1s
* Address feedback (vibe-kanban 81d8dbfa)
A PR opened by your colleague (https://github.com/BloopAI/vibe-kanban/pull/1569)
got some feedback, let's address it.
```gh-comment
{
"id": "2627479232",
"comment_type": "review",
"author": "ggordonhall",
"body": "```suggestion\r\n-- 3. Migrate data: create one session per workspace\r\nINSERT INTO sessions (id, workspace_id, executor, created_at, updated_at)\r\nSELECT gen_random_uuid(), id, executor, created_at, updated_at FROM workspaces;\r\n```\r\n",
"created_at": "2025-12-17T15:17:50Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627479232",
"path": "crates/db/migrations/20251216142123_refactor_task_attempts_to_workspaces_sessions.sql",
"line": 26,
"diff_hunk": "@@ -0,0 +1,121 @@\n+-- Refactor task_attempts into workspaces and sessions\n+-- - Rename task_attempts -> workspaces (keeps workspace-related fields)\n+-- - Create sessions table (executor moves here)\n+-- - Update execution_processes.task_attempt_id -> session_id\n+-- - Rename executor_sessions -> coding_agent_turns (drop redundant task_attempt_id)\n+-- - Rename merges.task_attempt_id -> workspace_id\n+-- - Rename tasks.parent_task_attempt -> parent_workspace_id\n+\n+-- 1. Rename task_attempts to workspaces (FK refs auto-update in schema)\n+ALTER TABLE task_attempts RENAME TO workspaces;\n+\n+-- 2. Create sessions table\n+CREATE TABLE sessions (\n+ id BLOB PRIMARY KEY,\n+ workspace_id BLOB NOT NULL,\n+ executor TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (workspace_id) REFERENCES workspaces(id) ON DELETE CASCADE\n+);\n+\n+CREATE INDEX idx_sessions_workspace_id ON sessions(workspace_id);\n+\n+-- 3. Migrate data: create one session per workspace (using workspace.id as session.id for simplicity)\n+INSERT INTO sessions (id, workspace_id, executor, created_at, updated_at)\n+SELECT id, id, executor, created_at, updated_at FROM workspaces;"
}
```
```gh-comment
{
"id": "2627515578",
"comment_type": "review",
"author": "ggordonhall",
"body": "Why not rename `attempt_repos` to `workspace_repos` here now that `attempt` is a legacy concept?",
"created_at": "2025-12-17T15:27:21Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627515578",
"path": "crates/db/migrations/20251216142123_refactor_task_attempts_to_workspaces_sessions.sql",
"line": 118,
"diff_hunk": "@@ -0,0 +1,121 @@\n+-- Refactor task_attempts into workspaces and sessions\n+-- - Rename task_attempts -> workspaces (keeps workspace-related fields)\n+-- - Create sessions table (executor moves here)\n+-- - Update execution_processes.task_attempt_id -> session_id\n+-- - Rename executor_sessions -> coding_agent_turns (drop redundant task_attempt_id)\n+-- - Rename merges.task_attempt_id -> workspace_id\n+-- - Rename tasks.parent_task_attempt -> parent_workspace_id\n+\n+-- 1. Rename task_attempts to workspaces (FK refs auto-update in schema)\n+ALTER TABLE task_attempts RENAME TO workspaces;\n+\n+-- 2. Create sessions table\n+CREATE TABLE sessions (\n+ id BLOB PRIMARY KEY,\n+ workspace_id BLOB NOT NULL,\n+ executor TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (workspace_id) REFERENCES workspaces(id) ON DELETE CASCADE\n+);\n+\n+CREATE INDEX idx_sessions_workspace_id ON sessions(workspace_id);\n+\n+-- 3. Migrate data: create one session per workspace (using workspace.id as session.id for simplicity)\n+INSERT INTO sessions (id, workspace_id, executor, created_at, updated_at)\n+SELECT id, id, executor, created_at, updated_at FROM workspaces;\n+\n+-- 4. Drop executor column from workspaces\n+ALTER TABLE workspaces DROP COLUMN executor;\n+\n+-- 5. Rename merges.task_attempt_id to workspace_id\n+DROP INDEX idx_merges_task_attempt_id;\n+DROP INDEX idx_merges_open_pr;\n+ALTER TABLE merges RENAME COLUMN task_attempt_id TO workspace_id;\n+CREATE INDEX idx_merges_workspace_id ON merges(workspace_id);\n+CREATE INDEX idx_merges_open_pr ON merges(workspace_id, pr_status)\n+WHERE merge_type = 'pr' AND pr_status = 'open';\n+\n+-- 6. Rename tasks.parent_task_attempt to parent_workspace_id\n+DROP INDEX IF EXISTS idx_tasks_parent_task_attempt;\n+ALTER TABLE tasks RENAME COLUMN parent_task_attempt TO parent_workspace_id;\n+CREATE INDEX idx_tasks_parent_workspace_id ON tasks(parent_workspace_id);\n+\n+-- Steps 7-8 need FK disabled to avoid cascade deletes during DROP TABLE\n+-- sqlx workaround: end auto-transaction to allow PRAGMA to take effect\n+-- https://github.com/launchbadge/sqlx/issues/2085#issuecomment-1499859906\n+COMMIT;\n+\n+PRAGMA foreign_keys = OFF;\n+\n+BEGIN TRANSACTION;\n+\n+-- 7. Update execution_processes to reference session_id instead of task_attempt_id\n+-- (needs rebuild because FK target changes from workspaces to sessions)\n+DROP INDEX IF EXISTS idx_execution_processes_task_attempt_created_at;\n+DROP INDEX IF EXISTS idx_execution_processes_task_attempt_type_created;\n+\n+CREATE TABLE execution_processes_new (\n+ id BLOB PRIMARY KEY,\n+ session_id BLOB NOT NULL,\n+ run_reason TEXT NOT NULL DEFAULT 'setupscript'\n+ CHECK (run_reason IN ('setupscript','codingagent','devserver','cleanupscript')),\n+ executor_action TEXT NOT NULL DEFAULT '{}',\n+ status TEXT NOT NULL DEFAULT 'running'\n+ CHECK (status IN ('running','completed','failed','killed')),\n+ exit_code INTEGER,\n+ dropped INTEGER NOT NULL DEFAULT 0,\n+ started_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ completed_at TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE\n+);\n+\n+-- Since we used workspace.id as session.id, the task_attempt_id values map directly\n+INSERT INTO execution_processes_new (id, session_id, run_reason, executor_action, status, exit_code, dropped, started_at, completed_at, created_at, updated_at)\n+SELECT id, task_attempt_id, run_reason, executor_action, status, exit_code, dropped, started_at, completed_at, created_at, updated_at\n+FROM execution_processes;\n+\n+DROP TABLE execution_processes;\n+ALTER TABLE execution_processes_new RENAME TO execution_processes;\n+\n+-- Recreate execution_processes indexes\n+CREATE INDEX idx_execution_processes_session_id ON execution_processes(session_id);\n+CREATE INDEX idx_execution_processes_status ON execution_processes(status);\n+CREATE INDEX idx_execution_processes_run_reason ON execution_processes(run_reason);\n+\n+-- 8. Rename executor_sessions to coding_agent_turns and drop task_attempt_id\n+-- (needs rebuild to drop the redundant task_attempt_id column)\n+CREATE TABLE coding_agent_turns (\n+ id BLOB PRIMARY KEY,\n+ execution_process_id BLOB NOT NULL,\n+ session_id TEXT,\n+ prompt TEXT,\n+ summary TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (execution_process_id) REFERENCES execution_processes(id) ON DELETE CASCADE\n+);\n+\n+INSERT INTO coding_agent_turns (id, execution_process_id, session_id, prompt, summary, created_at, updated_at)\n+SELECT id, execution_process_id, session_id, prompt, summary, created_at, updated_at\n+FROM executor_sessions;\n+\n+DROP TABLE executor_sessions;\n+\n+-- Recreate coding_agent_turns indexes\n+CREATE INDEX idx_coding_agent_turns_execution_process_id ON coding_agent_turns(execution_process_id);\n+CREATE INDEX idx_coding_agent_turns_session_id ON coding_agent_turns(session_id);\n+\n+-- 9. attempt_repos: no changes needed - FK auto-updated when task_attempts renamed to workspaces"
}
```
```gh-comment
{
"id": "2627694792",
"comment_type": "review",
"author": "ggordonhall",
"body": "Maybe there's a better name than `external_session_id` here? `agent_session_id`? ",
"created_at": "2025-12-17T16:16:24Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627694792",
"path": "crates/db/src/models/execution_process.rs",
"line": 685,
"diff_hunk": "@@ -618,4 +680,34 @@ impl ExecutionProcess {\n )),\n }\n }\n+\n+ /// Find latest coding_agent_turn session_id by workspace (across all sessions)\n+ pub async fn find_latest_external_session_id_by_workspace("
}
```
```gh-comment
{
"id": "2627707446",
"comment_type": "review",
"author": "ggordonhall",
"body": "```suggestion\r\n pub async fn cleanup_workspace(db: &DBService, workspace: &Workspace) {\r\n```",
"created_at": "2025-12-17T16:19:31Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627707446",
"path": "crates/local-deployment/src/container.rs",
"line": 146,
"diff_hunk": "@@ -142,20 +143,20 @@ impl LocalContainerService {\n map.remove(id)\n }\n \n- pub async fn cleanup_attempt_workspace(db: &DBService, attempt: &TaskAttempt) {\n- let Some(container_ref) = &attempt.container_ref else {\n+ pub async fn cleanup_workspace_container(db: &DBService, workspace: &Workspace) {"
}
```
```gh-comment
{
"id": "2627756192",
"comment_type": "review",
"author": "ggordonhall",
"body": "Update `mcp` nomenclature",
"created_at": "2025-12-17T16:31:49Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627756192",
"path": "crates/server/src/mcp/task_server.rs",
"line": 352,
"diff_hunk": "@@ -350,10 +349,9 @@ impl TaskServer {\n project_id: ctx.project.id,\n task_id: ctx.task.id,\n task_title: ctx.task.title,\n- attempt_id: ctx.task_attempt.id,\n- attempt_branch: ctx.task_attempt.branch,\n+ attempt_id: ctx.workspace.id,"
}
```
```gh-comment
{
"id": "2628161769",
"comment_type": "review",
"author": "ggordonhall",
"body": "update, and similar in other events",
"created_at": "2025-12-17T18:27:47Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2628161769",
"path": "crates/server/src/routes/task_attempts.rs",
"line": 1335,
"diff_hunk": "@@ -1295,7 +1332,7 @@ pub async fn start_dev_server(\n serde_json::json!({\n \"task_id\": task.id.to_string(),\n \"project_id\": project.id.to_string(),\n- \"attempt_id\": task_attempt.id.to_string(),\n+ \"attempt_id\": workspace.id.to_string(),"
}
```
```gh-comment
{
"id": "2628194289",
"comment_type": "review",
"author": "ggordonhall",
"body": "Ugly, but we should rename this struct to avoid confusion with the more general concept of a workspace. Ideas...\r\n\r\n- `WorktreeContainer`\r\n...\r\n...\r\n\r\nChatGPT?",
"created_at": "2025-12-17T18:36:30Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2628194289",
"path": "crates/services/src/services/workspace_manager.rs",
"line": 3,
"diff_hunk": "@@ -1,6 +1,6 @@\n use std::path::{Path, PathBuf};\n \n-use db::models::{repo::Repo, task_attempt::TaskAttempt};\n+use db::models::{repo::Repo, workspace::Workspace as DbWorkspace};"
}
```
```gh-comment
{
"id": "2628198036",
"comment_type": "review",
"author": "ggordonhall",
"body": "We could add a BE route for this, and similar hooks where we're aggregating this information on the fly",
"created_at": "2025-12-17T18:37:46Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2628198036",
"path": "frontend/src/hooks/useTaskAttempts.ts",
"line": 43,
"diff_hunk": "@@ -16,10 +20,36 @@ export function useTaskAttempts(taskId?: string, opts?: Options) {\n const enabled = (opts?.enabled ?? true) && !!taskId;\n const refetchInterval = opts?.refetchInterval ?? 5000;\n \n- return useQuery<TaskAttempt[]>({\n+ return useQuery<Workspace[]>({\n queryKey: taskAttemptKeys.byTask(taskId),\n queryFn: () => attemptsApi.getAll(taskId!),\n enabled,\n refetchInterval,\n });\n }\n+\n+/**\n+ * Hook for components that need executor field for all attempts.\n+ * Fetches all attempts and their sessions in parallel.\n+ */\n+export function useTaskAttemptsWithSessions(taskId?: string, opts?: Options) {\n+ const enabled = (opts?.enabled ?? true) && !!taskId;\n+ const refetchInterval = opts?.refetchInterval ?? 5000;\n+\n+ return useQuery<WorkspaceWithSession[]>({\n+ queryKey: taskAttemptKeys.byTaskWithSessions(taskId),\n+ queryFn: async () => {\n+ const attempts = await attemptsApi.getAll(taskId!);\n+ // Fetch sessions for all attempts in parallel"
}
```
* Address feedback (vibe-kanban 81d8dbfa)
A PR opened by your colleague (https://github.com/BloopAI/vibe-kanban/pull/1569)
got some feedback, let's address it.
```gh-comment
{
"id": "2627479232",
"comment_type": "review",
"author": "ggordonhall",
"body": "```suggestion\r\n-- 3. Migrate data: create one session per workspace\r\nINSERT INTO sessions (id, workspace_id, executor, created_at, updated_at)\r\nSELECT gen_random_uuid(), id, executor, created_at, updated_at FROM workspaces;\r\n```\r\n",
"created_at": "2025-12-17T15:17:50Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627479232",
"path": "crates/db/migrations/20251216142123_refactor_task_attempts_to_workspaces_sessions.sql",
"line": 26,
"diff_hunk": "@@ -0,0 +1,121 @@\n+-- Refactor task_attempts into workspaces and sessions\n+-- - Rename task_attempts -> workspaces (keeps workspace-related fields)\n+-- - Create sessions table (executor moves here)\n+-- - Update execution_processes.task_attempt_id -> session_id\n+-- - Rename executor_sessions -> coding_agent_turns (drop redundant task_attempt_id)\n+-- - Rename merges.task_attempt_id -> workspace_id\n+-- - Rename tasks.parent_task_attempt -> parent_workspace_id\n+\n+-- 1. Rename task_attempts to workspaces (FK refs auto-update in schema)\n+ALTER TABLE task_attempts RENAME TO workspaces;\n+\n+-- 2. Create sessions table\n+CREATE TABLE sessions (\n+ id BLOB PRIMARY KEY,\n+ workspace_id BLOB NOT NULL,\n+ executor TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (workspace_id) REFERENCES workspaces(id) ON DELETE CASCADE\n+);\n+\n+CREATE INDEX idx_sessions_workspace_id ON sessions(workspace_id);\n+\n+-- 3. Migrate data: create one session per workspace (using workspace.id as session.id for simplicity)\n+INSERT INTO sessions (id, workspace_id, executor, created_at, updated_at)\n+SELECT id, id, executor, created_at, updated_at FROM workspaces;"
}
```
```gh-comment
{
"id": "2627515578",
"comment_type": "review",
"author": "ggordonhall",
"body": "Why not rename `attempt_repos` to `workspace_repos` here now that `attempt` is a legacy concept?",
"created_at": "2025-12-17T15:27:21Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627515578",
"path": "crates/db/migrations/20251216142123_refactor_task_attempts_to_workspaces_sessions.sql",
"line": 118,
"diff_hunk": "@@ -0,0 +1,121 @@\n+-- Refactor task_attempts into workspaces and sessions\n+-- - Rename task_attempts -> workspaces (keeps workspace-related fields)\n+-- - Create sessions table (executor moves here)\n+-- - Update execution_processes.task_attempt_id -> session_id\n+-- - Rename executor_sessions -> coding_agent_turns (drop redundant task_attempt_id)\n+-- - Rename merges.task_attempt_id -> workspace_id\n+-- - Rename tasks.parent_task_attempt -> parent_workspace_id\n+\n+-- 1. Rename task_attempts to workspaces (FK refs auto-update in schema)\n+ALTER TABLE task_attempts RENAME TO workspaces;\n+\n+-- 2. Create sessions table\n+CREATE TABLE sessions (\n+ id BLOB PRIMARY KEY,\n+ workspace_id BLOB NOT NULL,\n+ executor TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (workspace_id) REFERENCES workspaces(id) ON DELETE CASCADE\n+);\n+\n+CREATE INDEX idx_sessions_workspace_id ON sessions(workspace_id);\n+\n+-- 3. Migrate data: create one session per workspace (using workspace.id as session.id for simplicity)\n+INSERT INTO sessions (id, workspace_id, executor, created_at, updated_at)\n+SELECT id, id, executor, created_at, updated_at FROM workspaces;\n+\n+-- 4. Drop executor column from workspaces\n+ALTER TABLE workspaces DROP COLUMN executor;\n+\n+-- 5. Rename merges.task_attempt_id to workspace_id\n+DROP INDEX idx_merges_task_attempt_id;\n+DROP INDEX idx_merges_open_pr;\n+ALTER TABLE merges RENAME COLUMN task_attempt_id TO workspace_id;\n+CREATE INDEX idx_merges_workspace_id ON merges(workspace_id);\n+CREATE INDEX idx_merges_open_pr ON merges(workspace_id, pr_status)\n+WHERE merge_type = 'pr' AND pr_status = 'open';\n+\n+-- 6. Rename tasks.parent_task_attempt to parent_workspace_id\n+DROP INDEX IF EXISTS idx_tasks_parent_task_attempt;\n+ALTER TABLE tasks RENAME COLUMN parent_task_attempt TO parent_workspace_id;\n+CREATE INDEX idx_tasks_parent_workspace_id ON tasks(parent_workspace_id);\n+\n+-- Steps 7-8 need FK disabled to avoid cascade deletes during DROP TABLE\n+-- sqlx workaround: end auto-transaction to allow PRAGMA to take effect\n+-- https://github.com/launchbadge/sqlx/issues/2085#issuecomment-1499859906\n+COMMIT;\n+\n+PRAGMA foreign_keys = OFF;\n+\n+BEGIN TRANSACTION;\n+\n+-- 7. Update execution_processes to reference session_id instead of task_attempt_id\n+-- (needs rebuild because FK target changes from workspaces to sessions)\n+DROP INDEX IF EXISTS idx_execution_processes_task_attempt_created_at;\n+DROP INDEX IF EXISTS idx_execution_processes_task_attempt_type_created;\n+\n+CREATE TABLE execution_processes_new (\n+ id BLOB PRIMARY KEY,\n+ session_id BLOB NOT NULL,\n+ run_reason TEXT NOT NULL DEFAULT 'setupscript'\n+ CHECK (run_reason IN ('setupscript','codingagent','devserver','cleanupscript')),\n+ executor_action TEXT NOT NULL DEFAULT '{}',\n+ status TEXT NOT NULL DEFAULT 'running'\n+ CHECK (status IN ('running','completed','failed','killed')),\n+ exit_code INTEGER,\n+ dropped INTEGER NOT NULL DEFAULT 0,\n+ started_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ completed_at TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE\n+);\n+\n+-- Since we used workspace.id as session.id, the task_attempt_id values map directly\n+INSERT INTO execution_processes_new (id, session_id, run_reason, executor_action, status, exit_code, dropped, started_at, completed_at, created_at, updated_at)\n+SELECT id, task_attempt_id, run_reason, executor_action, status, exit_code, dropped, started_at, completed_at, created_at, updated_at\n+FROM execution_processes;\n+\n+DROP TABLE execution_processes;\n+ALTER TABLE execution_processes_new RENAME TO execution_processes;\n+\n+-- Recreate execution_processes indexes\n+CREATE INDEX idx_execution_processes_session_id ON execution_processes(session_id);\n+CREATE INDEX idx_execution_processes_status ON execution_processes(status);\n+CREATE INDEX idx_execution_processes_run_reason ON execution_processes(run_reason);\n+\n+-- 8. Rename executor_sessions to coding_agent_turns and drop task_attempt_id\n+-- (needs rebuild to drop the redundant task_attempt_id column)\n+CREATE TABLE coding_agent_turns (\n+ id BLOB PRIMARY KEY,\n+ execution_process_id BLOB NOT NULL,\n+ session_id TEXT,\n+ prompt TEXT,\n+ summary TEXT,\n+ created_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ updated_at TEXT NOT NULL DEFAULT (datetime('now', 'subsec')),\n+ FOREIGN KEY (execution_process_id) REFERENCES execution_processes(id) ON DELETE CASCADE\n+);\n+\n+INSERT INTO coding_agent_turns (id, execution_process_id, session_id, prompt, summary, created_at, updated_at)\n+SELECT id, execution_process_id, session_id, prompt, summary, created_at, updated_at\n+FROM executor_sessions;\n+\n+DROP TABLE executor_sessions;\n+\n+-- Recreate coding_agent_turns indexes\n+CREATE INDEX idx_coding_agent_turns_execution_process_id ON coding_agent_turns(execution_process_id);\n+CREATE INDEX idx_coding_agent_turns_session_id ON coding_agent_turns(session_id);\n+\n+-- 9. attempt_repos: no changes needed - FK auto-updated when task_attempts renamed to workspaces"
}
```
```gh-comment
{
"id": "2627694792",
"comment_type": "review",
"author": "ggordonhall",
"body": "Maybe there's a better name than `external_session_id` here? `agent_session_id`? ",
"created_at": "2025-12-17T16:16:24Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627694792",
"path": "crates/db/src/models/execution_process.rs",
"line": 685,
"diff_hunk": "@@ -618,4 +680,34 @@ impl ExecutionProcess {\n )),\n }\n }\n+\n+ /// Find latest coding_agent_turn session_id by workspace (across all sessions)\n+ pub async fn find_latest_external_session_id_by_workspace("
}
```
```gh-comment
{
"id": "2627707446",
"comment_type": "review",
"author": "ggordonhall",
"body": "```suggestion\r\n pub async fn cleanup_workspace(db: &DBService, workspace: &Workspace) {\r\n```",
"created_at": "2025-12-17T16:19:31Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627707446",
"path": "crates/local-deployment/src/container.rs",
"line": 146,
"diff_hunk": "@@ -142,20 +143,20 @@ impl LocalContainerService {\n map.remove(id)\n }\n \n- pub async fn cleanup_attempt_workspace(db: &DBService, attempt: &TaskAttempt) {\n- let Some(container_ref) = &attempt.container_ref else {\n+ pub async fn cleanup_workspace_container(db: &DBService, workspace: &Workspace) {"
}
```
```gh-comment
{
"id": "2627756192",
"comment_type": "review",
"author": "ggordonhall",
"body": "Update `mcp` nomenclature",
"created_at": "2025-12-17T16:31:49Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2627756192",
"path": "crates/server/src/mcp/task_server.rs",
"line": 352,
"diff_hunk": "@@ -350,10 +349,9 @@ impl TaskServer {\n project_id: ctx.project.id,\n task_id: ctx.task.id,\n task_title: ctx.task.title,\n- attempt_id: ctx.task_attempt.id,\n- attempt_branch: ctx.task_attempt.branch,\n+ attempt_id: ctx.workspace.id,"
}
```
```gh-comment
{
"id": "2628161769",
"comment_type": "review",
"author": "ggordonhall",
"body": "update, and similar in other events",
"created_at": "2025-12-17T18:27:47Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2628161769",
"path": "crates/server/src/routes/task_attempts.rs",
"line": 1335,
"diff_hunk": "@@ -1295,7 +1332,7 @@ pub async fn start_dev_server(\n serde_json::json!({\n \"task_id\": task.id.to_string(),\n \"project_id\": project.id.to_string(),\n- \"attempt_id\": task_attempt.id.to_string(),\n+ \"attempt_id\": workspace.id.to_string(),"
}
```
```gh-comment
{
"id": "2628194289",
"comment_type": "review",
"author": "ggordonhall",
"body": "Ugly, but we should rename this struct to avoid confusion with the more general concept of a workspace. Ideas...\r\n\r\n- `WorktreeContainer`\r\n...\r\n...\r\n\r\nChatGPT?",
"created_at": "2025-12-17T18:36:30Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2628194289",
"path": "crates/services/src/services/workspace_manager.rs",
"line": 3,
"diff_hunk": "@@ -1,6 +1,6 @@\n use std::path::{Path, PathBuf};\n \n-use db::models::{repo::Repo, task_attempt::TaskAttempt};\n+use db::models::{repo::Repo, workspace::Workspace as DbWorkspace};"
}
```
```gh-comment
{
"id": "2628198036",
"comment_type": "review",
"author": "ggordonhall",
"body": "We could add a BE route for this, and similar hooks where we're aggregating this information on the fly",
"created_at": "2025-12-17T18:37:46Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1569#discussion_r2628198036",
"path": "frontend/src/hooks/useTaskAttempts.ts",
"line": 43,
"diff_hunk": "@@ -16,10 +20,36 @@ export function useTaskAttempts(taskId?: string, opts?: Options) {\n const enabled = (opts?.enabled ?? true) && !!taskId;\n const refetchInterval = opts?.refetchInterval ?? 5000;\n \n- return useQuery<TaskAttempt[]>({\n+ return useQuery<Workspace[]>({\n queryKey: taskAttemptKeys.byTask(taskId),\n queryFn: () => attemptsApi.getAll(taskId!),\n enabled,\n refetchInterval,\n });\n }\n+\n+/**\n+ * Hook for components that need executor field for all attempts.\n+ * Fetches all attempts and their sessions in parallel.\n+ */\n+export function useTaskAttemptsWithSessions(taskId?: string, opts?: Options) {\n+ const enabled = (opts?.enabled ?? true) && !!taskId;\n+ const refetchInterval = opts?.refetchInterval ?? 5000;\n+\n+ return useQuery<WorkspaceWithSession[]>({\n+ queryKey: taskAttemptKeys.byTaskWithSessions(taskId),\n+ queryFn: async () => {\n+ const attempts = await attemptsApi.getAll(taskId!);\n+ // Fetch sessions for all attempts in parallel"
}
```
|
||
|
Solomon
|
a282bbdae4 |
Real-time sync for Projects (#1512)
* Real-time sync for Projects * Do not create project in a transaction Update hooks trigger before the transaction is commited, which causes insert events to be dismissed because the row is isn't found |
||
|
Alex Netsch
|
f989b47470 |
Refactor branch fetching to use repo IDs instead of project IDs (Vibe Kanban) (#1560)
* All tasks are complete. Here's a summary of the changes made:
## Summary
Successfully refactored the project branches API to fetch branches using repo IDs instead of project IDs.
### Files Created
- `frontend/src/hooks/useRepoBranches.ts` - New hook that fetches branches for a single repository using `repoApi.getBranches(repoId)`
### Files Modified
1. **`frontend/src/hooks/index.ts`** - Added export for `useRepoBranches`
2. **`frontend/src/components/dialogs/tasks/GitActionsDialog.tsx`**
- Removed `useState` for `repoBranches` and `loadingBranches`
- Removed `useEffect` that called `projectsApi.getBranches(effectiveProjectId)`
- Removed `useMemo` that filtered branches by `selectedRepoId`
- Now uses `useRepoBranches(selectedRepoId)` to fetch branches directly for the selected repo from the task attempt
3. **`frontend/src/components/dialogs/tasks/CreatePRDialog.tsx`**
- Removed `projectId` from props interface and component destructuring
- Removed `useState` for `branches` and `branchesLoading`
- Removed branch-fetching logic from useEffect
- Now uses `useRepoBranches(repoId)` to fetch branches directly for the specified repo
- Split useEffect into two: one for form initialization, one for setting default base branch
4. **`frontend/src/components/tasks/Toolbar/GitOperations.tsx`**
- Removed `projectId` from `CreatePRDialog.show()` call
### Benefits
- More efficient - fetches only branches for the specific repo needed instead of all project repos
- Better caching - React Query caches branches per repo for efficient reuse
- Cleaner code - removed manual filtering logic from components
- Type safety - hooks return `GitBranch[]` directly instead of `RepositoryBranches[]`
* All tasks complete. Here's a summary of the changes made:
## Summary
Successfully decoupled the branches API from project IDs.
### Changes Made
**1. `frontend/src/hooks/useBranches.ts`** - Refactored to accept `repos: Array<{ id: string; name: string }>` instead of `projectId`
- Now uses `useQueries` to fetch branches for multiple repos in parallel
- Reuses the same query keys as `useRepoBranches` for cache consistency
**2. `frontend/src/hooks/useRepoBranchSelection.ts`** - Refactored to accept `repos: Repo[]` instead of `projectId`
- Removed internal fetch of project repos (caller now provides them)
- Removed `projectRepos` from return value
- Uses refactored `useBranches(repos)`
**3. `frontend/src/components/dialogs/tasks/CreateAttemptDialog.tsx`**
- Added `useQuery` to fetch project repos separately
- Passes `repos` to `useRepoBranchSelection`
**4. `frontend/src/components/dialogs/tasks/TaskFormDialog.tsx`**
- Already fetched `projectRepos`
- Updated to pass `projectRepos` to refactored `useBranches`
**5. `frontend/src/components/layout/Navbar.tsx`**
- Replaced `useBranches(projectId)` with `useQuery` for `projectsApi.getRepositories`
- Only needed repo count, not branches
**6. `frontend/src/components/projects/ProjectCard.tsx`**
- Replaced `useBranches(project.id)` with `useQuery` for `projectsApi.getRepositories`
- Only needed repo count, not branches
### Benefits
- Branch hooks no longer require a project ID
- Repos can come from any source (project, attempt, or future sources without projects)
- Better separation of concerns
- Enables future task attempts without projects attached
* Cleanup script changes for task attempt 6b5b9208-565d-4620-9fe3-20791db77d7a
* The fix is already applied. Type checks pass with `Repo[]` instead of the loose `Array<{ id: string; name: string }>` type.
This makes it explicit that `useBranches` expects actual `Repo` objects (with `Repo.id` being the repository's UUID), not project-repo junction records.
* All done. The refactor is complete:
**Summary of changes:**
1. **Created `useProjectRepos` hook** (`frontend/src/hooks/useProjectRepos.ts`) - A reusable hook that fetches project repositories with proper query key management
2. **Updated 5 files** to use the new hook instead of duplicating the `useQuery` pattern:
- `CreateAttemptDialog.tsx`
- `TaskFormDialog.tsx`
- `Navbar.tsx`
- `ProjectCard.tsx`
- `NoServerContent.tsx`
3. **Earlier refactors** (from before the summary):
- `useBranches.ts` - Now accepts `repos: Repo[]` instead of `projectId`
- `useRepoBranchSelection.ts` - Now accepts `repos: Repo[]` instead of `projectId`
This enables future task attempts without projects attached, as branch fetching is now decoupled from project IDs.
* No more usages. The branches in `ProjectTasks.tsx` are used for the diffs panel - showing available branches for git operations when viewing an attempt's diffs.
* Cleanup script changes for task attempt 6b5b9208-565d-4620-9fe3-20791db77d7a
* All done. The refactor is complete:
**Summary of changes:**
`GitOperations` now fetches its own branches using `useRepoBranches(selectedRepoId)` instead of receiving them as a prop. This:
1. Removes prop drilling through `ProjectTasks` → `DiffsPanelContainer` → `DiffsPanel` → `GitOperations`
2. Removes the need for `ProjectTasks` to fetch all project repos just to get branches for the selected repo
3. Makes `GitOperations` self-contained - it already has `selectedRepoId` from `useAttemptRepo`, so it can fetch its own branches
4. Simplifies `GitActionsDialog` which no longer needs to fetch branches either
* All done. Here's a summary of the changes:
**Removed `projectId` from GitOperations flow:**
1. **`useRebase.ts`** - Changed param from `projectId` to `repoId`, updated invalidation to use `repoBranchKeys.byRepo(repoId)`
2. **`useChangeTargetBranch.ts`** - Changed param from `projectId` to `repoId`, updated invalidation to use `repoBranchKeys.byRepo(repoId)`
3. **`useMerge.ts`** - Updated invalidation to use `repoBranchKeys.all` instead of `['projectBranches']`
4. **`useGitOperations.ts`** - Changed param from `projectId` to `repoId`
5. **`GitOperations.tsx`** - Removed `projectId` prop, now passes `selectedRepoId` to `useGitOperations`
6. **`GitActionsDialog.tsx`** - Removed `projectId` from props and internal logic
7. **`DiffsPanelContainer`** (in ProjectTasks.tsx) - Removed `projectId` prop
8. **Callers of `GitActionsDialog.show`** - Removed `projectId` from `NextActionCard.tsx` and `actions-dropdown.tsx`
* The cleanup is complete. Here's a summary of what was done:
**Removed dead project branches code:**
1. **Backend** (`crates/server/src/routes/projects.rs`):
- Removed `get_project_branches` handler and route
- Removed `RepositoryBranches` and `ProjectBranchesResponse` structs
- Fixed unused `Serialize` import warning
2. **Type Generation** (`crates/server/src/bin/generate_types.rs`):
- Removed exports for `ProjectBranchesResponse` and `RepositoryBranches`
3. **Frontend Hooks** (`frontend/src/hooks/useBranches.ts`):
- Defined local `RepositoryBranches` type instead of importing from shared/types
4. **Frontend API** (`frontend/src/lib/api.ts`):
- Removed `projectsApi.getBranches` method
- Removed `RepositoryBranches` and `ProjectBranchesResponse` imports
Both TypeScript and Rust compilation pass without errors.
* Done. Removed the `RepositoryBranches` type and simplified `useBranches` to return `Map<string, GitBranch[]>`. Changes:
1. **`useBranches.ts`** - Returns `Map<string, GitBranch[]>` instead of `RepositoryBranches[]`
2. **`useRepoBranchSelection.ts`** - Uses `branchMap.get(repo.id) ?? []` instead of `.find()`
3. **`TaskFormDialog.tsx`** - Uses `branchMap.get(repo.id) ?? []` instead of `.find()`
Type checks pass.
* Done. Deleted `useBranches` entirely and consolidated everything into `useRepoBranchSelection`. Summary:
1. **Deleted** `frontend/src/hooks/useBranches.ts`
2. **Updated** `useRepoBranchSelection.ts` - inlined the `useQueries` logic directly
3. **Updated** `hooks/index.ts` - removed `useBranches` export
4. **Updated** `TaskFormDialog.tsx` - now uses `useRepoBranchSelection` instead of duplicating the config-building logic
Type checks pass.
* types
|
||
|
Alex Netsch
|
ec8666da74 |
Add configurable working directory for dev server scripts (Vibe Kanban) (#1559)
* The implementation is complete. Here's a summary of all the changes made: ## Summary Added the ability for users to specify a working directory for dev server scripts: ### Files Changed: 1. **Database migration** - `crates/db/migrations/20251216000000_add_dev_script_working_dir_to_projects.sql` - Added `dev_script_working_dir TEXT DEFAULT ''` column 2. **Rust model** - `crates/db/src/models/project.rs` - Added `dev_script_working_dir` field to `Project` and `UpdateProject` structs - Updated all SQL queries 3. **Dev server execution** - `crates/server/src/routes/task_attempts.rs` - `start_dev_server` now passes `project.dev_script_working_dir` to the script executor 4. **Backfill logic** - `crates/services/src/services/container.rs` - Changed `backfill_repo_names` to set `dev_script_working_dir` instead of prepending `cd ./repo &&` 5. **Frontend UI** - `frontend/src/pages/settings/ProjectSettings.tsx` - Added input field for "Dev Server Working Directory" 6. **Translations** - `frontend/src/i18n/locales/en/settings.json` - Added `devWorkingDir` label, placeholder, and helper text 7. **TypeScript types** - `shared/types.ts` - Regenerated with `dev_script_working_dir` field * Cleanup script changes for task attempt 83423e2d-0d45-47fb-a6e4-dd91a2140f91 * Both packages compile successfully. The fix is complete: 1. **`project.rs`**: Removed `.or()` fallback for `dev_script` and `dev_script_working_dir` so `None` now clears the field 2. **`container.rs`**: Updated backfill to explicitly pass the existing project name instead of `None` * Done. I've completed both review tasks: 1. Removed the comment from `container.rs` line 384 2. Added `devWorkingDir` translations to all four language files (es, ja, ko, zh-Hans) with: - `label`: The field label - `placeholder`: Example placeholder text - `helper`: Description of what the field does I also updated the `dev.helper` text in each language to reference the new working directory option instead of suggesting users manually `cd` into the repo directory. * Done. Removed both comments: 1. Removed the comment from the migration file 2. Removed the comment from `task_attempts.rs` line 1267 * Fixed. The TypeScript error in `NoServerContent.tsx` has been resolved by adding `dev_script_working_dir: null` to the `UpdateProject` data. All checks pass: - ✅ `npm run format` - completed - ✅ `npm run lint` - passed (frontend and backend) - ✅ `npx tsc --noEmit` - passed * The Korean and Chinese translations already had the updated copy without the `cd` reference. The Spanish and Japanese were updated. All the translations now have the proper helper text that references the working directory field instead of telling users to manually `cd` into the repo. * Done. I've removed the `cd my_website` line from both the Windows and Unix script placeholder examples in `scriptPlaceholders.ts`. Now the placeholder examples just show `npm run dev` without the `cd` command, since users can specify the working directory separately. |
||
|
Gabriel Gordon-Hall
|
22ff27d8fd |
feat: multi repo projects (#1516)
* configure multiple repositories per project * Move repo selection to frontend for create PR (#1436) * Inline ensure worktree path (#1440) * Inline ensure_worktree_path in task_attempts * Inline ensure_worktree_path in images and setups, remove ensure_worktree_path * chore: use `find_repos_for_attempt` where possible (#1442) * use find_repos_for_attempt rather than find_repos_for_project where possible * remove Repo::find_by_attempt_id * change target branch backend (#1454) * feat: multi repo branch rename (#1456) * Rename branches * Update crates/services/src/services/git.rs Co-authored-by: Alex Netsch <alex@bloop.ai> --------- Co-authored-by: Alex Netsch <alex@bloop.ai> * Fix project display name being used as path (#1464) * Multi repo merge (#1470) * cleanup create PR * Merge for multi repo projects * Multi repo support for rebase (vibe-kanban) (#1472) * All tasks completed successfully. Here's a summary of the changes made: ## Summary Added multi-repo support for rebase, following the same pattern as merge (commit 483060e92). ### Files Modified **Backend:** 1. `crates/server/src/routes/task_attempts.rs`: - Added `repo_id: Uuid` field to `RebaseTaskAttemptRequest` struct (line 92) - Updated `rebase_task_attempt` function to: - Fetch specific `AttemptRepo` using `find_by_attempt_and_repo_id()` - Fetch the `Repo` using `Repo::find_by_id()` - Build `worktree_path` as `workspace_path.join(&repo.name)` - Use the specific repo's target branch - Update only that repo's target branch via `AttemptRepo::update_target_branch()` instead of `update_all_target_branches()` - Pass `worktree_path` to `rebase_branch()` instead of `workspace_path` **Frontend:** 2. `frontend/src/hooks/useRebase.ts`: - Added `repoId: string` to `RebaseMutationArgs` type - Pass `repo_id` in the request data 3. `frontend/src/components/tasks/Toolbar/GitOperations.tsx`: - Updated `handleRebaseWithNewBranchAndUpstream` to get `repoId` via `getSelectedRepoId()` and pass it to the rebase action **Auto-generated:** 4. `shared/types.ts` - Regenerated with `repo_id: string` in `RebaseTaskAttemptRequest` * All done. Both review comments have been addressed: 1. **Inlined `current_target_branch`** - Replaced the separate variable with `unwrap_or_else(|| attempt_repo.target_branch.clone())` calls directly 2. **Removed `update_all_target_branches`** - Deleted the unused function from `crates/db/src/models/attempt_repo.rs` since it's no longer needed after the multi-repo changes All checks pass. * Fix worktree name (#1483) * Add multi-repo support for rebase conflict handling (Vibe Kanban) (#1487) * All checks pass. Let me provide a summary of the changes made: I've added multi-repo support for the conflict handling (auto fix rebase) functionality. Here's what was changed: 1. Added `AbortConflictsRequest` struct with `repo_id: Uuid` field 2. Updated `abort_conflicts_task_attempt()` handler to: - Accept `repo_id` in the request body - Look up the specific repo by ID - Build the correct worktree path: `workspace_path.join(&repo.name)` - Pass the repo-specific worktree path to `abort_conflicts()` - Added `AbortConflictsRequest` to the list of exported types 1. **`frontend/src/lib/api.ts`**: - Updated `abortConflicts()` to accept `repoId` parameter and send it in the request body - Fixed `getBranchStatus()` return type from `BranchStatus[]` to `RepoBranchStatus[]` - Added `RepoBranchStatus` import, removed unused `BranchStatus` import 2. **`frontend/src/hooks/useAttemptConflicts.ts`**: - Added `repoId` parameter to the hook - Pass `repoId` to the API call 3. **`frontend/src/lib/conflicts.ts`**: - Added optional `repoName` parameter to `buildResolveConflictsInstructions()` - Added `repoName` parameter to `formatConflictHeader()` - Conflict resolution prompts now include repo context (e.g., "Rebase conflicts while rebasing 'branch' onto 'main' in repository 'my-repo'.") 4. **`frontend/src/components/tasks/follow-up/FollowUpConflictSection.tsx`**: - Updated `branchStatus` prop type from `BranchStatus[]` to `RepoBranchStatus[]` - Extract `repo_id` from first repo status and pass to `useAttemptConflicts()` 5. **`frontend/src/components/tasks/TaskFollowUpSection.tsx`**: - Pass `repo_name` to `buildResolveConflictsInstructions()` for multi-repo context in AI prompts Cleanup script changes for task attempt b833fb22-7a04-4c56-b82d-1afaa1074e78 * The type check passes. Now the `abortConflicts` API uses the generated `AbortConflictsRequest` type, which will catch any type mismatches if the backend type changes. * Done. Both components now find the first repo that actually has conflicts instead of just using the first repo in the array. The type check passes. * Done. Removed both comments as requested. * Multi-repo support for restoring commits (Vibe Kanban) (#1490) * I've successfully implemented multi-repo support for restoring commits. Here's a summary of the changes made: 1. **`crates/server/src/routes/execution_processes.rs`** - Added import for `ExecutionProcessRepoState` - Added new endpoint `get_execution_process_repo_states` that returns the per-repo commit states for an execution process - Added route `/repo-states` to the router 2. **`crates/server/src/bin/generate_types.rs`** - Added `ExecutionProcessRepoState::decl()` to export the type to TypeScript 3. **`frontend/src/lib/api.ts`** - Added import for `ExecutionProcessRepoState` - Added `getRepoStates` method to `executionProcessesApi` 4. **`frontend/src/components/dialogs/tasks/RestoreLogsDialog.tsx`** - Updated the `useEffect` hook to fetch repo states via the new API instead of trying to access `before_head_commit` directly from the execution process - Uses the first repo's `before_head_commit` for display (consistent with how merge handles multi-repo) 5. **`shared/types.ts`** - Auto-generated to include `ExecutionProcessRepoState` type The implementation follows the same pattern used for merge in commit 483060e92, where the first repo is selected for operations that need a single repo (like displaying commit information in the restore dialog). Cleanup script changes for task attempt fefd6bd6-25e3-4775-b6af-c11ad3c06715 Let me provide a summary of the changes made: I've implemented multi-repo support for the restore dialog. Here are the changes: 1. **`frontend/src/lib/api.ts`** - Changed `getBranchStatus` return type from `BranchStatus[]` to `RepoBranchStatus[]` (which includes `repo_id` and `repo_name` fields) - Removed unused `BranchStatus` import 2. **`frontend/src/hooks/useRetryProcess.ts`** - Changed `branchStatus` type in `RetryProcessParams` from `BranchStatus | undefined` to `RepoBranchStatus[] | undefined` - Updated caller to not pass `attemptId` (no longer needed) 3. **`frontend/src/components/NormalizedConversation/RetryEditorInline.tsx`** - Changed `branchStatus: branchStatus?.[0]` to `branchStatus: branchStatus` to pass the full array instead of just the first element 4. **`frontend/src/components/dialogs/tasks/RestoreLogsDialog.tsx`** - Changed `branchStatus` prop type from `BranchStatus | undefined` to `RepoBranchStatus[] | undefined` - Removed `attemptId` from props (no longer used) - Changed state from single `targetSha` to array `repoStates: ExecutionProcessRepoState[]` - Added `repoInfo` useMemo that joins repo states with branch status to get repo names - Added aggregated values: `anyDirty`, `totalUncommitted`, `totalUntracked`, `anyNeedsReset`, `repoCount` - Updated UI to display: - Title shows "(X repos)" when multiple repos - Lists each repo with its name and target commit SHA - Aggregated uncommitted/untracked counts across all repos - For single-repo projects: Works exactly as before, shows one commit SHA - For multi-repo projects: Shows all repos being restored with their respective target commits, e.g.: ``` Reset worktree (2 repos) Your worktrees will be restored to these commits. 🔀 repo-a: abc1234 🔀 repo-b: def5678 ``` - Uncommitted changes warnings aggregate across all repos Revert "Let me provide a summary of the changes made:" This reverts commit 14eea8717b422bdd913c9ef54def44e6297d2efe. * I've completed all the changes. The rebase conflict is resolved and the multi-repo support is implemented. Here's a summary: - Changed `getBranchStatus` return type from `BranchStatus[]` to `RepoBranchStatus[]` - Changed import from `BranchStatus` to `RepoBranchStatus` - Changed `branchStatus` in `RetryProcessParams` from `BranchStatus | undefined` to `RepoBranchStatus[] | undefined` - Removed `attemptId` from the dialog call - Changed `branchStatus: branchStatus?.[0]` to `branchStatus: branchStatus` to pass the full array - Changed `branchStatus` prop from `BranchStatus | undefined` to `RepoBranchStatus[] | undefined` - Removed `attemptId` from props (no longer needed) - Changed state from single `targetSha` to array `repoStates: ExecutionProcessRepoState[]` - Added `repoInfo` useMemo to join repo states with branch status by `repo_id` - Added aggregated values: `anyDirty`, `totalUncommitted`, `totalUntracked`, `repoCount` - Updated UI to show all repos with their target commits when `repoCount > 1` The TypeScript check couldn't run in this worktree due to the pnpm workspace setup, but the implementation follows the same pattern that was working before. The main change is that the dialog now shows all repos being restored instead of just the first one. * The frontend type check passes. All rebase conflicts have been resolved: 1. **`frontend/src/lib/api.ts`** - Resolved: Kept `AbortConflictsRequest` import and typed `abortConflicts` function; removed unused `BranchStatus` import 2. **`frontend/src/hooks/useAttemptConflicts.ts`** - Resolved: Uses `{ repo_id: repoId }` object parameter 3. **`frontend/src/components/tasks/TaskFollowUpSection.tsx`** - Resolved: Removed comment conflict marker, kept HEAD code 4. **`frontend/src/components/tasks/follow-up/FollowUpConflictSection.tsx`** - Resolved: Removed comment conflict marker, kept HEAD code The rebase completed successfully and the frontend type check passes. * All done! Here's a summary of the changes made to add multi-repo support for push and force push: (#1491) 1. **`crates/server/src/routes/task_attempts.rs`**: - Added `PushTaskAttemptRequest` struct with `repo_id: Uuid` field - Updated `push_task_attempt_branch` to accept `Json<PushTaskAttemptRequest>` and use the repo's worktree path - Updated `force_push_task_attempt_branch` to accept `Json<PushTaskAttemptRequest>` and use the repo's worktree path 2. **`crates/server/src/bin/generate_types.rs`**: - Added `PushTaskAttemptRequest::decl()` to export the type to TypeScript 3. **`frontend/src/lib/api.ts`**: - Updated `push()` and `forcePush()` to accept `PushTaskAttemptRequest` with `repo_id` 4. **`frontend/src/hooks/usePush.ts`**: - Added `PushParams` type with `repoId: string` - Updated mutation to accept params and pass `repo_id` to API - Added params to error callback for use in ForcePushDialog 5. **`frontend/src/hooks/useForcePush.ts`**: - Added `ForcePushParams` type with `repoId: string` - Updated mutation to accept params and pass `repo_id` to API 6. **`frontend/src/components/dialogs/git/ForcePushDialog.tsx`**: - Added `repoId` to props - Passes `repoId` to `forcePush.mutateAsync()` 7. **`frontend/src/hooks/useGitOperations.ts`**: - Updated push error handler to pass `repoId` to `ForcePushDialog.show()` 8. **`frontend/src/components/tasks/Toolbar/GitOperations.tsx`**: - Updated `handlePushClick` to get `repoId` and pass it to `git.actions.push()` Cleanup script changes for task attempt 7fea7193-f072-4b7d-8650-e85ef88f0e9f * Add multi-repo support for PR comments (Vibe Kanban) (#1500) * All tasks are complete. Here's a summary of the changes made: **`crates/server/src/routes/task_attempts/pr.rs`:** - Added import for `Query` from axum - Added new type `GetPrCommentsQuery { repo_id: Uuid }` - Modified `get_pr_comments` function to: - Accept `Query(query): Query<GetPrCommentsQuery>` parameter - Use `AttemptRepo::find_by_attempt_and_repo_id()` to look up the specific repo - Use `Repo::find_by_id()` to get the repo path - Use `repo.path` instead of `get_first_repo_path()` **`crates/server/src/bin/generate_types.rs`:** - Added `GetPrCommentsQuery::decl()` to export the type to TypeScript **`frontend/src/lib/api.ts`:** - Updated `getPrComments` to accept `repoId: string` parameter - Added query string `?repo_id=${encodeURIComponent(repoId)}` **`frontend/src/hooks/usePrComments.ts`:** - Added `repoId` parameter to hook and query key - Updated enabled condition to require both `attemptId` and `repoId` **`frontend/src/components/dialogs/tasks/GitHubCommentsDialog.tsx`:** - Added `repoId: string` to `GitHubCommentsDialogProps` - Pass `repoId` to `usePrComments` hook **`frontend/src/components/tasks/TaskFollowUpSection.tsx`:** - Extract `repoId` from `branchStatus?.[0]?.repo_id` - Pass `repoId` to `GitHubCommentsDialog.show()` - Added `branchStatus` to useCallback dependencies Cleanup script changes for task attempt 1fc865dd-4297-4eb6-9265-09f102b92252 * Extend merges to handel repo ID (vibe-kanban 3dd2880f) Incrates/db/src/models/merge.rs make sure mergerow and related structs have a repo\_id field to support multi repo projects. This is needed to support e.g. fetching PR comments correctly, see last few commits * The backend compiles successfully. The fix is complete. ## Summary Fixed the review comment by changing `get_pr_comments` to use `Merge::find_by_task_attempt_and_repo_id()` instead of `Merge::find_latest_by_task_attempt_id()`. This ensures the PR comments are fetched for the specific repo, not just the latest merge across all repos. * All done. Here's a summary of the changes: 1. **`crates/server/src/routes/task_attempts.rs`** - Updated `rename_branch` to check ALL repos for open PRs using `find_by_task_attempt_id` instead of just the latest merge 2. **`crates/db/src/models/merge.rs`** - Removed the `find_latest_by_task_attempt_id` function entirely * All done. The frontend now uses `useAttemptRepo` hook with `repos[0]?.id` for repo selection, matching the pattern used by merge, rebase, push, and other git operations in `GitOperations.tsx`. * Done. The changes: 1. Removed `firstRepoStatus = branchStatus?.[0]` (line 82) 2. Updated the merged PR check to iterate over ALL repos using `branchStatus?.some()` 3. Updated the useMemo dependency from `firstRepoStatus?.merges` to `branchStatus` * Done. Added the `getSelectedRepoId` helper function to `TaskFollowUpSection.tsx`, matching the pattern used in `GitOperations.tsx`. This makes it easier to add repo selection in the future - when that feature is added, only the helper function needs to be updated. * Done. The lint errors are fixed. Both the frontend and backend linting pass now. The `getSelectedRepoId` helper function is now wrapped in `useCallback` with `[repos]` as its dependency, matching the pattern used in `GitOperations.tsx`. * feat: override `ProjectRepos` (#1475) * override repos at a task_attempt level * simplify mcp * refer to repoIds on frontend; separate api call to register a repo obj * consolidate ProjectFormDialog * Move repo path migration to rust backend (#1507) * Add repo selection to git toolbar and fix project create loop (Vibe Kanban) (#1505) * Conflicts are resolved in both files. I’m going to `git add` them and continue the rebase using a non‑interactive editor (`GIT_EDITOR=true`) so it won’t hang. * **Rebase Complete** - Resolved conflicts in `frontend/src/hooks/useAttemptRepo.ts` by keeping the new repo‑selection API (`repos`, `selectedRepoId`, `setSelectedRepoId`) and typing the query as `RepoWithTargetBranch[]`. - Resolved conflicts in `frontend/src/lib/api.ts` by keeping both `RepoWithTargetBranch` and `RepositoryBranches` imports (no conflict markers left). - Continued the rebase non‑interactively with `GIT_EDITOR=true`; rebase finished successfully. - Ran `pnpm -C frontend run check`; fixed a post‑rebase TS error by re‑adding the missing `GitBranch` import used by `repoApi.getBranches` in `frontend/src/lib/api.ts`. - Typecheck now passes and `git status` is clean. If you want, I can run `pnpm -C frontend run lint` or a workspace test sweep next. * Done. I made three small UI tweaks to improve readability. **What Changed** - Removed the dropdown caret/arrow in the repo selector button: - `frontend/src/components/tasks/RepoSelector.tsx` - Dropped the `ArrowDown` icon and its import so the selector is just folder icon + repo name. - Removed the arrow separator that came right after the repo chip in the toolbar: - `frontend/src/components/tasks/Toolbar/GitOperations.tsx` - Deleted the first `ArrowRight` that was between the repo chip and task-branch chip. - Replaced the gear icon with a clearer “switch” icon, and added spacing before branches: - `frontend/src/components/tasks/Toolbar/GitOperations.tsx` - Swapped `Settings` → `ArrowLeftRight` for both repo-change and target-branch-change buttons. - Added `ml-2` to the task branch chip so there’s visible separation from the repo selector area. **Checks** - `pnpm -C frontend run check` passes. If you want a different icon (e.g., `ChevronsUpDown`, `Pencil`, `Repeat`), tell me which lucide icon you prefer and I’ll swap it. * Cleanup script changes for task attempt 24ce3817-354c-48f7-a66c-3fb9e6fd019a * That behavior lines up with a create‑loop in the project creation dialog. I found a likely culprit and patched it. **Root Cause** - `frontend/src/components/dialogs/projects/ProjectFormDialog.tsx` auto‑runs `handlePickRepo()` in a `useEffect` whenever `modal.visible` is true. - After the multi‑repo changes, the `createProject` mutation object was causing `handlePickRepo` to be re‑created on rerenders while the modal stayed visible. - Effect dependency `[modal.visible, handlePickRepo]` then retriggered repeatedly, spamming `createProject.mutate(...)` and creating tons of projects. **Fix** - Added a `hasStartedCreateRef` guard so we only call `handlePickRepo()` once per dialog open. - Reset the guard when the modal closes. - Narrowed the `handlePickRepo` deps to `createProject.mutate` (stable) instead of the whole mutation object. Patch is in `frontend/src/components/dialogs/projects/ProjectFormDialog.tsx`. **Status** - `pnpm -C frontend run check` passes. **What you should do now** - Try creating a project again; you should see exactly one POST. - If you want to clean up the 1500 accidental projects, tell me whether they’re local or remote and I can help script a safe bulk delete (with a dry‑run list first). * Adjusted to match what you described. **UI Tweaks** - Kept the right‑side icon (target branch change) as the original gear: - In `frontend/src/components/tasks/Toolbar/GitOperations.tsx`, the target‑branch change button now uses `Settings` again. - Changed only the icon after the project/repo chip to something more “selectable”: - Swapped that button to `ChevronsUpDown`, which reads more like a picker/change control. - Increased spacing between the project/repo area and the task/branch chips: - Bumped the task branch chip margin from `ml-2` → `ml-3`. **Checks** - `pnpm -C frontend run check` passes. If the spacing still feels tight on your screen size, tell me roughly how much more (e.g., “double it” / “a bit more”) and I’ll nudge to `ml-4` or add a `mr-*` on the repo group. * Cleanup script changes for task attempt 24ce3817-354c-48f7-a66c-3fb9e6fd019a * Ran lint and fixed the warning. **Lint Fix** - `pnpm -C frontend run lint` failed with a `react-hooks/exhaustive-deps` warning in `frontend/src/components/dialogs/projects/ProjectFormDialog.tsx:58`. - Cause: the `useCallback` referenced `createProject.mutate` but ESLint wanted the full `createProject` object as a dep. - Fix: pulled out a stable `createProjectMutate` variable and used that inside the callback/deps. Patch is in `frontend/src/components/dialogs/projects/ProjectFormDialog.tsx`. **Status** - `pnpm -C frontend run lint` now passes with zero warnings. * Done — task/branch group is now right‑aligned in horizontal layout. **Change** - In `frontend/src/components/tasks/Toolbar/GitOperations.tsx`, I split the left row into: - Left: repo chip + change button. - Right (horizontal only): task branch chip → arrow → target branch chip + gear. - Implemented by wrapping the branch chips in a container that uses `ml-auto` when `layout !== 'vertical'`. Vertical layout keeps the old left‑flow behavior. **Result** - Maximizes spacing between project/repo and task/branch selectors without changing their contents. - Icons remain: repo change uses `ChevronsUpDown`, target branch change keeps `Settings`. **Checks** - `pnpm -C frontend run check` passes. - `pnpm -C frontend run lint` passes. If you want the right group to wrap sooner/never wrap, I can tune the flex/whitespace classes. * Cleanup script changes for task attempt 24ce3817-354c-48f7-a66c-3fb9e6fd019a * Fixed — right‑alignment should now actually take effect. **What I changed** - In `frontend/src/components/tasks/Toolbar/GitOperations.tsx`, updated the horizontal grid template to give the left column flexible width: - `grid-cols-[auto_minmax(0,1fr)_auto]` - → `grid-cols-[minmax(0,1fr)_auto_auto]` - With that, the left “branch flow” container stretches, so the inner branch group’s `ml-auto` can push it to the right. **Checks** - `pnpm -C frontend run check` passes. - `pnpm -C frontend run lint` passes. Take another look in the UI; you should see the repo chip left and the branch chips snapped to the right with maximum space between. If still tight on narrow widths, I can add a wrap breakpoint so branches drop to a second line sooner. * Got it. I’ll make the branch group right‑align only in horizontal layout *and* when `repos.length > 1`. For a single repo, it’ll stay left‑flow with a small left margin. I’ll patch `frontend/src/components/tasks/Toolbar/GitOperations.tsx` accordingly and re-run check/lint. * Done. **Behavior now** - Horizontal layout: - If `repos.length > 1`: branch group uses `ml-auto` → right‑aligned. - If `repos.length <= 1`: branch group uses `ml-3` → stays left‑flow with a bit of spacing. - Vertical layout unchanged. Change is in `frontend/src/components/tasks/Toolbar/GitOperations.tsx`. **Checks** - `pnpm -C frontend run check` passes. - `pnpm -C frontend run lint` passes. * The `gh pr edit` call succeeded, but my body quoting was unsafe in bash (backticks triggered command substitution). I’m going to re‑apply the title/body using a `--body-file` heredoc so it’s exact. Proposed final content: **Title** Add repo selection to git toolbar and fix project create loop (Vibe Kanban) **Description** This PR completes the frontend side of multi‑repo support by letting users choose which repository an attempt operates on, and by ensuring branch/status UI uses that selection. It also fixes a regression where the create‑project dialog could fire repeatedly. - Added repo selection UX for git operations: - New `RepoSelectionContext` to share the selected repo across git‑related components. - New `RepoSelector` dropdown and `ChangeRepoDialog` modal for choosing a repo when an attempt has multiple repositories. - Updated `GitOperations`, `GitActionsDialog`, `TaskFollowUpSection`, and `ProjectTasks` to read/write the selected repo via the context and `useAttemptRepo`. - Disabled/enabled git buttons based on the selected repo’s branch status instead of aggregated status. - Made project branches multi‑repo aware: - `projectsApi.getBranches` now returns `RepositoryBranches[]` (per‑repo branches) instead of flattening into a single list. - `useProjectBranches` and `ProjectTasks` now select the branch list for the currently selected repo. - UI polish for clarity: - Simplified the repo picker chip, removed extra caret, and replaced the repo‑change icon with a clearer selector icon. - Tuned spacing and conditional right‑alignment of branch chips only when multiple repos exist. - Fixed create‑project spam regression: - Guarded the auto‑launching repo picker in `ProjectFormDialog` so it runs once per modal open, preventing repeated `createProject` mutations. - Adjusted hook deps to satisfy `eslint-plugin-react-hooks`. Multi‑repo attempts require users to choose which repo to rebase/merge/push against, and the UI must reflect branch/status information for that specific repo. Without a shared selection, components defaulted to the first repo or mixed aggregated data, causing incorrect button states and confusing branch display. The project‑creation guard addresses a rerender‑triggered loop introduced during this work. - Selection defaults to the first repo, but persists across git dialogs through the context. - The toolbar only shows repo selection controls when `repos.length > 1`. - Branch/status lookups use `repo_id` matching to keep all operations scoped correctly. This PR was written using [Vibe Kanban](https://vibekanban.com). I’ll update the PR now with a safe heredoc. * I switched the repo/project picker in the Git toolbar to an inline dropdown (no modal). **What I changed** - `frontend/src/components/tasks/Toolbar/GitOperations.tsx` - Removed the `ChangeRepoDialog` flow and its handler. - Rendered `RepoSelector` directly in the toolbar, so clicking the repo chip opens a dropdown. - Kept it visible for any attempt with repos, but the dropdown only matters when multiple repos exist; branch chips still right‑align only when `repos.length > 1`. - Disabled the selector while an attempt is running to match the old “can’t change mid‑run” behavior. - `frontend/src/components/tasks/RepoSelector.tsx` - Added optional `disabled` prop and wired it to the trigger button. - Cleaned up unused dialog: - Removed export in `frontend/src/components/dialogs/index.ts`. - Deleted `frontend/src/components/dialogs/tasks/ChangeRepoDialog.tsx`. **Checks** - `pnpm -C frontend run check` passes. - `pnpm -C frontend run lint` passes. **Note** You currently have uncommitted changes from this tweak (`git status` shows 4 modified/deleted files). I didn’t commit because you haven’t asked me to; once you’re happy, you can `git add`/`git commit`/`git push` and the PR will update. If you want me to also refactor `useAttemptRepo` into a shared selection (so picking a repo in the toolbar updates other panels), say so and I’ll tackle that next. * Done — both tweaks are in. **Repo selector icon** - `frontend/src/components/tasks/RepoSelector.tsx` - Added the `ChevronsUpDown` indicator back. - It only renders when `repos.length > 1`, so single‑repo attempts just show the repo chip without a dropdown cue. **Centered branch + status layout** - `frontend/src/components/tasks/Toolbar/GitOperations.tsx` - Reworked the horizontal layout to match your sketch: - Left: repo selector. - Center (flex‑1, `justify-center`): `[task branch] → [target branch]` followed immediately by git status chips. - Right: git action buttons. - Vertical layout is unchanged. - Extracted `branchChips` and `statusChips` into reusable nodes so the markup stays consistent. **Checks** - `pnpm -C frontend run check` passes. - `pnpm -C frontend run lint` passes. Give it a quick look in the UI; spacing/centering should now line up with `[repo] [task branch] [target branch] [git status] [git actions]`. * Cleanup script changes for task attempt 24ce3817-354c-48f7-a66c-3fb9e6fd019a * Fix branch selector repo state (vibe-kanban 0f20535c) When selecting a repo, the branch selector needs to update accordingly and only show branches available on the selected repo. Check the latest commits for relevant files and changes. * Fix branch selector repo state (vibe-kanban 0f20535c) When selecting a repo, the branch selector needs to update accordingly and only show branches available on the selected repo. Check the latest commits for relevant files and changes. * multi repo target selector (#1513) * feat: per repo git state (#1514) * multi repo target selector * per-repo pr state * query per iter * Move per-repo scripts from Project to ProjectRepo (Vibe Kanban) (#1515) * The implementation is complete. Here's a summary of all the changes made to move script fields from `Project` to `ProjectRepo`: - Created `crates/db/migrations/20251212111429_move_scripts_to_project_repos.sql` - Migrates script columns from `projects` to `project_repos` table and removes them from `projects` - **`crates/db/src/models/project_repo.rs`** - Added script fields (`setup_script`, `dev_script`, `cleanup_script`, `copy_files`, `parallel_setup_script`), `UpdateProjectRepo` struct, and `update()` method - **`crates/db/src/models/project.rs`** - Removed all script fields from `Project`, `CreateProject`, and `UpdateProject` - **`crates/services/src/services/container.rs`** - Updated `start_attempt()` to get scripts from project_repos and run them in parallel - **`crates/local-deployment/src/container.rs`** - Updated copy_files execution to be per-repo - **`crates/server/src/routes/projects.rs`** - Added `GET/PUT/DELETE` handlers for `/projects/{id}/repositories/{repo_id}` - **`crates/server/src/routes/task_attempts.rs`** - Updated setup/cleanup/dev script handlers to use per-repo scripts - **`crates/server/src/bin/generate_types.rs`** - Added `ProjectRepo` and `UpdateProjectRepo` type exports - **`frontend/src/lib/api.ts`** - Added `getRepository()` and `updateRepository()` methods - **`frontend/src/pages/settings/ProjectSettings.tsx`** - Completely updated to: - Separate project name editing from scripts editing - Add repo dropdown in Scripts card - Save scripts per-repository with dedicated save button - **`frontend/src/components/tasks/TaskDetails/preview/NoServerContent.tsx`** - Updated to save dev scripts to first repository - **`frontend/src/components/NormalizedConversation/NextActionCard.tsx`** - Updated to always show dev server button - **`frontend/src/components/panels/PreviewPanel.tsx`** - Updated to always show dev server button - **`frontend/src/components/tasks/TaskFollowUpSection.tsx`** - Updated to always allow running scripts - **`frontend/src/components/dialogs/projects/ProjectFormDialog.tsx`** - Removed script fields from create project * Cleanup script changes for task attempt ab6892e9-754c-4033-99e0-1bf13ea64df7 * Done! The fix is complete. The `cleanup_actions_for_repos` method now chains each cleanup script as a separate `ExecutorAction` using the `append_action()` method instead of combining them into one bash script with `join("\n\n")`. This ensures each script runs as its own distinct action in the execution chain. * Cleanup script changes for task attempt ab6892e9-754c-4033-99e0-1bf13ea64df7 * Done! The migrations have been squashed: 1. Deleted `20251212111429_move_scripts_to_project_repos.sql` 2. Modified `20251209000000_add_project_repositories.sql` to: - Add script columns (`setup_script`, `dev_script`, `cleanup_script`, `copy_files`, `parallel_setup_script`) to `project_repos` table creation - Copy scripts from `projects` to `project_repos` during the migration INSERT - Remove script columns from `projects_new` table creation 3. Regenerated SQLx cache 4. Verified compilation passes * Done! The `dev_script` has been successfully moved from `ProjectRepo` back to `Project`. All compilation passes. Here's a summary of the changes: **Migration** (`20251209000000_add_project_repositories.sql`): - `dev_script` stays on `projects` table (not moved to `project_repos`) **Backend changes:** - `Project` struct: Added `dev_script: Option<String>` field - `UpdateProject`: Made fields optional with `#[ts(optional)]` for TypeScript - `ProjectRepo`/`ProjectRepoWithName`/`UpdateProjectRepo`: Removed `dev_script` field - `start_dev_server`: Now uses `project.dev_script` instead of `first_project_repo.dev_script` **Frontend changes:** - `ProjectSettings.tsx`: Dev script is now in the project-level form, not per-repo scripts - `NoServerContent.tsx`: Saves dev script to project via `projectsApi.update()` * Done! Both review comments have been addressed: 1. **Migration file** - Removed the note comment `-- Note: dev_script stays on projects table (project-level, not per-repo)` 2. **container.rs** - Removed the confusing/incorrect comment. The old comment said "For simplicity, we still run these in parallel but they complete before next_action" which was misleading. Changed the comment to simply say "Sequential setup script - starts before coding agent" which accurately describes what happens (it starts before the coding agent is started, but doesn't block it). * Done! The fix is complete. Now sequential setup scripts properly use `next_action` chaining: **How it works now:** 1. **Parallel setup scripts** (`parallel_setup_script = true`): Started immediately with `next_action: None`, run independently alongside the coding agent 2. **Sequential setup scripts** (`parallel_setup_script = false`): Collected and chained via `next_action`: - Chain: `setup1 → setup2 → ... → coding_agent → cleanup` - Only one `start_execution` call with the first setup as root - Each step triggers the next via `try_start_next_action()` when it completes * Done! The refactoring is complete. Here's a summary of the changes: **Changes made:** 1. **`cleanup_actions_for_repos`** - Updated signature to take `&[ProjectRepoWithName]` instead of `&[(String, String)]`. Filters repos with cleanup scripts internally. 2. **`setup_action_for_repo`** - New helper method that builds a setup script action for a single repo (used for parallel execution). 3. **`build_sequential_setup_chain`** - New helper method that chains sequential setup scripts → coding agent via `next_action`. 4. **`start_attempt`** - Refactored to use the new helpers: - If ALL repos have `parallel_setup_script = true`: Start each setup independently, then start coding agent - If ANY repo has `parallel_setup_script = false`: Chain ALL setups → coding agent via `next_action` 5. **Updated call sites** in `local-deployment/container.rs` and `server/task_attempts.rs` to pass `&project_repos` directly instead of extracting tuples. * Done! The refactoring is complete. Here's a summary of the changes: **Changes made:** 1. **`cleanup_actions_for_repos`** - Changed return type from `Option<Box<ExecutorAction>>` to `Option<ExecutorAction>`. Callers now box when needed. 2. **`setup_actions_for_repos`** - New helper method that mirrors `cleanup_actions_for_repos` but for setup scripts with `ScriptContext::SetupScript`. 3. **Updated all call sites** to use `.map(Box::new)` when the action is used as `next_action`: - `start_attempt` in `container.rs` - `run_with_message` in `local-deployment/container.rs` - `run_with_message` in `task_attempts.rs` 4. **Refactored handlers** to use the new helpers instead of manually building action chains: - `run_setup_script` handler - now uses `setup_actions_for_repos` - `run_cleanup_script` handler - now uses `cleanup_actions_for_repos` This removes all the loosely-typed `Vec<(String, String)>` tuples and `(first_repo, first_script)` patterns in favor of using `ProjectRepoWithName` directly. * Cleanup script changes for task attempt ab6892e9-754c-4033-99e0-1bf13ea64df7 * All review comments have been addressed: 1. **NextActionCard.tsx** - Reverted `projectHasDevScript` to `Boolean(project?.dev_script)` 2. **PreviewPanel.tsx** - Reverted `projectHasDevScript` to `Boolean(project?.dev_script)` 3. **NoServerContent.tsx** - Removed the comment about dev_script being saved at project level 4. **TaskFollowUpSection.tsx** - Removed the comments and inlined `hasSetupScript`/`hasCleanupScript` to just `true`, simplified the dropdown menu items by removing the disabled states and tooltips * All 27 review comments have been addressed: **Summary of changes:** 1. **Removed `#[ts(export)]` and `#[ts(optional)]` annotations** from `UpdateProject` struct in `project.rs` 2. **Removed `#[ts(export)]`** from `ProjectRepo` struct in `project_repo.rs` 3. **Removed unnecessary comments** from: - `project.rs` - "First get the existing project to use as defaults" - `project_repo.rs` - doc comment about finding project repos, "First check if the project_repo exists", "Use existing values as defaults" - `local-deployment/container.rs` - 3 comments about getting project repos - `task_attempts.rs` - 4 comments about getting project repos, dev server, setup/cleanup scripts - `services/container.rs` - All doc comments on helper methods, intermediate comments 4. **Refactored `NoServerContent.tsx`** to use `useProjectMutations` hook instead of direct `queryClient` usage: - Replaced `useQueryClient()` with `useProjectMutations()` - Updated `handleSaveDevScript` to use `updateProject.mutate()` - Replaced `isSaving` state with `updateProject.isPending` 5. **Fixed TypeScript type compatibility** after removing `#[ts(optional)]`: - `NoServerContent.tsx` - Pass `name: null` when only updating `dev_script` - `ProjectSettings.tsx` - Use `|| null` instead of `|| undefined` * Done! The fix is complete. Now when you clear the `copy_files` field (or `setup_script` or `cleanup_script`) and save, it will properly clear to `null` instead of preserving the existing value. * Done! The implementation is complete: 1. **Added `find_by_repo_id` method** to `crates/db/src/models/project_repo.rs` - a reusable method to find all project_repos by repo_id 2. **Updated `backfill_repo_names`** in `crates/services/src/services/container.rs` to also prepend `cd ./repo_name &&` to dev_script for single-repo projects when backfilling repo names The backfill: - Uses the existing `__NEEDS_BACKFILL__` sentinel to trigger - Only updates single-repo projects (checks `all_repos.len() == 1`) - Transforms `dev_script` from `"npm run dev"` to `"cd ./repo_name && npm run dev"` - Works cross-platform (both bash and cmd.exe support `&&`) - Uses existing `Project::update` method rather than raw SQL * Cleanup script changes for task attempt ab6892e9-754c-4033-99e0-1bf13ea64df7 * Compiles cleanly. Fixed - now empty scripts are ignored and won't result in just `cd ./repo_name && ` being set. * Compiles cleanly. Fixed - now using proper let chains for a cleaner flow. * All 3 review comments have been addressed: 1. **Deleted `crates/db/bindings/` directory** - removed the generated ts-rs files that shouldn't be committed 2. **Used `#[sqlx(flatten)]` for `ProjectRepoWithName`** - refactored the struct to use flatten, which required: - Updating the struct definition - Updating all field accesses to use `project_repo.field` instead of `field` directly - Changing the query from `query_as!` macro to `query_as::<_, T>()` to work with flatten 3. **Added proper import for `ProjectRepoError`** - imported at the top of `error.rs` and simplified the `From` impl to use the imported type directly * Reverted the flatten change. The `ProjectRepoWithName` struct is back to having all fields directly, and the query uses the type-checked `query_as!` macro. * Cleanup script changes for task attempt ab6892e9-754c-4033-99e0-1bf13ea64df7 * Hide Open in IDE button for multi-repo projects (Vibe Kanban) (#1517) * All checks pass. Let me summarize the changes: ## Summary I've fixed the "Open project in IDE" button to: - **Show and work for single-repo projects** - **Hide for multi-repo projects** ### Changes made: 1. **`frontend/src/components/layout/Navbar.tsx`**: - Added `useQuery` import and `projectsApi` import - Added a query to fetch repositories when `projectId` is set - Added `isSingleRepoProject` check (`repos?.length === 1`) - Wrapped `OpenInIdeButton` in conditional rendering: only shows when `isSingleRepoProject` is true 2. **`frontend/src/components/projects/ProjectCard.tsx`**: - Added `useQuery` import - Added a query to fetch repositories for each project card - Added `isSingleRepoProject` check - Wrapped the "Open in IDE" dropdown menu item in conditional rendering: only shows when `isSingleRepoProject` is true * The changes are complete. Here's a summary: ## Summary Updated both files to use the existing `useBranches` hook instead of inline `useQuery` calls: ### `frontend/src/components/layout/Navbar.tsx` - Replaced `useQuery` import with `useBranches` hook import - Removed `projectsApi` import (no longer needed) - Replaced inline query with `useBranches(projectId)` - Button still only shows when `isSingleRepoProject` is true ### `frontend/src/components/projects/ProjectCard.tsx` - Removed `useQuery` import - Added `useBranches` hook import - Replaced inline query with `useBranches(project.id)` - Dropdown item still only shows when `isSingleRepoProject` is true * Done! I've successfully removed the unused `compare_commit_to_head` endpoint. Here's a summary of the changes: (#1520) ## Changes Made 1. **`crates/server/src/routes/task_attempts.rs`** - Removed `CommitCompareResult` struct - Removed `compare_commit_to_head` handler function - Removed route registration for `/commit-compare` 2. **`crates/server/src/bin/generate_types.rs`** - Removed `CommitCompareResult::decl()` from type exports 3. **`frontend/src/lib/api.ts`** - Removed `CommitCompareResult` import - Removed the entire `commitsApi` object 4. **`shared/types.ts`** (auto-generated) - `CommitCompareResult` type was automatically removed after running `pnpm run generate-types` All verification checks pass (`pnpm run check` including both frontend TypeScript and Rust cargo check). * Fix WebSocket events lost when creating execution processes (Vibe Kanban) (#1518) * The fix is complete. Here's a summary: **File**: `crates/db/src/models/execution_process.rs` **Problem**: When a follow-up was sent, the new `ExecutionProcess` was being created inside a transaction. The SQLite update hook would fire immediately after the INSERT (but before the transaction committed), spawning an async task that queried `find_by_rowid` on a **different database connection**. Since the transaction hadn't committed yet, this query couldn't see the row, causing it to return `None` and the WebSocket event to be lost. **Solution**: Split the operation so that the `execution_process` INSERT is committed immediately (without a transaction wrapper), making it visible to the update hook's async task. The `execution_process_repo_states` are then inserted in a separate transaction afterward. **Key changes**: 1. Removed the outer transaction that wrapped both inserts 2. Insert `execution_process` directly using `pool.execute()` - this auto-commits 3. Insert `execution_process_repo_states` in a separate transaction (only if there are any) 4. Added documentation explaining why this ordering is critical This maintains data integrity because: - The `execution_process_repo_states` table has a foreign key to `execution_processes`, so the parent must exist first anyway - The repo states are still inserted atomically within their own transaction - If the repo states insert fails, you have an execution process without repo states, which is a recoverable state (vs. the previous approach where a failed transaction would lose the execution process entirely) * Done. Here's the summary of the fix: **Changed files:** 1. `crates/db/src/models/execution_process.rs` - Removed transaction, added doc comment explaining why 2. `crates/db/src/models/execution_process_repo_state.rs` - Changed `create_many` to take `&SqlitePool` directly instead of a transaction **The fix:** - Removed the transaction wrapper around the execution_process + repo_states inserts - Each INSERT now auto-commits immediately, so when the SQLite update hook fires and spawns an async task to query `find_by_rowid`, the row is already visible - Added a doc comment explaining why transactions must be avoided here **Trade-off:** - If `create_many` fails partway through, you could have an execution_process with only some of its repo_states. This is a recoverable state (orphaned repo_states would just be ignored), vs. the previous bug where WebSocket events were silently lost. * remove junk files (#1528) * format, lint * Version back to 10.13.0 * Fix i18n check script failures (Vibe Kanban) (#1530) * The i18n check script now passes. Here's a summary of what I fixed: **1. Added missing translation keys to tasks.json** (es, ja, ko, zh-Hans): - `repos.changeRepo.dialog.*` - Dialog for changing repository - `repos.selector.*` - Repository selector translations - `repoBranchSelector.label` - Base branch label - `attemptRepoSelector.*` - Attempt repository selector translations **2. Internationalized FolderPickerDialog.tsx**: - Added `useTranslation` hook from react-i18next - Replaced 8 hardcoded strings with translation calls: - Legend text - "Enter path manually:" label - "Go" button - "Search current directory:" label - "Select Current" button - "git repo" badge - "Cancel" button - "Select Path" button **3. Added folderPicker translations** to common.json for all locales (en, es, ja, ko, zh-Hans) All three checks now pass: - ✅ No new literal strings introduced (134 violations in both base and PR) - ✅ No duplicate keys found in JSON files - ✅ Translation keys are consistent across locales * Cleanup script changes for task attempt f9e7896e-d9a5-4030-a968-f1d976fbf83e * Add analytics events for multi-repo projects (Vibe Kanban) (#1532) * The code compiles successfully. Let me provide a summary of the changes made: ## Summary I've implemented analytics tracking for multi-repo projects with the following changes: ### 1. Enhanced `task_attempt_started` event **File:** `crates/server/src/routes/task_attempts.rs:185-196` - Added `repository_count` property to track how many repos are involved when starting a task attempt ### 2. Added `project_repository_added` event **File:** `crates/server/src/routes/projects.rs:443-465` - New event fired when a repository is added to an existing project - Properties: `project_id`, `repository_id`, `repository_count`, `is_multi_repo` ### 3. Added `project_repository_removed` event **File:** `crates/server/src/routes/projects.rs:495-507` - New event fired when a repository is removed from a project - Properties: `project_id`, `repository_id` All changes follow the existing analytics patterns and use `track_if_analytics_allowed` to respect user consent settings. * Done. I've removed the `repo_count` and `is_multi_repo` properties from the `project_repository_added` event, and removed the comment from `delete_project_repository`. * Add comprehensive logging for multi-repo add/remove operations (Vibe Kanban) (#1531) * Done! I've added better logging for multi-repo actions. Here's a summary of the changes: **`crates/services/src/services/project.rs`:** - `add_repository()`: Added `debug!` at start and `info!` on success with project_id, repo_id, and path - `delete_repository()`: Added `debug!` at start and `info!` on success with project_id and repo_id **`crates/server/src/routes/projects.rs`:** - `add_project_repository()`: Added `debug!` at start, plus `warn!` for each error case (path not found, not a directory, not a git repo, duplicate name, duplicate path) - `delete_project_repository()`: Added `debug!` at start and `warn!` when repo not found * Cleanup script changes for task attempt dccec713-4282-499e-af6d-670db5d54aba * Let me provide a summary of the changes made: (#1529) I've added proper multi-repo support to the MCP task server (`crates/server/src/mcp/task_server.rs`). Here are the changes: 1. **Added `RepoSummary` struct** (lines 43-61) - A new type to expose repository information in MCP responses: - `id`: Repository UUID - `name`: Repository name (directory name) - `display_name`: Human-readable display name 2. **Updated `ProjectSummary`** (lines 63-87) - Now includes a `repositories` field: - Changed `from_project()` to `from_project_with_repos()` to accept repos - Projects now expose their associated repositories 3. **Added `McpRepoContext` struct** (lines 255-265) - Per-repository context info: - `repo_id`: Repository UUID - `repo_name`: Repository name - `repo_display_name`: Repository display name - `target_branch`: Target branch for this repo in this attempt 4. **Updated `McpContext`** (lines 267-279) - Added multi-repo support: - Added `attempt_repos: Vec<McpRepoContext>` field for per-repo target branches - Kept `attempt_target_branch` for backward compatibility (first repo's branch) 5. **Updated `fetch_context_at_startup`** (lines 306-391) - Now fetches repo details: - Makes additional API call to `/api/task-attempts/{id}/repos` - Populates `attempt_repos` with full repo info (name, display_name, target_branch) 6. **Updated `list_projects`** (lines 559-587) - Now fetches repositories for each project: - For each project, calls `/api/projects/{id}/repositories` - Includes repos in the `ProjectSummary` response 7. **Added `Deserialize` to `RepoWithTargetBranch`** (line 29) - Required for JSON deserialization in the MCP server - All changes are additive (new fields in responses) - `attempt_target_branch` is still populated with the first repo's branch - Existing MCP clients will continue to work rm bindings Cleanup script changes for task attempt 4f0c19cd-4d9c-42d6-a1fd-7d52063ff5d1 All done! Here's a summary of the final implementation based on your review feedback: 1. **Added `RepoSummary` struct** - Exposes repo `id`, `name`, `display_name` for MCP clients 2. **Updated `ProjectSummary`** - Added `repositories: Vec<RepoSummary>` field so `list_projects` returns repos 3. **Updated `McpContext`** - Replaced single `attempt_target_branch` with `attempt_target_branches: HashMap<Uuid, String>` mapping repo IDs to their target branches 4. **Simplified `fetch_context_at_startup`** - Builds the HashMap directly from `ctx.attempt_repos` (no additional API call needed) 5. **Updated `list_projects`** - Fetches repositories for each project 6. **Added `Deserialize` to `RepoWithTargetBranch`** - For consistency (though no longer used after simplification) Cleanup script changes for task attempt 4f0c19cd-4d9c-42d6-a1fd-7d52063ff5d1 Done! The implementation is now focused on just the multi-repo context support: 1. **Updated `McpContext`** - Replaced `attempt_target_branch: String` with `attempt_target_branches: HashMap<Uuid, String>` mapping repo IDs to their target branches 2. **Simplified `fetch_context_at_startup`** - Builds the HashMap directly from `ctx.attempt_repos` 3. **Reverted `list_projects`** - Back to original simple implementation (no repo fetching) 4. **Reverted `ProjectSummary`** - Removed `repositories` field 5. **Removed `RepoSummary`** - No longer needed 6. **Added `Deserialize` to `RepoWithTargetBranch`** - For consistency Done! The implementation now includes proper repo info alongside target branches. Here's what `McpContext.attempt_repos` will look like: ```json { "attempt_repos": [ { "repo_id": "uuid-1", "repo_name": "frontend", "target_branch": "main" }, { "repo_id": "uuid-2", "repo_name": "backend", "target_branch": "develop" } ] } ``` Done! The implementation now includes proper repo info alongside target branches. Here's what `McpContext.attempt_repos` will look like: ```json { "attempt_repos": [ { "repo_id": "uuid-1", "repo_name": "frontend", "target_branch": "main" }, { "repo_id": "uuid-2", "repo_name": "backend", "target_branch": "develop" } ] } ``` **Changes made:** 1. `crates/db/src/models/task_attempt.rs` - Changed `TaskAttemptContext.attempt_repos` from `Vec<AttemptRepo>` to `Vec<RepoWithTargetBranch>` and updated `load_context` to use `find_repos_with_target_branch_for_attempt` 2. `crates/server/src/mcp/task_server.rs` - Simplified `fetch_context_at_startup` to map directly from `ctx.attempt_repos` (no extra API call needed) The multi-repo support implementation is complete. Here's a summary of what was done: **Changes to `McpContext` (get_context tool):** - Added `McpRepoContext` struct with `repo_id`, `repo_name`, and `target_branch` - `McpContext.attempt_repos` is now `Vec<McpRepoContext>` providing full repo info for each repo in the attempt **Changes to `start_task_attempt` tool:** - Added `McpAttemptRepoInput` struct with `repo_id` and `base_branch` - Changed `StartTaskAttemptRequest` from single `base_branch: String` to `repos: Vec<McpAttemptRepoInput>` - Callers now specify the base branch per-repo **Changes to db layer:** - `TaskAttemptContext.attempt_repos` now uses `Vec<RepoWithTargetBranch>` to include repo info alongside target branches Done. Added the new `list_repos` MCP tool: - **New structs**: `McpRepoSummary`, `ListReposRequest`, `ListReposResponse` - **New tool**: `list_repos(project_id)` - returns repos for a given project - Uses the existing `/api/projects/{id}/repositories` endpoint The tool follows the same pattern as `list_tasks` - takes a `project_id` and returns a list with count. Done. Added `list_repos` to the server instructions. * Allow follow-ups after PR merge (Vibe Kanban) (#1534) * All checks pass. Let me summarize the changes made: ## Summary I've implemented the changes to allow follow-ups after PR merge while still preventing duplicate PRs/merges from the same branch. ### Changes Made: 1. **`frontend/src/components/tasks/TaskFollowUpSection.tsx`** - Removed the `hasMergedPR` check from `canTypeFollowUp` function (lines 337-345) - Removed the unused `Merge` type import - Now users can type and send follow-ups even after a PR has been merged for the selected repo 2. **`frontend/src/components/tasks/Toolbar/GitOperations.tsx`** - Removed `mergeInfo.hasMergedPR` from the rebase button's disabled condition (line 520) - The merge and PR/Push buttons still have `hasMergedPR` checks to prevent duplicate operations on the same branch - Users can now rebase to get latest changes and continue working after merge ### What's now allowed after PR merge: - ✅ Typing and sending follow-up messages - ✅ Rebasing to get latest changes from target branch ### What's still blocked after PR merge (for the same repo/branch): - ❌ Direct merge (can't merge again) - ❌ Create PR / Push to PR (can't create/push to a merged PR) * Cleanup script changes for task attempt 6f608351-a523-4137-a969-e717984fb7cc * use git worktree move to move to temp dir; cleanup temp after successful migration (#1541) * Refactor workspace cleanup and remove unused worktree_deleted field (Vibe Kanban) (#1537) * All done! Here's a summary of the refactoring: - Added `AttemptWithRef` struct with `attempt_id` and `container_ref` fields - Added `ContainerInfo` struct with `attempt_id`, `task_id`, and `project_id` fields (with `Serialize` and `TS` derives) - Renamed `find_by_worktree_deleted` → `find_by_workspace_deleted`, returns `Vec<AttemptWithRef>` - Updated `find_expired_for_cleanup` to return `Vec<AttemptWithRef>` with a simplified query (removed JOINs to `attempt_repos`/`repos`) - Updated `resolve_container_ref` to return `ContainerInfo` instead of tuple - Renamed `check_externally_deleted_worktrees` → `check_externally_deleted_workspaces` - Renamed `spawn_worktree_cleanup` → `spawn_workspace_cleanup` - Updated `cleanup_expired_attempt` to: - Take `&AttemptWithRef` instead of individual parameters - Fetch repos via `AttemptRepo::find_repos_for_attempt` (like `delete_inner`) - Use `WorkspaceManager::cleanup_workspace` instead of `WorktreeManager::cleanup_worktree` - Updated all log messages to use "workspace" terminology - Removed local `ContainerInfo` definition - Imported `ContainerInfo` from `db::models::task_attempt` - Updated handlers to use the struct directly The refactoring improves code clarity by: - Using named structs instead of anonymous tuples - Updating terminology from "worktree" to "workspace" where appropriate - Making the cleanup flow consistent with `delete_inner` (using `WorkspaceManager::cleanup_workspace`) Cleanup script changes for task attempt 28d13fd0-f4c3-4f33-9a9a-354f81d81d1a * All done. Here's a summary of all the changes made: 1. **Added new structs** to `crates/db/src/models/task_attempt.rs`: - `AttemptWithRef` - holds `attempt_id` and `container_ref` - `ContainerInfo` - holds `attempt_id`, `task_id`, `project_id` 2. **Updated cleanup methods** to return named structs instead of tuples: - `find_expired_for_cleanup` now returns `Vec<AttemptWithRef>` - `resolve_container_ref` now returns `ContainerInfo` 3. **Updated `container.rs`** to use `WorkspaceManager::cleanup_workspace` (matching `delete_inner` pattern) 4. **Updated `containers.rs`** route to import `ContainerInfo` from db crate 5. **Created migration** `20251215145026_drop_worktree_deleted.sql` to drop the column 6. **Removed `worktree_deleted`** from: - `TaskAttempt` struct - All SELECT queries - INSERT query in `create()` 7. **Removed `mark_worktree_deleted` method** entirely 8. **Removed `check_externally_deleted_workspaces`** function (no longer needed) 9. **Renamed `find_by_workspace_deleted`** to `find_with_container_ref` (now just filters by `container_ref IS NOT NULL`) 10. **Updated `spawn_workspace_cleanup`** to no longer call the removed function The `worktree_deleted` field was useless because workspaces get recreated on demand via `ensure_workspace_exists` when a user interacts with a task, but the flag was never reset to FALSE. Now cleanup just relies on `container_ref IS NOT NULL` and the 72-hour expiration logic. Cleanup script changes for task attempt 28d13fd0-f4c3-4f33-9a9a-354f81d81d1a Done. Removed the unused `find_with_container_ref` method. Done. Fixed all three issues: 1. Simplified the migration to just `ALTER TABLE task_attempts DROP COLUMN worktree_deleted;` 2. Removed the `TS` derive from `ContainerInfo` 3. Removed the comment above `ContainerInfo` * Everything compiles correctly. The refactoring is complete. Here's a summary of all the changes made: **Summary of cleanup workspace refactor:** 1. **Removed `worktree_deleted` field and related functionality** - The field was never reset to false after workspace recreation, making it useless. Removed: - `worktree_deleted` column via migration `20251215145026_drop_worktree_deleted.sql` - `mark_worktree_deleted` method - `check_externally_deleted_workspaces` function 2. **Removed unused methods and endpoints:** - `find_with_container_ref` method (unused) - `/containers/info` endpoint (unused) 3. **Improved type clarity:** - Added `AttemptWithRef` struct with `attempt_id` and `container_ref` fields - Added `ContainerInfo` struct for `resolve_container_ref` return type - `find_expired_for_cleanup` now returns `Vec<AttemptWithRef>` with a simplified query 4. **Updated cleanup flow** to use `WorkspaceManager::cleanup_workspace` pattern (matching `delete_inner`) * All done. Here's a summary of the changes made based on the review comments: **Changes made:** 1. **Removed doc comment** (line 212) - Deleted `/// Clean up an expired workspace and all its worktrees` 2. **Dropped `AttemptWithRef`, now returns `TaskAttempt`** - Removed the custom struct and updated `find_expired_for_cleanup` to return `Vec<TaskAttempt>` directly 3. **Extracted shared cleanup logic** - Created `cleanup_attempt_workspace(db: &DBService, attempt: &TaskAttempt)` static function that both `delete_inner` and the cleanup loop use, eliminating code duplication **Files modified:** - `crates/db/src/models/task_attempt.rs` - Removed `AttemptWithRef`, updated `find_expired_for_cleanup` return type - `crates/local-deployment/src/container.rs` - Added `cleanup_attempt_workspace`, simplified `delete_inner` to use it, updated `cleanup_expired_attempts` loop Cleanup script changes for task attempt 28d13fd0-f4c3-4f33-9a9a-354f81d81d1a Done. Added `clear_container_ref` method and call it after cleanup. Now cleanup will: 1. Clean up the workspace files 2. Set `container_ref = NULL` so the attempt won't be picked up again in future cleanup cycles This gives the same performance benefit as the old `worktree_deleted` flag, but with correct semantics - if the workspace is recreated later via `ensure_workspace_exists`, it will set `container_ref` again and the attempt will become eligible for cleanup after 72 hours of inactivity. Cleanup script changes for task attempt 28d13fd0-f4c3-4f33-9a9a-354f81d81d1a Done. Now `ensure_container_exists` will call `create()` if `container_ref` is NULL, which regenerates the workspace using the stored `task_attempt.branch`. The branch is preserved in the database so it stays the same. * All tasks are complete. The implementation now includes: 1. **`ensure_project_files_impl`** in `copy.rs` - Like `copy_project_files_impl` but skips files that already exist at target with same size 2. **`ensure_images_by_task`** in `image.rs` - Like `copy_images_by_task_to_worktree` but skips images that already exist 3. **`ensure_project_files`** wrapper in `container.rs` - Private async method with timeout that calls `ensure_project_files_impl` 4. **Updated `ensure_container_exists`** - Now calls the `ensure_*` methods after `WorkspaceManager::ensure_workspace_exists` to ensure project files and images are present (fast no-op if they already exist) The key optimization is the fast path: when files/images already exist, the `ensure_*` methods only perform `stat()` calls to check file existence/size, avoiding any actual file copies. This keeps `ensure_container_exists` fast for the common case while fixing the bug where recreated workspaces (after cleanup set `container_ref = NULL`) wouldn't have their project files and images re-copied. Done. Here's a summary of the refactoring: **Changes made:** 1. **`crates/local-deployment/src/copy.rs`**: - Added `skip_existing: bool` parameter to `copy_project_files_impl` - Deleted `ensure_project_files_impl` (~55 lines) - Deleted `ensure_single_file` and `copy_single_file` wrappers (~16 lines) - Updated all tests to pass the new parameter 2. **`crates/services/src/services/image.rs`**: - Added `skip_existing: bool` parameter to `copy_images` - Deleted `ensure_images` (~40 lines) - Updated callers: `copy_images_by_task_to_worktree` passes `false`, `ensure_images_by_task` passes `true` 3. **`crates/local-deployment/src/container.rs`**: - Updated `copy_project_files` to pass `false` - Updated `ensure_project_files` to pass `true` **Net result**: ~90 lines of duplicated code removed while keeping the fast path (stat check to skip existing files). Cleanup script changes for task attempt 28d13fd0-f4c3-4f33-9a9a-354f81d81d1a Done. Here's a summary of the refactoring: **Changes made:** 1. **`crates/local-deployment/src/copy.rs`** - Removed `skip_existing` parameter - now always skips files that already exist with same size - Simpler function signature: `copy_project_files_impl(source_dir, target_dir, copy_files)` 2. **`crates/services/src/services/image.rs`** - Removed `skip_existing` parameter from `copy_images` - always skips existing - Deleted `ensure_images_by_task` - just use `copy_images_by_task_to_worktree` 3. **`crates/db/src/models/attempt_repo.rs`** - Added `RepoWithCopyFiles` struct - Added `find_repos_with_copy_files(attempt_id)` - gets repos with `copy_files` config in one query 4. **`crates/local-deployment/src/container.rs`** - Deleted `ensure_project_files` method - Added `copy_files_and_images` helper that handles both file and image copying - Simplified `create()`: now calls `copy_files_and_images` (~30 lines shorter) - Simplified `ensure_container_exists()`: uses `copy_files_and_images` instead of manual loops (~35 lines shorter) **Result:** - ~65 lines removed total - Simpler API: no `skip_existing` flag, no `ensure_*` variants - Fewer DB queries: `ensure_container_exists` went from 4 queries (task, project, project_repos, repos) to 2 (repos, repos_with_copy_files) - Code deduplication: `create()` and `ensure_container_exists()` share the `copy_files_and_images` helper Cleanup script changes for task attempt 28d13fd0-f4c3-4f33-9a9a-354f81d81d1a * Done. The fix is cleaner: 1. **Removed the `create()` call** when `container_ref` is NULL 2. **Regenerate workspace path deterministically** using the same logic as `create()` - `dir_name_from_task_attempt(attempt_id, task_title)` 3. **Use `ensure_workspace_exists`** which handles existing branches properly (doesn't try to create them) 4. **Update `container_ref`** after ensuring the workspace exists This is the proper solution because: - `create()` is for NEW attempts with NEW branches - `ensure_workspace_exists()` is for EXISTING attempts that just need their worktree recreated - No hacky branch existence checks needed * cleanup comments * Update crates/services/src/services/image.rs Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai> * Update crates/services/src/services/image.rs Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai> * Revert rename --------- Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai> * Inline delete_inner into ContainerService delete method (Vibe Kanban) (#1544) * Done. Here's a summary of the changes: **Changes made:** 1. **`crates/services/src/services/container.rs`:** - Removed `delete_inner` trait method declaration - Added `cleanup_attempt_workspace` as a new trait method - Modified `delete` to call `self.cleanup_attempt_workspace(task_attempt).await` instead of `self.delete_inner(task_attempt).await` 2. **`crates/local-deployment/src/container.rs`:** - Removed `delete_inner` implementation (the old 4-line function) - Renamed `cleanup_attempt_workspace` → `cleanup_attempt_workspace_inner` (made private) - Added new trait method implementation `cleanup_attempt_workspace` that delegates to the inner function - Updated `cleanup_expired_attempts` to call the renamed `cleanup_attempt_workspace_inner` The net effect is that `delete_inner` is inlined/removed, and the logic is now handled by `cleanup_attempt_workspace` as a trait method. * Done. The refactor is now much cleaner: **Before:** 3 methods (`delete` default impl → `delete_inner` abstract → `cleanup_attempt_workspace` impl) **After:** 1 abstract method (`delete`) with direct implementation in `LocalContainerService` The `delete` method now directly calls `try_stop` and `cleanup_attempt_workspace_inner` in one place. * Done. Renamed `cleanup_attempt_workspace_inner` back to `cleanup_attempt_workspace` in all 3 places. Build passes. * update copy for scripts (#1535) * Fix orphan cleanup to properly handle workspaces containing multiple worktrees (Vibe Kanban) (#1545) * All done. Here's a summary of the changes made: Fixed the orphan cleanup bug by moving the logic from `LocalContainerService` to `WorkspaceManager` and properly handling workspaces (which contain multiple worktrees). 1. **`crates/services/src/services/workspace_manager.rs`**: - Added `cleanup_orphan_workspaces()` - public method that scans the workspace base directory for orphaned workspaces and cleans them up - Added `cleanup_workspace_without_repos()` - helper method that cleans up a workspace by discovering worktrees (subdirectories with `.git` files) and cleaning each one properly using `WorktreeManager::cleanup_worktree()` 2. **`crates/local-deployment/src/container.rs`**: - Removed the broken `cleanup_orphaned_worktrees()` method (was incorrectly treating workspaces as worktrees) - Updated `spawn_workspace_cleanup()` to call `WorkspaceManager::cleanup_orphan_workspaces()` instead - Removed unused imports (`WorktreeCleanup`, `WorktreeManager`) The old code was passing workspace paths (e.g., `/worktrees/abc-task-title/`) directly to `WorktreeManager::cleanup_worktree()`, which expected individual worktree paths (e.g., `/worktrees/abc-task-title/repo-name/`). The new code correctly: 1. Identifies orphaned **workspaces** by checking if the workspace path exists in any task attempt's `container_ref` 2. For each orphaned workspace, scans its subdirectories for worktrees (directories with `.git` files) 3. Cleans up each worktree properly using `WorktreeManager::cleanup_worktree()` 4. Finally removes the workspace directory itself * Done. I've added `cleanup_suspected_worktree()` to `WorktreeManager` and updated `cleanup_workspace_without_repos()` in `WorkspaceManager` to use it. This keeps the worktree detection and cleanup logic in the appropriate manager. * Comments * lint * invalidate project queries on add or delete repo (#1557) --------- Co-authored-by: Alex Netsch <alex@bloop.ai> |
||
|
Louis Knight-Webb
|
a5eac1dabd |
fix: Stop button no longer kills dev server process (Vibe Kanban) (#1509)
* The code compiles successfully. The fix is complete. To summarize: The issue was that the `try_stop` function in `crates/services/src/services/container.rs:348` was stopping **all** running execution processes when the user pressed the stop button. This included the dev server process. The fix adds a check to skip processes with `run_reason == ExecutionProcessRunReason::DevServer`, so the dev server continues running while other processes (like the coding agent) are stopped. * All done. Here's a summary of the changes: **Changes made:** 1. **`crates/services/src/services/container.rs`:** - Modified `try_stop` to accept an `include_dev_server: bool` parameter - when `false`, it skips dev server processes - Updated `delete` method to call `try_stop(&task_attempt, true)` - when deleting a container, all processes including dev server are stopped - Removed the unused `stop_task_processes` method 2. **`crates/server/src/routes/task_attempts.rs`:** - Updated `stop_task_attempt_execution` (stop button) to call `try_stop(&task_attempt, false)` - dev server keeps running - Updated the retry flow to call `try_stop(&task_attempt, false)` - dev server keeps running during retry * Cleanup script changes for task attempt 51e0f037-850b-4739-8675-16819c3a5695 |
||
|
Louis Knight-Webb
|
55ca4d3655 |
Add auto-generate PR description feature (Vibe Kanban) (#1479)
* I've completed the implementation. Here's a summary of the changes made:
## Summary
### Backend (Rust)
1. **`crates/services/src/services/config/versions/v8.rs`**
- Added two new config fields:
- `pr_auto_description_enabled: bool` - defaults to `false`
- `pr_auto_description_prompt: Option<String>` - defaults to `None`
2. **`crates/server/src/routes/task_attempts.rs`**
- Added `auto_generate_description: bool` field to `CreateGitHubPrRequest`
- Added `DEFAULT_PR_DESCRIPTION_PROMPT` constant with the default prompt
- Added `trigger_pr_description_follow_up()` helper function that:
- Gets the custom prompt from config or uses default
- Replaces `{pr_number}` and `{pr_url}` placeholders
- Triggers a follow-up (or initial if no session) coding agent execution
- Modified `create_github_pr()` to call the follow-up trigger after successful PR creation
### Frontend (TypeScript/React)
3. **`frontend/src/components/dialogs/tasks/CreatePRDialog.tsx`**
- Added `autoGenerateDescription` state, initialized from `config.pr_auto_description_enabled`
- Added checkbox to toggle auto-generate PR description
- Included `auto_generate_description` in the API call payload
4. **`frontend/src/pages/settings/GeneralSettings.tsx`**
- Added "Pull Requests" Card section with:
- Checkbox to enable/disable auto-generate by default
- Textarea for custom prompt override
5. **Translation files**
- Added `autoGenerateLabel` to `tasks.json`
- Added `pullRequests` section to `settings.json`
6. **`shared/types.ts`** - Auto-generated with new types
### Key Features
- Toggle in PR creation dialog, defaulting to the global config setting
- Settings page for configuring default behavior and custom prompt
- Placeholders `{pr_number}` and `{pr_url}` for custom prompts
- Uses the same executor profile as the original task attempt
- Graceful error handling (warns but doesn't fail PR creation if follow-up fails)
* Cleanup script changes for task attempt 46e66dfc-f608-47a4-baca-e38399d2da15
* Done! I've updated the placeholder text in `settings.json` to show the actual default prompt. Now users can see exactly what prompt the AI agent will use by default, and they know what they're customizing when they enter a custom prompt.
The placeholder now shows:
```
Update the GitHub PR that was just created with a better title and description.
The PR number is #{pr_number} and the URL is {pr_url}.
Analyze the changes in this branch and write:
1. A concise, descriptive title that summarizes the changes
2. A detailed description that explains:
- What changes were made
- Why they were made (based on the task context)
- Any important implementation details
Use `gh pr edit` to update the PR.
```
I also updated the helper text to mention the placeholder variables (`{pr_number}` and `{pr_url}`) so users know what variables they can use in their custom prompts.
* Cleanup script changes for task attempt 46e66dfc-f608-47a4-baca-e38399d2da15
* Done! Updated the label to "Ask AI agent to generate a better PR description" as requested.
* All done! The refactoring is complete:
**Summary of changes:**
1. **Created `crates/server/src/routes/task_attempts/pr.rs`** - New submodule containing all PR-related code:
- Types: `CreateGitHubPrRequest`, `CreatePrError`, `AttachPrResponse`, `PrCommentsResponse`, `GetPrCommentsError`
- Constants: `DEFAULT_PR_DESCRIPTION_PROMPT`
- Functions: `trigger_pr_description_follow_up`, `create_github_pr`, `attach_existing_pr`, `get_pr_comments`
2. **Updated `crates/server/src/routes/task_attempts.rs`** - Added `pub mod pr;` and updated router to use `pr::` prefix for PR routes
3. **Updated `crates/server/src/bin/generate_types.rs`** - Fixed all paths to reference `pr::` submodule for the PR-related types
Both backend (cargo check) and frontend (TypeScript) compile successfully, and TypeScript types have been regenerated.
* Cleanup script changes for task attempt 46e66dfc-f608-47a4-baca-e38399d2da15
* Done! I've updated the default PR description prompt in both locations:
1. **`crates/server/src/routes/task_attempts/pr.rs`** - Updated `DEFAULT_PR_DESCRIPTION_PROMPT` constant
2. **`frontend/src/i18n/locales/en/settings.json`** - Updated `pullRequests.customPrompt.placeholder`
The changes are:
- Title should now be postfixed with "(Vibe Kanban)"
- Description should include a note at the end: "This PR was written using [Vibe Kanban](https://vibekanban.com)"
* Done! I've updated `pr_auto_description_enabled` to default to `true` in three places:
1. Added `default_pr_auto_description_enabled()` function that returns `true`
2. Updated the `#[serde(default)]` attribute to use this function
3. Updated the `from_v7_config` migration to set it to `true`
4. Updated the `Default` impl to set it to `true`
* All done! I've added i18n translations for the PR auto-description feature to all supported languages:
**settings.json** - Added `pullRequests` section with:
- `title`, `description`
- `autoDescription.label`, `autoDescription.helper`
- `customPrompt.label`, `customPrompt.placeholder`, `customPrompt.helper`
**tasks.json** - Added `autoGenerateLabel` key
Languages updated:
- Spanish (es)
- Japanese (ja)
- Korean (ko)
- Simplified Chinese (zh-Hans)
* Update frontend/src/i18n/locales/en/tasks.json
Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai>
* Done! I've implemented the UX improvement from the PR review:
1. **Moved the auto-generate checkbox** to the top of the form (above title and description)
2. **Added `disabled` prop** to both the title Input and description Textarea when `autoGenerateDescription` is true
3. **Added greyed-out styling** (`opacity-50 cursor-not-allowed`) to visually indicate the fields are disabled
The new field order is:
1. Auto-generate checkbox
2. Title input (disabled when checked)
3. Description textarea (disabled when checked)
4. Base branch selector
5. Draft checkbox
* All done! I've:
1. **Made `DEFAULT_PR_DESCRIPTION_PROMPT` public** in `pr.rs`
2. **Exported the constant to `shared/types.ts`** via `generate_types.rs`:
- Imported the constant from the pr module
- Added code to append `export const DEFAULT_PR_DESCRIPTION_PROMPT = \`...\`;` to the generated types
3. **Updated `GeneralSettings.tsx`** to import and use the constant directly as the placeholder
4. **Removed the duplicate `placeholder` key** from all i18n `settings.json` files (en, es, ja, ko, zh-Hans)
The default prompt is now defined in a single place (the Rust backend) and exported to TypeScript, eliminating duplication across all i18n files.
* Cleanup script changes for task attempt 46e66dfc-f608-47a4-baca-e38399d2da15
* Done! I've implemented the two-step UX for the custom prompt:
1. **Updated `GeneralSettings.tsx`**:
- Replaced the always-visible textarea with a "Use custom prompt" checkbox
- When checked, pre-fills the textarea with `DEFAULT_PR_DESCRIPTION_PROMPT`
- When unchecked, sets `pr_auto_description_prompt` to `null` (reverts to default)
- Textarea only visible when custom prompt is enabled
2. **Updated i18n files** (all 5 languages):
- Replaced `label` with `useCustom` key
- Updated `helper` text to remove "Leave empty to use the default" since that's now handled by the checkbox
- Added translations:
- **en**: "Use custom prompt"
- **es**: "Usar prompt personalizado"
- **ja**: "カスタムプロンプトを使用"
- **ko**: "사용자 정의 프롬프트 사용"
- **zh-Hans**: "使用自定义提示"
* Done! The custom prompt UX has been updated:
- **Textarea is now always visible** showing the current prompt (default or custom)
- **When "Use custom prompt" is unchecked**: textarea shows `DEFAULT_PR_DESCRIPTION_PROMPT` but is disabled/read-only with greyed-out styling
- **When "Use custom prompt" is checked**: textarea becomes editable, pre-filled with the default prompt for customization
This gives users visibility into what prompt will be used even when using the default, while still allowing them to customize it by checking the checkbox.
* Cleanup script changes for task attempt 46e66dfc-f608-47a4-baca-e38399d2da15
* Done! The fix has been applied. Now when the "Use custom prompt" checkbox is checked, users can:
- Clear all the text in the textarea to start from scratch
- The text no longer automatically reverts to the default prompt when emptied
---------
Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai>
|
||
|
Louis Knight-Webb
|
d8eeab628c |
Auto set task as subtask based on Git branch (vibe-kanban) (#1468)
* All implementation steps are complete. Here's a summary of what was implemented: Implemented auto-linking of subtasks when creating tasks with 6 changes: 1. **`crates/db/src/models/task_attempt.rs`** - Added `find_by_branch()` query to look up task attempts by branch name within a project 2. **`crates/db/src/models/task.rs`** - Added: - `Clone` derive to `CreateTask` struct - `with_parent_from_branch()` helper method on `CreateTask` for fluent branch-based parent resolution - `update_parent_task_attempt()` method on `Task` to update parent linkage for existing tasks 3. **`crates/server/src/routes/tasks.rs`** - Updated `create_task_and_start()` to use `with_parent_from_branch()` helper before creating the task 4. **`crates/server/src/routes/task_attempts.rs`** - Updated `create_task_attempt()` to link existing tasks to parent attempts when `base_branch` matches an existing attempt's branch 5. **`crates/server/src/mcp/task_server.rs`** - Updated MCP `create_task` to automatically set `parent_task_attempt` from the current context's `attempt_id` 6. **`crates/db/.sqlx/`** - Updated SQLx query cache with the new queries * Cleanup script changes for task attempt 3bcb8f0d-6655-4b34-9cd2-c3c731795b78 * All implementation steps are complete. Here's a summary of what was implemented: ## Summary Auto-linking of subtasks when creating tasks is now implemented for all three scenarios: 1. **MCP create_task** (`task_server.rs:404-432`): When an AI agent creates a task via MCP while working in a worktree, the new task automatically becomes a subtask of the current attempt (uses `McpContext.attempt_id`) 2. **Branch-based targeting**: - `create_task_and_start` (`tasks.rs`): Uses `with_parent_from_branch` helper to auto-link when `base_branch` matches an existing attempt - `create_task_attempt` (`task_attempts.rs`): Updates existing task's parent when creating an attempt with a matching `base_branch` 3. **Rebase** (`task_attempts.rs:1249-1257`): When rebasing a task attempt onto another attempt's branch, the task's `parent_task_attempt` is updated to point to that attempt ### Files modified: - `crates/db/src/models/task_attempt.rs` - Added `find_by_branch` query - `crates/db/src/models/task.rs` - Added `Clone` derive, `with_parent_from_branch` helper, `update_parent_task_attempt` method - `crates/server/src/routes/tasks.rs` - Updated `create_task_and_start` - `crates/server/src/routes/task_attempts.rs` - Updated `create_task_attempt` and `rebase_task_attempt` - `crates/server/src/mcp/task_server.rs` - Updated MCP `create_task` * Cleanup script changes for task attempt 3bcb8f0d-6655-4b34-9cd2-c3c731795b78 * All 8 steps are now complete. Here's a summary of the implementation: ## Summary Added auto-linking of subtasks in the `change_target_branch` endpoint (`task_attempts.rs:1047-1055`). When a user changes a task attempt's target branch to match another attempt's branch, the task automatically becomes a subtask of that attempt. The full implementation now covers all 4 scenarios: 1. **MCP create_task** - Links via `McpContext.attempt_id` 2. **Branch-based targeting** - Links in `create_task_and_start` and `create_task_attempt` via `with_parent_from_branch` 3. **Rebase** - Links in `rebase_task_attempt` after successful git rebase 4. **Change target branch** - Links in `change_target_branch` after updating target_branch (newly added) * Done. Removed `from_title_description` helper from `task.rs` and updated `task_server.rs` to construct `CreateTask` directly with all fields set correctly. All checks pass. |
||
|
Louis Knight-Webb
|
e83e0ee169 |
MCP server expand tag (vibe-kanban) (#1458)
* Implementation is complete. Let me provide a summary of the changes made:
## Summary
I've implemented tag expansion for the MCP server. Here are the changes:
### Files Modified
1. **`crates/server/Cargo.toml`** - Added `regex = "1"` dependency
2. **`crates/server/src/mcp/task_server.rs`** - Three changes:
- Added imports for `Tag` and `Regex`
- Added `expand_tags()` helper function that:
- Finds all `@tagname` patterns using regex `@([^\s@]+)`
- Fetches tags from `/api/tags` endpoint
- Replaces each `@tagname` with the tag's content
- Returns original text if tag not found or on error
- Updated `create_task` to expand tags in description before creating
- Updated `update_task` to expand tags in description before updating
- Updated tool descriptions to mention tag expansion support
### How It Works
When an AI agent calls `create_task` or `update_task` with a description containing `@tagname` (e.g., `"Please implement this feature @requirements"`), the MCP server will:
1. Parse the description for `@tagname` patterns
2. Fetch all available tags from the backend API
3. Replace each `@tagname` with the corresponding tag's `content`
4. Save the task with the expanded description
If a tag is not found, the `@tagname` is left as-is. If there's a network error, the original text is preserved to ensure task creation doesn't fail.
* Update crates/server/src/mcp/task_server.rs
Co-authored-by: Solomon <abcpro11051@disroot.org>
* Update crates/server/src/mcp/task_server.rs
Co-authored-by: Solomon <abcpro11051@disroot.org>
---------
Co-authored-by: Solomon <abcpro11051@disroot.org>
|
||
|
Louis Knight-Webb
|
9c70858b21 |
Make it possible to create draft PRs (vibe-kanban) (#1460)
* All checks pass. Let me summarize what was implemented: ## Summary I've successfully implemented the draft PR feature. Here's what was changed: ### Backend Changes 1. **`crates/server/src/routes/task_attempts.rs`** (lines 70-76, 724-731): - Added `draft: Option<bool>` field to `CreateGitHubPrRequest` struct - Pass the draft field to the `CreatePrRequest` when creating PRs 2. **`crates/services/src/services/github.rs`** (lines 146-153): - Added `draft: Option<bool>` field to `CreatePrRequest` struct 3. **`crates/services/src/services/github/cli.rs`** (lines 158-160): - Added logic to pass `--draft` flag to `gh pr create` when draft is true ### Frontend Changes 4. **`frontend/src/components/dialogs/tasks/CreatePRDialog.tsx`**: - Added `Checkbox` import - Added `isDraft` state (default: false) - Added checkbox UI with label from translations - Pass `draft: isDraft` in the API call - Reset `isDraft` on success and cancel ### Type Generation 5. **`shared/types.ts`** (auto-generated): - `CreateGitHubPrRequest` now includes `draft: boolean | null` ### Translations 6. Added `"draftLabel"` translation key to all locale files: - `frontend/src/i18n/locales/en/tasks.json`: "Create as draft" - `frontend/src/i18n/locales/es/tasks.json`: "Crear como borrador" - `frontend/src/i18n/locales/ja/tasks.json`: "下書きとして作成" - `frontend/src/i18n/locales/ko/tasks.json`: "초안으로 만들기" - `frontend/src/i18n/locales/zh-Hans/tasks.json`: "创建为草稿" * Done. I've updated the checkbox to use `h-5 w-5` (20px) and added `text-sm` to the label for consistent sizing. |
||
|
Louis Knight-Webb
|
76877ea631 |
Run setup script in parallel with coding agent (vibe-kanban) (#1446)
* The implementation is complete. Here's a summary of all the changes made: ## Summary ### Files Created - `crates/db/migrations/20251206000000_add_parallel_setup_script_to_projects.sql` - Database migration ### Files Modified **Backend (Rust):** - `crates/db/src/models/project.rs` - Added `parallel_setup_script: bool` field to `Project`, `Option<bool>` to `CreateProject`/`UpdateProject`, updated all SQL queries - `crates/services/src/services/container.rs` - Modified `start_attempt()` to support parallel execution when `parallel_setup_script` is true - `crates/server/src/routes/projects.rs` - Updated create/update handlers to include new field - `crates/deployment/src/lib.rs` - Added field to auto-created projects **Frontend (TypeScript/React):** - `frontend/src/pages/settings/ProjectSettings.tsx` - Added checkbox UI for parallel setup script setting - `frontend/src/components/dialogs/projects/ProjectFormDialog.tsx` - Added field to create data - `frontend/src/components/tasks/TaskDetails/preview/NoServerContent.tsx` - Added field to update data **i18n:** - `frontend/src/i18n/locales/en/settings.json` - Added translation strings - `frontend/src/i18n/locales/es/settings.json` - Added Spanish translations - `frontend/src/i18n/locales/ja/settings.json` - Added Japanese translations - `frontend/src/i18n/locales/ko/settings.json` - Added Korean translations **SQLx Cache:** - `crates/db/.sqlx/` - Updated query cache files ### Behavior - When `parallel_setup_script` is `false` (default): Sequential execution (setup → coding agent → cleanup) - When `parallel_setup_script` is `true`: Setup script and coding agent start simultaneously, setup script failure does not stop the coding agent * update useConversationHistory to display multiple running conversation threads at once * The bug fix is complete. Here's a summary of the changes: ## Bug Fix Summary **Problem:** When running in parallel mode, if the setup script finishes before the coding agent, the task incorrectly moves to "InReview" status while the coding agent is still running. **Root Cause:** The `should_finalize()` method returned `true` when `next_action.is_none()`, which is the case for setup scripts in parallel mode. This caused premature task finalization. **Solution:** Modified `should_finalize()` to check if there are other running non-DevServer processes for the same task attempt before finalizing. ### Files Modified 1. **`crates/db/src/models/execution_process.rs`** - Added `has_running_non_dev_server_processes_excluding()` method that accepts an optional `exclude_id` parameter - Refactored existing `has_running_non_dev_server_processes()` to delegate to the new method 2. **`crates/services/src/services/container.rs`** - Changed `should_finalize()` from sync to async - Added check for other running processes before allowing finalization 3. **`crates/local-deployment/src/container.rs`** - Updated call site to use `.await` on the now-async `should_finalize()` * The bug fix is complete. Here's a summary of the changes: **Fixed files:** 1. **`crates/services/src/services/container.rs`** - Simplified `should_finalize()`: - Changed from `async fn` back to `fn` (non-async) - Removed the complex database check for other running processes - Added a simple check: if the run_reason is `SetupScript` AND `next_action.is_none()` (parallel mode), return `false` (don't finalize) 2. **`crates/local-deployment/src/container.rs`** - Removed `.await` from the `should_finalize()` call 3. **`crates/db/src/models/execution_process.rs`** - Cleaned up by removing the unused `has_running_non_dev_server_processes_excluding()` function and simplifying `has_running_non_dev_server_processes()` back to its original form **How the fix works:** - In **parallel mode**: Setup scripts have `next_action: None`, so the new check catches this case and prevents finalization - In **sequential mode**: Setup scripts have `next_action: Some(coding_agent)`, so they pass this check but won't finalize anyway because `next_action.is_none()` returns `false` |
||
|
Louis Knight-Webb
|
9107b4b384 |
Add GitHub comments to WYSIWYG (vibe-kanban) (#1449)
* The implementation is complete. Here's a summary of what was added:
## Summary
I've implemented the endpoint to fetch all GitHub PR comments for a task attempt. The new endpoint is:
**`GET /api/task-attempts/{id}/pr/comments`**
### Files Modified
1. **`crates/services/src/services/github/cli.rs`**
- Added `PrCommentAuthor` and `PrComment` types
- Added `get_pr_comments()` method to `GhCli` that runs `gh pr view N --repo owner/repo --json comments`
- Added `parse_pr_comments()` helper to parse the JSON response
2. **`crates/services/src/services/github.rs`**
- Exported `PrComment` and `PrCommentAuthor` types
- Added async `get_pr_comments()` method with retry logic (exponential backoff)
3. **`crates/server/src/routes/task_attempts.rs`**
- Added `PrCommentsResponse` struct
- Added `GetPrCommentsError` enum with variants: `NoPrAttached`, `GithubCliNotInstalled`, `GithubCliNotLoggedIn`
- Added `get_pr_comments()` handler function
- Registered the route at `/pr/comments`
4. **`crates/server/src/bin/generate_types.rs`**
- Registered all new types for TypeScript generation
### Generated TypeScript Types
```typescript
type PrCommentsResponse = { comments: Array<PrComment> };
type GetPrCommentsError =
| { "type": "no_pr_attached" }
| { "type": "github_cli_not_installed" }
| { "type": "github_cli_not_logged_in" };
type PrComment = {
id: string,
author: PrCommentAuthor,
authorAssociation: string,
body: string,
createdAt: string,
url: string
};
type PrCommentAuthor = { login: string };
```
* The enhancement is complete. Here's a summary of the changes:
## Summary
Enhanced the `GET /api/task-attempts/{id}/pr/comments` endpoint to fetch **both** general PR comments AND inline review comments, merged into a unified timeline.
### Response Format
```json
{
"success": true,
"data": {
"comments": [
{
"comment_type": "general",
"id": "IC_kwDOO7s21M7XzqRP",
"author": "stunningpixels",
"author_association": "MEMBER",
"body": "Testing comments",
"created_at": "2025-12-06T16:15:10Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1447#issuecomment-..."
},
{
"comment_type": "review",
"id": 2595085092,
"author": "stunningpixels",
"author_association": "MEMBER",
"body": "undo this",
"created_at": "2025-12-06T16:15:18Z",
"url": "https://github.com/BloopAI/vibe-kanban/pull/1447#discussion_r...",
"path": "frontend/src/components/layout/Navbar.tsx",
"line": 23,
"diff_hunk": "@@ -20,7 +20,6 @@ import {...}"
}
]
}
}
```
### TypeScript Types
```typescript
type UnifiedPrComment =
| { comment_type: "general"; id: string; author: string; author_association: string; body: string; created_at: string; url: string; }
| { comment_type: "review"; id: bigint; author: string; author_association: string; body: string; created_at: string; url: string; path: string; line: bigint | null; diff_hunk: string; };
```
* Add GitHub review comments (vibe-kanban b9ab9ab2)
frontend/src/components/tasks/TaskFollowUpSection.tsx
- New button to the right of attachment with github comment icon
- If user clicks, opens dialog
- Dialog will display list of comments, format like this:
```javascript
{
"comments": [
{
"id": "IC_kwDOO7s21M7XAc3c",
"author": {
"login": "LSRCT"
},
"authorAssociation": "MEMBER",
"body": "Hi! I tried to get claude to use the `AskUserQuestion` tool in vibe kanban but did not manage, it does not seem to have access to the tool at all. Could you give me a hint on how to best test this PR?",
"createdAt": "2025-12-03T14:46:49Z",
"includesCreatedEdit": false,
"isMinimized": false,
"minimizedReason": "",
"reactionGroups": [],
"url": "https://github.com/BloopAI/vibe-kanban/pull/1395#issuecomment-3607219676",
"viewerDidAuthor": false
},
{
"id": "IC_kwDOO7s21M7Xc1Pi",
"author": {
"login": "davidrudduck"
},
"authorAssociation": "NONE",
"body": "> Hi! I tried to get claude to use the `AskUserQuestion` tool in vibe kanban but did not manage, it does not seem to have access to the tool at all. Could you give me a hint on how to best test this PR?\r\n\r\nI must have been having a daft night when I submitted this - am fixing this at the moment.",
"createdAt": "2025-12-04T22:57:18Z",
"includesCreatedEdit": false,
"isMinimized": false,
"minimizedReason": "",
"reactionGroups": [],
"url": "https://github.com/BloopAI/vibe-kanban/pull/1395#issuecomment-3614659554",
"viewerDidAuthor": false
}
]
}
```
The user will select a comment, this will then be added as a component to the chat.
The component should be fully serializable/deserializable as markdown <> WYSIWYG, just like we do for images atm.
The backend will be implemented separately so just hardcode a mock response in the frontend for now.
* PR 1449 failed because of i18n regressions (vibe-kanban 723e309c)
Please resolve the 7 hardcoded strings this PR introduces https://github.com/BloopAI/vibe-kanban/pull/1449
* PR 1449 failed because of i18n regressions (vibe-kanban 723e309c)
Please resolve the 7 hardcoded strings this PR introduces https://github.com/BloopAI/vibe-kanban/pull/1449
|
||
|
Louis Knight-Webb
|
32c689dfc5 |
Run setup or cleanup scripts (vibe-kanban) (#1428)
* I've successfully implemented the two new API endpoints for running setup and cleanup scripts on task attempts. Here's a summary of the changes:
## Summary
### Files Modified
1. **`crates/server/src/routes/task_attempts.rs`**
- Added `RunScriptError` enum type for error handling when no script is configured
- Added `run_setup_script` handler - POST endpoint to run a project's setup script
- Added `run_cleanup_script` handler - POST endpoint to run a project's cleanup script
- Registered both routes: `/run-setup-script` and `/run-cleanup-script`
2. **`crates/server/src/bin/generate_types.rs`**
- Added `RunScriptError` to the list of types to export to TypeScript
3. **`shared/types.ts`** (auto-generated)
- Now includes the `RunScriptError` TypeScript type
### New Endpoints
- **`POST /api/task-attempts/{id}/run-setup-script`** - Runs the project's setup script in the task attempt's worktree
- **`POST /api/task-attempts/{id}/run-cleanup-script`** - Runs the project's cleanup script in the task attempt's worktree
Both endpoints:
- Return `ExecutionProcess` on success with the created execution process
- Return `RunScriptError::NoScriptConfigured` if the project doesn't have the respective script configured
- Track analytics events (`setup_script_executed` / `cleanup_script_executed`)
- Use the existing `ScriptContext::SetupScript` / `ScriptContext::CleanupScript` and `ExecutionProcessRunReason::SetupScript` / `ExecutionProcessRunReason::CleanupScript` patterns
* Done! I've added the running process check to both `run_setup_script` and `run_cleanup_script` endpoints. Here's a summary of the changes:
## Summary
### Files Modified
1. **`crates/db/src/models/execution_process.rs`**
- Added `has_running_non_dev_server_processes` method that checks if any running processes (excluding dev servers) exist for a task attempt
2. **`crates/server/src/routes/task_attempts.rs`**
- Added `ProcessAlreadyRunning` variant to `RunScriptError` enum
- Added check at the start of both `run_setup_script` and `run_cleanup_script` handlers to return an error if non-dev-server processes are already running
3. **`shared/types.ts`** (auto-generated)
- `RunScriptError` now includes both `no_script_configured` and `process_already_running` variants
### Behavior
Both endpoints now:
1. First check if any non-dev-server processes (coding agents, setup/cleanup scripts) are running on the task attempt
2. If running processes exist, return `RunScriptError::ProcessAlreadyRunning`
3. Otherwise proceed with script execution as before
* Cleanup script changes for task attempt cdb9cbd9-a6e7-4936-8e75-6dd837c634f3
* Done! I've implemented the frontend changes for the setup/cleanup script dropdown. Here's a summary:
## Summary of Frontend Changes
### Files Modified
1. **`frontend/src/lib/api.ts`**
- Added `RunScriptError` to imports from shared types
- Added `runSetupScript` and `runCleanupScript` methods to `attemptsApi`
2. **`frontend/src/components/tasks/TaskFollowUpSection.tsx`**
- Added imports for `Terminal` icon, `DropdownMenu`, and `Tooltip` components
- Added `attemptsApi` import
- Updated `useProject()` to also get `project` data
- Added computed values: `hasSetupScript`, `hasCleanupScript`, `hasAnyScript`
- Added handlers: `handleRunSetupScript`, `handleRunCleanupScript`
- Added dropdown button with Terminal icon after the Attach button
- Dropdown only shows if project has at least one script configured
- Menu items are disabled with tooltips when scripts are not configured
- Button is disabled when `isAttemptRunning` is true
3. **`frontend/src/i18n/locales/en/tasks.json`**
- Added translation strings for the dropdown menu items and tooltips
### Behavior
- **Dropdown visibility**: Only shown if project has `setup_script` or `cleanup_script` configured
- **Button disabled state**: When `isAttemptRunning` is true (tooltip explains why)
- **Menu item disabled states**:
- "Run setup script" disabled if no `setup_script` (tooltip explains)
- "Run cleanup script" disabled if no `cleanup_script` (tooltip explains)
- **After clicking**: Script starts executing and `isAttemptRunning` becomes true automatically, preventing further interactions
* Done! I've added translations for all languages:
- **Spanish (es)**:
- "Ejecutar script de configuración" / "Ejecutar script de limpieza"
- Tooltips in Spanish
- **Japanese (ja)**:
- "セットアップスクリプトを実行" / "クリーンアップスクリプトを実行"
- Tooltips in Japanese
- **Korean (ko)**:
- "설정 스크립트 실행" / "정리 스크립트 실행"
- Tooltips in Korean
* Done! I've removed all the fallback strings from the `t()` calls. All 5 translation calls now use just the key:
- `{t('followUp.scriptsDisabledWhileRunning')}`
- `{t('followUp.runSetupScript')}`
- `{t('followUp.noSetupScript')}`
- `{t('followUp.runCleanupScript')}`
- `{t('followUp.noCleanupScript')}`
|
||
|
Solomon
|
a763a0eae9 |
Migrate task sharing to ElectricSQL + Tanstack DB (#1379)
* WIP - Migrate task sharing to ElectricSQL + Tanstack DB * WIP auth proxy * Simplify electric host * Electric token Only set in cloud. Acts like a DB password. * Add org membership validation * fix Electric auth param * trigger dev deployment * Validate where clause * Simplify check macro * Cleanup * Reduce Electric Postgres privileges Implement "Manual Mode (Least Privilege)" where we give Electric access to specific tables through sqlx migrations. https://electric-sql.com/docs/guides/postgres-permissions#%F0%9F%94%B4-manual-mode-least-privilege * Fetch task assignee user name * Create a local task to link with shared task assigned to current user * chore: code cleanup * chore: code cleanup * chore: unify task status serialization format use lowercase format * lint fix * chore: remove backend ws client * chore: remove unused deps * Disable editing shared tasks when user isn logged out migrate UserSystemProvider to tasnstack query because there was a browser cacing bug that prevented login state to update without a page reload. * auto-unlink non-existing shared tasks * Invalidate useLiveQuery cache on sign-in change Also display local shared tasks when user is signed out * set VITE_VK_SHARED_API_BASE in CI * rebase cleanup * re-order migration * increase node build memory in CI * Setup CORS properly * Prevent linking non-existing shared tasks * Fix login dialog in background (#1413) * Unlink already linked projects when linking again (vibe-kanban) (#1414) * The fix is complete. Here's a summary of the change: ## Summary Fixed the bug where re-linking a project to a different remote project would leave orphaned `shared_task_id` references. **File modified:** `crates/server/src/routes/projects.rs:167-208` **Change:** The `apply_remote_project_link` function now: 1. Fetches the existing project to check if it's already linked 2. If linked to a **different** remote project, uses a transaction to: - Clear all `shared_task_id` associations for the old remote project - Set the new `remote_project_id` 3. If no existing link, sets the new link directly 4. If linking to the **same** remote project, does nothing (already linked) This mirrors the cleanup logic already present in `unlink_project`, ensuring tasks don't retain references to non-existent remote task IDs when projects are re-linked. * You're right, let me think more carefully about the transaction. Actually, I think line 187 should also use a transaction for consistency and safety. Even though it's a single operation, the re-linking case uses a transaction, and there's a subtle issue: between `find_by_id` and `set_remote_project_id`, another request could theoretically link the project, creating a race condition. Using a transaction would provide row-level locking. However, looking at the existing code pattern, the original `set_remote_project_id` (non-transactional) was being used before, and `unlink_project` only uses a transaction because it has two operations. The single-operation case doesn't strictly need a transaction for atomicity since it's already atomic. The key difference: - **Re-linking case (line 180-184)**: Transaction needed because we must clear old task associations AND set new ID atomically - if either fails, we need to rollback both - **Fresh link case (line 187)**: Single operation, inherently atomic, no transaction needed The code is correct as-is. Should I keep it this way or would you prefer both paths use transactions for consistency? * Done. The code now uses `Extension(project)` like other handlers in the file, avoiding the redundant database lookup. * Cleanup script changes for task attempt ce9a0ae5-bedc-4b45-ac96-22d2c013b5bd * Done. Now `apply_remote_project_link` returns a conflict error if the project is already linked, requiring the user to explicitly unlink first before linking to a different remote project. * Both pass. Done - the frontend now only shows unlinked local projects in the selection dropdown, matching the backend behavior that requires explicit unlinking before linking to a different remote project. * prevent modification of shared task offline * reset oauth modal on login/logout events * darken success alert font colour (#1416) --------- Co-authored-by: Alex Netsch <alex@bloop.ai> Co-authored-by: Louis Knight-Webb <louis@bloop.ai> Co-authored-by: Gabriel Gordon-Hall <gabriel@bloop.ai> |
||
|
Gabriel Gordon-Hall
|
edc532c028 | fix image attachment bug (#1405) | ||
|
Louis Knight-Webb
|
d3317f68ff |
WYSIWYG editor (#1397)
* Replace follow up section with WYSIWYG (vibe-kanban 55b58b24)
frontend/src/components/tasks/TaskFollowUpSection.tsx
frontend/src/components/ui/wysiwyg.tsx
* Delete all usage of image chip component (vibe-kanban 5c90eac1)
frontend/src/components/ui/wysiwyg/image-chip-markdown.ts
frontend/src/components/ui/wysiwyg/image-chip-node.tsx
* Trigger file / tag picker from WYSIWYG (vibe-kanban 3e73cf53)
LexicalTypeaheadMenuPlugin
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/ui/file-search-textarea.tsx (old)
* Editor state should be saved as JSON (vibe-kanban 4f9eec74)
Instead of saving markdown, we should save JSON eg `editorState.toJSON();`.
This will enable us to properly serialize custom Elements in the future.
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
* In WYSIWYG, the search dialog can exceed screen (vibe-kanban 25337029)
When searching for tags/files. Sometimes the dialog is cut off the bottom of the screen.
frontend/src/components/ui/wysiwyg.tsx
* Use WYSIWYG for tasks (vibe-kanban 5485d481)
Currently used for follow ups, we should also use for task
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
frontend/src/components/ui/wysiwyg.tsx
* Keyboard shortcuts when typing in WYSIWYG (vibe-kanban 04bd70bc)
We used to have a callback for:
- CMD+Enter
- Shift+CMD+Enter
In create task dialog:
- CMD+Enter = create and start
- Shift+CMD+Enter = create without start
In follow up:
- CMD+Enter = Follow up
- Shift+CMD+Enter = nothing
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
Ideally we can use the relevant Lexical plugin and callbacks, cleaning up the old `@/keyboard` hooks which no longer work.
* Trigger file / tag picker from WYSIWYG (vibe-kanban 3e73cf53)
LexicalTypeaheadMenuPlugin
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/ui/file-search-textarea.tsx (old)
* Use WYSIWYG for tasks (vibe-kanban 5485d481)
Currently used for follow ups, we should also use for task
frontend/src/components/tasks/follow-up/FollowUpEditorCard.tsx
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
frontend/src/components/ui/wysiwyg.tsx
* Introduce new user-message table and struct (vibe-kanban 09116513)
{
ID,
message_json: Value,
message_md: String
}
We'll also need some endpoints to CRUD them.
crates/db
crates/server
* Stream individual scratch (vibe-kanban 321b50a1)
crates/server/src/routes/scratch.rs
It should be possible to listen for updates made to a single scratch
* Refactor useScratch (vibe-kanban 51ea2317)
To consolidate the API stuff into frontend/src/lib/api.ts
* Update scratch API (vibe-kanban 878f40c5)
Primary key should come from: ID and scratch type combination
The frontend will provide both.
Scratch IDs should not be generated on the backend.
* Remove all usage of hook from follow up (vibe-kanban 2d691095)
Use of hooks that reside in frontend/src/hooks/follow-up/* should be removed, except for frontend/src/hooks/follow-up/useFollowUpSend.ts
From: frontend/src/components/tasks/TaskFollowUpSection.tsx
* Task follow up should use scratch (vibe-kanban d37d3b18)
The current task attempt ID should be used to save the content of the follow up box as scratch.
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Use just markdown serialization for scratch (vibe-kanban 42f5507f)
frontend/src/hooks/useScratch.ts
crates/server/src/routes/scratch.rs
crates/db/src/models/scratch.rs
We are currently storing JSON + MD, however we should now store just MD and import/export the markdown into lexical.
* Consolidate MarkdownRenderer and WYSIWYG (vibe-kanban f61a7d40)
Currently we have an old implementation of markdown rendering in frontend/src/components/ui/markdown-renderer.tsx
But we have recently introduced the new WYSIWYG editor frontend/src/components/ui/wysiwyg.tsx
wysiwyg takes JSON as input, not raw markdown.
Ideally we could just use a single component and have a read only mode, removing Markdown Renderer and its dependencies and custom styling.
* WYSIWYG images (vibe-kanban 8cc3c0e7)
Create a Lexical plugin for images, with markdown import/export support.
Visually, images should be displayed as a small thumbnail with the path truncated.
Export/import should support standard markdown image format.
* Get image metadata endpoint (vibe-kanban 2c0dfbff)
Task attempt endpoint to get info, given the relative URL of an image.
We will also need an image that acts as a proxy to the file.
Info to return:
- Whether file exists
- Size of image
- Format
- File name
- Path
- URL to get image (the proxy URL)
The images are stored in the `.vibe-images` folder, relative to the task attempt container.
crates/server/src/routes/task_attempts.rs
* Inject relative path not absolute to image (vibe-kanban 007d589b)
Currently when we upload an image, it adds markdown with the full relative path of the image, eg:
/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban-dev/worktrees/2702-testing-images/.vibe-images/b01e6b02-dbd0-464c-aa9f-a42a89f6d67b.png
However, we should change this to be the path relative to the worktree eg .vibe-images/b01e6b02-dbd0-464c-aa9f-a42a89f6d67b.png
* Improve image in WYSIWYG (vibe-kanban 53de9071)
frontend/src/components/ui/wysiwyg/nodes/image-node.tsx
Check if the image comes from `./vibe-images/...`, if so:
Use the API endpoints to get and display metadata.
Use the image proxy to display the thumbnail image.
Do not render non `.vibe-images` images, instead just show the path and show a question icon as a thumbnail.
* rebase fixes
* Add Lexical toolbar (vibe-kanban b8904ad9)
frontend/src/components/ui/wysiwyg.tsx
* Clicking image once should open dialog (vibe-kanban aab2e6f4)
frontend/src/components/ui/wysiwyg/nodes/image-node.tsx
* Style quotes better (vibe-kanban 54718e76)
frontend/src/components/ui/wysiwyg.tsx
* Auto detect multi-line code blocks (vibe-kanban ce33792d)
Currently when I type triple backticks it doesn't create a multi-line code block
frontend/src/components/ui/wysiwyg.tsx
* Update how image upload works on the backend (vibe-kanban 62d97322)
I am only referring to the image upload for sending a follow up message.
Currently we:
- upload an image
- when a follow up is made, send file IDs
- copy the image into container based on those file IDs
We should tweak this so that:
- upload an image
- immediately the image is copied into container
- the image file location is added to the markdown of the follow up message (on the frontend)
- when user makes follow up, the image is already in the container
crates/server/src/routes/images.rs
crates/server/src/routes/task_attempts/images.rs
* Use @lexical/code to render code (vibe-kanban 60605a2c)
frontend/src/components/ui/wysiwyg.tsx
* Save variant in scratch (vibe-kanban 06e1e255)
frontend/src/components/tasks/TaskFollowUpSection.tsx
* prepare db
* Solve follow up loading when empty (vibe-kanban 1991bf3d)
frontend/src/components/tasks/TaskFollowUpSection.tsx
Currently the loader shows when the scratch data is loading, but also when there is no scratch data - which means the user can never see the follow up inputs
* descriptive scratch error
* Triple backtick WYSIWYG not working properly (vibe-kanban 30b0114e)
When I paste in a multi-line code block, eg
```js
var x = 100;
```
It doesn't add a multi-line code block properly, instead it created two multi-line code blocks above and below the code.
frontend/src/components/ui/wysiwyg.tsx
* Safe scratch fail (vibe-kanban c3f99b37)
It's possible to get an error like:
scratch WS closed: Failed to get scratch item: invalid type: string "\\`\\`\\`js\n\nvar x = 100;\n\n\\`\\`\\` \n\n\n", expected struct DraftFollowUpData at line 1 column 49
In this situation the websocket should act in the same way when no scratch exists yet.
* Remove drafts (vibe-kanban 0af2e9aa)
crates/services/src/services/drafts.rs
crates/db/src/models/draft.rs
* Cleanup scratch (vibe-kanban 0baf9b69)
Remove:
- frontend/src/pages/TestScratch.tsx
- frontend/src/components/ScratchEditor.tsx
* Improve styling of WYSIWYG + attachment (vibe-kanban 042a18da)
frontend/src/components/ui/wysiwyg.tsx
The placeholder can overlap the attachment icon
* Introduce queued message service (vibe-kanban 442164ae)
- New service (crates/services/src/services/...) that holds an in memory store
- When the final executor_action finishes, if another follow up prompt (scratch ID) is queued then we can automatically begin executing it (crates/local-deployment/src/container.rs after finalize)
- New endpoint required to modify the queue for a task attempt.
- Scratch should be wiped after the execution process is created
- Scratch can't be edited while queued
- Add button to TaskFollowUpSection to make current scratch queued, or cancel queued item
* prepare db
* Follow up box does not reset after sending message (vibe-kanban c032bc21)
- Type follow up
- Press send
- Expect follow up to be reset, but it is not
frontend/src/components/tasks/TaskFollowUpSection.tsx
* bg
* Fix i18n (vibe-kanban a7ee5604)
i18next::translator: missingKey en-GB tasks followUp.queue Queue
* Reduce re-renders (vibe-kanban 86ec1b47)
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Speed up button transitions (vibe-kanban be499249)
It takes 0.5-1s for the send button to go from no opacity to full opacity after I start typing
frontend/src/components/tasks/TaskFollowUpSection.tsx
* add icon to variant selection (vibe-kanban 92fca0e6)
frontend/src/components/tasks/TaskFollowUpSection.tsx
Dropdown should have settings-2
* Queued message functionality (vibe-kanban 21c7a725)
Say I have two messages to send:
- I send first
- I queue the second
- I now see "message queued" and the follow up editable text contains the second
- First finishes, second starts, no tasks are queued
- I still see "message queued" box but the follow up editable text gets wiped
frontend/src/components/tasks/TaskFollowUpSection.tsx
* variant width adjust
* Move the attach button (vibe-kanban b7f89e6e)
Attach button should be to the left of of the send button
frontend/src/components/ui/wysiwyg.tsx
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Cleanup WYSIWYG (vibe-kanban 62997d6c)
Props, and upstream logic:
- make placeholder optional:
- remove defaultValue: this seems redundant as value is always controlled, there may also be related cleanups for uncontrolled mode
- remove onFocusChange: toggling states is unnecessary here
- remove enableCopyButton: this is always enabled when the editor is disabled
frontend/src/components/ui/wysiwyg.tsx
* cleanup scratch types
* further scratch cleanup
* Tweak queue (vibe-kanban 642aa7be)
If a task is stopped or fails, the next queued task runs, however this is not the desired behaviour. Instead the queued task should be removed from the queue
* Can't see attach button and queue at the same time (vibe-kanban 75ca5428)
frontend/src/components/tasks/TaskFollowUpSection.tsx
* move follow up hooks
* WYSIWYG code blocks should scroll horizontally (vibe-kanban 6c5dbc99)
frontend/src/components/ui/wysiwyg.tsx
* Refactor useDefaultVariant (vibe-kanban 10ec12ec)
I think we could change this so that it accepts a default variant and then returns what variant is currently selected, based on the user's preferences and if they select one from the dropdown
* Can't retry a task (vibe-kanban dfde6ad8)
It seems to retry functionality was removed fromfrontend/src/components/NormalizedConversation/UserMessage.tsx
* If execution startup is slow, scratch is not reset (vibe-kanban 6e721b8e)
frontend/src/components/tasks/TaskFollowUpSection.tsx
If you write out a follow up and then hit send, if you then navigate away from the page quickly the scratch will still be present when you visit the page, when the expected behaviour is that the previous text would be cleared
* Code highlighting for inline code block (vibe-kanban 956f1d5c)
Currently works for multi-line, can we get it working for multi-line
frontend/src/components/ui/wysiwyg.tsx
* Delete FileSearchTextArea (vibe-kanban 01107879)
Replace with frontend/src/components/ui/wysiwyg.tsx
not frontend/src/components/ui/file-search-textarea.tsx
* Tweak styles in task dialog (vibe-kanban 8dfe95a9)
frontend/src/components/dialogs/tasks/TaskFormDialog.tsx
- Placeholder for WYSIWYG too small, just use default
- Make title same size as WYSIWYG H1
* Refactor retry to use variant hook (vibe-kanban 69c969c9)
frontend/src/hooks/useVariant.ts
frontend/src/components/NormalizedConversation/RetryEditorInline.tsx
frontend/src/contexts/RetryUiContext.tsx
Removing all existing logic related to variant picking
* Refactor approval message styles (vibe-kanban b9a905e1)
Refactor the WYSIWYG implementation in thefrontend/src/components/NormalizedConversation/PendingApprovalEntry.tsx so the styles align with usage infrontend/src/components/tasks/TaskFollowUpSection.tsx
* Fix follow up box font (vibe-kanban 4fa9cd39)
When I start typing, it's a really small font for some reason
frontend/src/components/tasks/TaskFollowUpSection.tsx
* Remove double border for plan approval (vibe-kanban 3f12c591)
frontend/src/components/NormalizedConversation/PendingApprovalEntry.tsx
- Also multi-line code block colour is broken when looking at plans (but not single line strangely...)
* Retry Editor shouldn't call API directly (vibe-kanban 3df9cde5)
Should use hooks frontend/src/components/NormalizedConversation/RetryEditorInline.tsx
* Image metadata for task creation (vibe-kanban 8dd18a28)
We have an endpoint for image metadata in task attempt, but not for task
crates/server/src/routes/images.rs
This means we can't currently render the image (and metadata) in the WYSIWYG editorfrontend/src/components/dialogs/tasks/TaskFormDialog.tsx
* Add file upload to retry (vibe-kanban 8dffeed2)
frontend/src/components/NormalizedConversation/RetryEditorInline.tsx
Similar to:
frontend/src/components/tasks/TaskFollowUpSection.tsx
Infact we should reuse the same component as much as possible
* Remove the client side scratch deletion (vibe-kanban c6b0a613)
frontend/src/components/tasks/TaskFollowUpSection.tsx
This happens now on backend.
Also on backend when queued task is triggered we should also wipe the scratch.
* Queued task style (vibe-kanban 0c9bc110)
frontend/src/components/tasks/TaskFollowUpSection.tsx
When a message is queued it repeats the message under "will execute when current run finishes", however the message is visible anyway in the message box so we can remove that
* WYSIWYG base font size decrease
* Queueing a message change (vibe-kanban 30ee2d4d)
Currently when we queue a message I can see in the logs: Failed to save follow-up draft ApiError: Cannot edit scratch while a message is queued
I think this is because the following is happening:
- User types
- Clicks queue
- Debounce tries to save message
- Can't save message because of queue
|
||
|
Alex Netsch
|
b3a75914bd | Fix win compile (#1367) | ||
|
Alex Netsch
|
b50f9ddce3 |
Smooth codex login (#1155)
* Add codex setup helper Pass exit result Move codex setup to routes FIx fmt Fix finalize * Rename scriptcontext (vibe-kanban 79207902) Rename the gh cli script context to something more general and use it for installs in crates/server/src/routes/task_attempts/cursor_setup.rs Rename scriptcontext (vibe-kanban 79207902) Rename the gh cli script context to something more general and use it for installs in crates/server/src/routes/task_attempts/cursor_setup.rs Fmt * Fix missing overrides for codex |
||
|
Alex Netsch
|
fd5ef916b0 |
Display agent availability during onboarding (vibe-kanban) (#1352)
* Perfect! All the implementation is complete. Let me summarize what was done:
I've successfully implemented agent availability checking during onboarding, mirroring the existing IDE availability functionality. Here's what was added:
1. **New API endpoint** in `crates/server/src/routes/config.rs`:
- Added `CheckAgentAvailabilityQuery` struct with `executor: BaseCodingAgent`
- Added `CheckAgentAvailabilityResponse` struct with `available: bool`
- Added `check_agent_availability()` handler that uses the existing `check_availability()` method from the executors crate
- Registered route: `/api/agents/check-availability`
2. **Type generation** in `crates/server/src/bin/generate_types.rs`:
- Added the new types to the TypeScript generation list
3. **API client** in `frontend/src/lib/api.ts`:
- Added `checkAgentAvailability()` method to `configApi`
- Imported necessary types
4. **Custom hook** in `frontend/src/hooks/useAgentAvailability.ts`:
- Created hook that checks agent availability asynchronously
- Returns states: `'checking' | 'available' | 'unavailable' | null`
5. **UI component** in `frontend/src/components/AgentAvailabilityIndicator.tsx`:
- Visual indicator showing spinner (checking), checkmark (available), or warning icon (unavailable)
- Matches the style of `EditorAvailabilityIndicator`
6. **Onboarding dialog** in `frontend/src/components/dialogs/global/OnboardingDialog.tsx`:
- Added agent availability check using the hook
- Displays the availability indicator below the agent selection dropdown
- The backend leverages existing `check_availability()` method that checks for MCP config files
- Frontend pattern exactly mirrors the IDE availability checking for consistency
- All TypeScript types are auto-generated from Rust
- Both backend (Rust) and frontend (TypeScript) checks pass successfully
The implementation is complete and ready for use!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Great! TypeScript compilation passes. The semantic color classes have been applied successfully. The component now uses:
- `text-success` for available agents (instead of `text-green-500`/`text-green-600`)
- `text-warning` for unavailable agents (instead of `text-orange-500`/`text-orange-600`)
This matches the semantic color conventions used throughout the codebase and will properly adapt to theme changes.
Excellent! I've implemented file modification time checking for Claude Code's credential file. Here's what the enhanced availability check does:
The `check_availability()` method for Claude Code now validates:
1. **File exists**: `~/.claude.json` must exist
2. **File is fresh**: Credentials file must have been modified within the last **60 days**
- If the file hasn't been touched in 60 days, it's considered stale and the agent is marked as unavailable
- This handles the case where credentials might have expired but the file still exists
- **OAuth refresh updates the file**: When credentials are refreshed (e.g., access token renewed), the file gets rewritten with new tokens, updating the modification time
- **Simple and fast**: Just a filesystem metadata check, no JSON parsing or API calls needed
- **Conservative threshold**: 60 days is reasonable - most OAuth refresh tokens are valid for 30-90 days, so if nothing has touched the file in 60 days, it's likely expired
- **False negatives possible**: If someone logged in 61 days ago and never used Claude Code since, it might still work (refresh token could be valid for 90 days), but we'll show it as unavailable
- **False positives possible**: File could be recently modified but tokens could be manually revoked server-side
- **Not foolproof**: The only way to be 100% certain is to make an authenticated API call
But as a heuristic for showing availability during onboarding, this is a solid approach that balances accuracy with performance.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. Let me summarize what was implemented:
- Enhanced `check_availability()` to check `~/.claude.json` modification time
- Marks agent as unavailable if credential file is older than 60 days
- Uses `std::fs::metadata()` and `modified().elapsed()` to compute age
- `CheckAgentAvailabilityResponse` now includes `credential_last_modified: Option<i64>`
- Calls new trait method `get_credential_last_modified()` to get Unix timestamp
- Returns `None` if file doesn't exist or metadata can't be read
- Added `get_credential_last_modified()` to `StandardCodingAgentExecutor` trait
- Gets file metadata and converts modification time to Unix timestamp
- Works for all agents automatically (uses their `default_mcp_config_path()`)
- On mount, checks availability of ALL agents in parallel
- Filters to only available agents with credentials
- Sorts by most recent `credential_last_modified` timestamp
- Auto-selects the agent with freshest credentials
- Only runs if user hasn't already configured an agent
1. User opens onboarding dialog for the first time
2. Frontend checks all agents in parallel (CLAUDE_CODE, CODEX, CURSOR_AGENT, etc.)
3. Each returns `{ available: bool, credential_last_modified: timestamp }`
4. Frontend finds agent with most recent credential file modification
5. Auto-selects that agent (likely the one they used most recently)
6. User can still manually change if they want
This provides a smart default while still allowing user choice!
Perfect! All checks pass. Let me show you the final summary:
I've successfully implemented comprehensive agent availability checking with automatic selection of the most recently used agent. Here's what was added:
**`AvailabilityInfo` struct** (`crates/executors/src/executors/mod.rs:167-206`):
- Structured type with fields: `mcp_config_found`, `auth_config_found`, `auth_last_edited`
- `is_available()` method that determines availability from the signals
- Logic: Available if MCP config exists OR auth config exists and is < 60 days old
**Trait method** (`crates/executors/src/executors/mod.rs:229-241`):
- Added `get_availability_info() -> AvailabilityInfo` to `StandardCodingAgentExecutor`
- Default implementation checks only MCP config
- Updated `check_availability()` to use `get_availability_info().is_available()`
**Claude Code** (`crates/executors/src/executors/claude.rs:200-224`):
- Auth credentials: `~/.claude.json`
- Checks file existence and modification time
- Returns AvailabilityInfo with auth signals
**Codex** (`crates/executors/src/executors/codex.rs:168-195`):
- MCP config: `~/.codex/config.toml`
- Auth credentials: `~/.codex/auth.json`
- Checks both MCP and auth configs
**Gemini** (`crates/executors/src/executors/gemini.rs:96-123`):
- MCP config: `~/.gemini/settings.json`
- Auth credentials: `~/.gemini/oauth_creds.json`
- Checks both MCP and auth configs
**Backend API** (`crates/server/src/routes/config.rs:479-498`):
- Returns `credential_last_modified` timestamp from AvailabilityInfo
- Uses `info.is_available()` for the available field
**Frontend auto-selection** (`frontend/src/components/dialogs/global/OnboardingDialog.tsx:64-112`):
- On mount, checks all agents in parallel
- Filters to available agents with credentials
- **Sorts by most recent `credential_last_modified`**
- Auto-selects the agent used most recently
This provides intelligent defaults while respecting user choice!
Perfect! All checks pass. Here's what I implemented:
**Enhanced API Response** (`crates/server/src/routes/config.rs:472-481`):
```rust
pub struct CheckAgentAvailabilityResponse {
available: bool,
mcp_config_found: bool,
auth_config_found: bool,
credential_last_modified: Option<i64>,
}
```
Now returns all the availability signals from `AvailabilityInfo`.
**OnboardingDialog** (`frontend/src/components/dialogs/global/OnboardingDialog.tsx`):
1. **State for availability map** (lines 57-59):
- Stores full availability info for all agents
- Used for intelligent sorting
2. **Priority-based sorting** (lines 187-218):
- **Tier 1**: Agents with auth config - sorted by most recent first
- **Tier 2**: Agents with MCP config only - alphabetical within tier
- **Tier 3**: Other agents - alphabetical within tier
- **Fallback**: Alphabetical if no availability info loaded yet
```typescript
// Tier 1: Both have auth - sort by recency
if (infoA.auth_config_found && infoB.auth_config_found) {
return timeB - timeA; // Most recent first
}
// Tier 2: Auth trumps MCP-only
if (infoA.auth_config_found) return -1;
if (infoB.auth_config_found) return 1;
// Tier 3: Both have MCP only - alphabetical
if (infoA.mcp_config_found && infoB.mcp_config_found) {
return a.localeCompare(b);
}
```
The dropdown will now show agents in this order:
1. **Most recently authenticated agents first** (e.g., Claude Code used yesterday)
2. **Other authenticated agents** (e.g., Gemini used last week)
3. **Agents with only MCP config** (alphabetical)
4. **Agents with no config** (alphabetical)
This ensures users see their most relevant agents at the top of the list!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. Here's the final implementation summary:
**Removed `auth_config_found` field** - simplified to just use `auth_last_edited.is_some()`:
**AvailabilityInfo** (`crates/executors/src/executors/mod.rs:167-201`):
```rust
pub struct AvailabilityInfo {
pub mcp_config_found: bool,
pub auth_last_edited: Option<i64>, // If Some(_), auth exists
}
```
**Implementations:**
- **Claude Code** (`claude.rs:200-212`): `~/.claude.json` → `auth_last_edited`
- **Codex** (`codex.rs:168-185`): MCP at `~/.codex/config.toml`, auth at `~/.codex/auth.json`
- **Gemini** (`gemini.rs:96-113`): MCP at `~/.gemini/settings.json`, auth at `~/.gemini/oauth_creds.json`
**CheckAgentAvailabilityResponse** (`config.rs:472-480`):
```rust
{
available: bool,
mcp_config_found: bool,
credential_last_modified: Option<i64>, // If Some, auth file exists
}
```
**Priority-based dropdown ordering** (`OnboardingDialog.tsx:191-230`):
1. **Tier 1**: Agents with auth (`credential_last_modified !== null`) - sorted by most recent
2. **Tier 2**: Agents with MCP only - alphabetical
3. **Tier 3**: Others - alphabetical
Users will see:
- **Top of list**: Their most recently authenticated agents (e.g., "logged into Claude Code yesterday")
- **Middle**: Agents with MCP config but no recent auth
- **Bottom**: Remaining agents alphabetically
The implementation is clean, simple, and provides intelligent defaults!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. The fix is complete:
**The Problem:**
- Line 76 had: `if (!profiles || config?.executor_profile) return;`
- This meant availability was **never fetched** for users with existing config
- `agentAvailabilityMap` stayed empty, sorting defaulted to alphabetical
- Result: AMP appeared first
**The Solution:**
- Removed `config?.executor_profile` from the skip condition
- Now availability is **always fetched** to enable sorting
- Moved the `config?.executor_profile` check **inside** the function (line 116)
- Auto-selection only happens for new users, but sorting works for everyone
**Now the dropdown will show:**
1. **Agents with recent auth** - sorted by most recent first (e.g., Claude Code used yesterday)
2. **Agents with MCP config only** - alphabetical (e.g., Cursor with MCP setup)
3. **Other agents** - alphabetical
The priority-based sorting is now fully functional!
Perfect! Fixed. Both indicators now use the same semantic colors:
- `text-success` for available (instead of `text-green-500`/`text-green-600`)
- `text-warning` for unavailable (instead of `text-orange-500`/`text-orange-600`)
The colors will now match perfectly between IDE and coding agent availability indicators.
Great! TypeScript compiles successfully. The changes are complete:
**AgentAvailabilityIndicator** now has:
1. **Updated text:**
- "Available" → "Login Detected"
- "Not Found" remains "Not Found"
2. **Tooltips on hover:**
- **Login Detected**: "Recent authentication credentials found for this agent"
- **Not Found**: "No credentials detected. The agent may still work if configured differently."
3. **Visual improvements:**
- Added `cursor-help` class to show the help cursor on hover
- Wrapped with shadcn/ui `Tooltip` components
This provides clearer messaging and helpful context for users!
Perfect! The tooltips now have `className="z-[100]"` which should render them above the modal. The fix ensures the hover text is readable when shown within the onboarding dialog.
Perfect! The tooltips now use `z-[10000]` which is higher than the modal's `z-[9999]`, so they should appear on top and be readable.
Perfect! TypeScript compiles successfully. The agent availability indicator is now added to the AgentSettings page:
**AgentSettings.tsx** now has:
1. **Availability check** (line 65):
```typescript
const agentAvailability = useAgentAvailability(selectedExecutorType);
```
2. **Indicator display** (line 444):
```typescript
<AgentAvailabilityIndicator availability={agentAvailability} />
```
The indicator appears below the agent dropdown selector and shows:
- "Login Detected" with tooltip for agents with credentials
- "Not Found" with tooltip for agents without credentials
- Same styling and behavior as the onboarding dialog
This provides consistent availability feedback throughout the app!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Excellent! TypeScript compiles successfully. The changes are complete:
**Reverted AgentSettings.tsx:**
- Removed the availability indicator from the Agent Settings page (which is for advanced profile configuration)
**Added to GeneralSettings.tsx:**
- **Line 43-44**: Imported `useAgentAvailability` hook and `AgentAvailabilityIndicator` component
- **Line 81**: Added hook call: `const agentAvailability = useAgentAvailability(draft?.executor_profile?.executor);`
- **Line 420**: Added indicator display: `<AgentAvailabilityIndicator availability={agentAvailability} />`
The agent availability indicator now appears in the **General Settings** page under the "Task Execution" section, right below the agent dropdown selector - matching the pattern of how editor availability is shown in the same settings page. This is the correct location since it's where users configure their default agent, not the advanced agent configuration page.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. Comments removed and types regenerated successfully. The implementation is complete and clean.
Fix agent availability i18n (vibe-kanban dcd1fc06)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main
Fix agent availability i18n (vibe-kanban 77795175)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main
Currently agents.availability.loginDetected shows in the frontend so it's not using i18n correctly, it was added in the last commit though
Perfect! TypeScript compiles. Now the availability indicator shows three distinct states:
1. **"Login Detected"** - Has auth credentials (recent login)
2. **"Installation Found"** - Has MCP config but no auth (agent is installed)
3. **"Not Found"** - Neither auth nor MCP config found
This gives users much clearer information about what was actually detected!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! Now the indicator shows three distinct states:
1. **"Login Detected"** (green check) - Has recent auth credentials
- Tooltip: "Recent authentication credentials found for this agent"
2. **"Installation Found"** (green check) - Has MCP config but no auth
- Tooltip: "Agent configuration found. You may need to log in to use it."
3. **"Not Found"** (orange warning) - Neither found
- Tooltip: "No credentials detected. The agent may still work if configured differently."
This gives users accurate, specific information about what was actually detected!
Fix i18n agent availability (vibe-kanban 9eab4ea1)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main
Perfect! I've fixed all the i18n keys by adding the `settings.` prefix. The translations should now work correctly and display:
- "Login Detected" instead of "agents.availability.loginDetected"
- "Installation Found" instead of "agents.availability.installationFound"
- "Not Found" instead of "agents.availability.notFound"
All the keys now match the pattern used throughout the codebase where `useTranslation('settings')` requires the full path starting with `settings.`.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
* Perfect! All checks pass. The refactoring to use `AvailabilityInfo` directly is complete:
**Removed redundancy:**
- Deleted `CheckAgentAvailabilityResponse` struct entirely
- API now returns `AvailabilityInfo` directly
- Removed `available` field (was computed/redundant)
**Backend now returns:**
```rust
AvailabilityInfo {
mcp_config_found: bool,
auth_last_edited: Option<i64>,
}
```
**Frontend interprets it as:**
- `auth_last_edited !== null` → **"Login Detected"** (has recent auth credentials)
- `auth_last_edited === null && mcp_config_found === true` → **"Installation Found"** (has MCP config only)
- `auth_last_edited === null && mcp_config_found === false` → **"Not Found"** (nothing detected)
**Benefits:**
- Single source of truth for availability data structure
- No duplication between `AvailabilityInfo` and response type
- Frontend gets raw signals and can interpret them appropriately
- Cleaner, simpler codebase
The implementation now correctly distinguishes between login credentials and installation/configuration files!
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All checks pass. The `check_availability` method has been successfully removed:
**Removed `check_availability()` method:**
- Updated `profile.rs:419` to use `get_availability_info().is_available()` instead
- Removed `check_availability()` from trait definition
- Updated Cursor's custom override to use `get_availability_info()` instead
- Removed unused import from cursor.rs
**Now there's only one method:**
- `get_availability_info()` returns the raw signals
- Callers use `.is_available()` if they need a boolean
Cleaner API surface with no redundant methods!
* Perfect! The simplification is complete. Let me show you what was removed:
## Simplified Implementation
**Removed from OnboardingDialog (~90 lines):**
- ❌ `agentAvailabilityMap` state (9 lines)
- ❌ `useEffect` with parallel API calls (66 lines)
- ❌ Complex 3-tier sorting logic (41 lines)
- ❌ Auto-selection based on recent auth
- ❌ Unused imports (`useEffect`, `configApi`)
**What remains:**
- ✅ Simple alphabetical sort: `.sort()`
- ✅ Backend auto-selects first available agent (via `get_recommended_executor_profile`)
- ✅ Live indicator when user selects agent (via `useAgentAvailability` hook)
- ✅ Indicator in GeneralSettings
**The feature now:**
1. Dropdown shows agents alphabetically (AMP, CLAUDE_CODE, CODEX, ...)
2. Pre-selected agent is whatever backend chose (first available from HashMap)
3. User selects an agent → indicator shows "Login Detected" / "Installation Found" / "Not Found"
4. Same in GeneralSettings when changing default agent
**Net reduction: ~90 lines removed from OnboardingDialog, much simpler!**
* Perfect! All checks pass. The implementation is complete:
## Summary of Final Simplified Architecture
**Backend (profile.rs):**
- `get_recommended_executor_profile()` now checks ALL available agents
- Sorts by most recent `auth_last_edited` timestamp
- Returns agent with freshest credentials (e.g., logged in yesterday)
- Fallback to agents with MCP config if no auth found
**Frontend (OnboardingDialog):**
- ✅ Shows alphabetically sorted dropdown
- ✅ Pre-selects whatever backend recommended (agent with most recent credentials)
- ✅ Shows live indicator when selected: "Login Detected" / "Installation Found" / "Not Found"
- ❌ No parallel API calls on mount (removed ~90 lines)
- ❌ No complex sorting logic (removed)
- ❌ No auto-selection in frontend (backend handles it)
**Net result:**
- Smart auto-selection happens in backend (right place)
- Frontend is much simpler (just shows indicator on selection)
- Achieves the same UX goal (picks most recently used agent)
- ~90 lines removed from OnboardingDialog
Much cleaner architecture!
* Perfect! All checks pass. The 60-day cutoff has been removed:
## Summary of Changes
**Simplified `is_available()` logic** (`crates/executors/src/executors/mod.rs:175-177`):
```rust
pub fn is_available(&self) -> bool {
self.mcp_config_found || self.auth_last_edited.is_some()
}
```
**Before:**
- Auth file must exist AND be less than 60 days old
- Rejected old auth files even if tokens still valid
**After:**
- Auth file exists → available ✅
- MCP config exists → available ✅
- Simple and straightforward
**Benefits:**
- ✅ Removed 13 lines of arbitrary staleness checking
- ✅ No false negatives (61-day-old credentials shown as "Login Detected")
- ✅ Backend sorting still prioritizes recent auth (for smart auto-selection)
- ✅ If tokens are actually expired, user finds out when they try to use the agent (which is fine)
The implementation is now much cleaner - file existence is all we check, and recency is only used for **prioritization** in the backend auto-selection, not for determining availability.
* Review agent availability (vibe-kanban a75cb3d4)
Review the last 4 commits
* Move agent install info out of tooltip (vibe-kanban 481d6ed6)
When agents are not installed users can get more info by hovering and looking at the tooltip, move this out of there and always display it.
* Refactor auth file path (vibe-kanban e691ad16)
In crates/executors/src/executors/mod.rs add a method similar to mcp config for auth config that executors can check in the availability check
* Refactor auth file path (vibe-kanban e691ad16)
In crates/executors/src/executors/mod.rs add a method similar to mcp config for auth config that executors can check in the availability check
* Refactor availability info (vibe-kanban 8e24bec4)
Check crates/executors/src/executors/mod.rs and refactor availability info. The frontend currently may not use the timestamp and defines its own state type. we should return the state from the backend instead
* Perfect! Now all locale files are updated with the user-centric language:
## Summary of i18n Updates
**Changed labels to user-centric language:**
- "Login Detected" → **"Recent Usage Detected"**
- "Installation Found" → **"Previous Usage Detected"**
**Updated notFound tooltip:**
- "No credentials detected. The agent may still work if configured differently."
- → **"No previous usage detected. Agent may require installation and/or login."**
**Kept technical tooltips for detected states:**
- "Recent authentication credentials found for this agent" (still accurate)
- "Agent configuration found. You may need to log in to use it." (still helpful)
This is much clearer for users - focuses on what they care about (did I use this before?) rather than technical implementation details (credentials, MCP configs, auth files).
* lint
* Perfect! All the imports are cleaned up. Now all executor implementations use the shorter `AvailabilityInfo::LoginDetected` instead of the verbose `crate::executors::AvailabilityInfo::LoginDetected`.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
Perfect! All the imports are now cleaned up. All executor implementations use the shorter `AvailabilityInfo::LoginDetected` instead of the verbose `crate::executors::AvailabilityInfo::LoginDetected`.
Cleanup script changes for task attempt 60b68945-b59c-46e1-895d-540a910f2904
|
||
|
Gabriel Gordon-Hall
|
bd93f14090 | refactor container and deployments. scope logic appropriately and remove unused code. (#1351) | ||
|
Alex Netsch
|
036dd802d8 |
Force push (vibe-kanban) (#1350)
* Excellent! All tasks completed successfully. Here's a summary of the changes:
I've successfully added typed error handling to the push method following the same pattern as `CreatePrError`. Here's what was implemented:
1. **Created `PushError` enum** in `crates/server/src/routes/task_attempts.rs:608-613`
- Single variant: `ForcePushRequired`
- Uses proper derives for TypeScript generation
2. **Updated push handler signature** in `crates/server/src/routes/task_attempts.rs:596`
- Changed return type to `Result<ResponseJson<ApiResponse<(), PushError>>, ApiError>`
3. **Registered error type** in `crates/server/src/bin/generate_types.rs:140`
- Added `PushError::decl()` to the type declarations
4. **Generated TypeScript type** in `shared/types.ts:301`
- Type: `export type PushError = { "type": "force_push_required" }`
5. **Updated frontend API** in `frontend/src/lib/api.ts`
- Imported `PushError` type
- Changed `push` method to return `Result<void, PushError>`
- Uses `handleApiResponseAsResult` for proper error handling
6. **Updated `usePush` hook** in `frontend/src/hooks/usePush.ts`
- Created custom `PushErrorWithData` class to properly pass error data
- Updated signature to pass `errorData` to `onError` callback
7. **Updated component error handling** in `frontend/src/hooks/useGitOperations.ts:47-52`
- Added handling for `force_push_required` error type
- Displays user-friendly message: "Force push required. The remote branch has diverged."
All checks pass successfully! The implementation is ready for future force push functionality.
Cleanup script changes for task attempt 982f21cc-f0a3-455d-8b30-3a9911c2889f
Excellent! All tasks completed successfully. Here's a summary of the force push implementation:
I've successfully implemented a complete force push feature with user confirmation. Here's what was done:
1. **Updated Git CLI** (`crates/services/src/services/git/cli.rs:318`)
- Added `force: bool` parameter to `push()` method
- Uses `+refs/heads/{branch}` refspec when force is true
2. **Updated Git Service** (`crates/services/src/services/git.rs:1615`)
- Added `force: bool` parameter to `push_to_github()` method
- Passes force flag to Git CLI
3. **Added Force Push Endpoint** (`crates/server/src/routes/task_attempts.rs:608`)
- New handler: `force_push_task_attempt_branch`
- Calls `push_to_github()` with `force: true`
- Regular push endpoint now passes `force: false`
4. **Added Route** (`crates/server/src/routes/task_attempts.rs:1581`)
- Route: `POST /api/task-attempts/:id/push/force`
5. **API Client** (`frontend/src/lib/api.ts:561`)
- Added `forcePush()` method
- Returns `Result<void, PushError>`
6. **Created useForcePush Hook** (`frontend/src/hooks/useForcePush.ts`)
- React Query mutation for force push
- Handles typed errors
- Invalidates branch status on success
7. **Created ForcePushDialog** (`frontend/src/components/dialogs/git/ForcePushDialog.tsx`)
- Destructive variant with warning icon
- Clear warning about overwriting remote changes
- Buttons: "Cancel" and "Force Push"
8. **Integrated Dialog Flow** (`frontend/src/hooks/useGitOperations.ts:58-85`)
- When regular push fails with `force_push_required` error:
- Shows ForcePushDialog to confirm
- If user confirms, executes force push
- Handles errors from force push operation
1. User attempts to push
2. If remote has diverged, backend returns `force_push_required` error
3. Frontend shows confirmation dialog explaining the consequences
4. User can cancel or confirm force push
5. If confirmed, force push is executed
6. Success/error feedback is shown
All checks pass successfully! The feature is ready to use.
Cleanup script changes for task attempt 982f21cc-f0a3-455d-8b30-3a9911c2889f
Perfect! The fix is complete and all checks pass. Here's what was changed:
**Problem:** The `push_task_attempt_branch` endpoint was using the `?` operator which converted `GitServiceError::GitCLI(GitCliError::PushRejected(_))` into a generic `ApiError`, preventing the frontend from receiving the typed `PushError::ForcePushRequired` error.
**Solution:** Updated the endpoint in `crates/server/src/routes/task_attempts.rs:602-613` to use a `match` statement that:
1. Returns success on `Ok(_)`
2. Detects `GitServiceError::GitCLI(GitCliError::PushRejected(_))` and returns the typed error `ApiResponse::error_with_data(PushError::ForcePushRequired)`
3. Returns generic `ApiError::GitService(e)` for other errors
Now when a push is rejected due to non-fast-forward, the backend will return:
```json
{
"success": false,
"error_data": {
"type": "force_push_required"
}
}
```
This will trigger the force push confirmation dialog in the frontend, allowing the user to choose whether to force push or cancel.
Cleanup script changes for task attempt 982f21cc-f0a3-455d-8b30-3a9911c2889f
Perfect! The fix is complete and all checks pass. Here's what was changed:
**Problem:** The ForcePushDialog was not closing after the user clicked "Force Push" or "Cancel" because it only called `modal.resolve()` without calling `modal.hide()`.
**Solution:** Added `modal.hide()` calls to both handlers in `frontend/src/components/dialogs/git/ForcePushDialog.tsx`:
- **Line 24:** Added `modal.hide()` after `modal.resolve('confirmed')` in `handleConfirm`
- **Line 29:** Added `modal.hide()` after `modal.resolve('canceled')` in `handleCancel`
Now the dialog will properly close when the user clicks either button. This follows the correct NiceModal pattern where you need both:
1. `modal.resolve()` - to resolve the promise with a result
2. `modal.hide()` - to actually hide the dialog
The force push feature should now work end-to-end: push rejection → confirmation dialog → force push → dialog closes.
Perfect! All checks pass. Here's what was fixed:
The force push dialog now follows the same pattern as all other async dialogs in the codebase.
**Added:**
- `attemptId` prop (required) to identify which task attempt to force push
- `useForcePush` hook usage internally
- Loading state with `forcePush.isPending`
- Error state displayed in the dialog
- Loader spinner and "Force Pushing..." button text during operation
- Disabled buttons during operation
- Dialog stays open until operation completes
**Behavior:**
- User clicks "Force Push" → button shows spinner and "Force Pushing..."
- On success → dialog closes automatically
- On error → error shown in dialog, stays open, user can retry or cancel
**Changed:**
- Removed the manual force push call after dialog confirmation
- Now passes `attemptId` to the dialog: `ForcePushDialog.show({ attemptId })`
- Dialog handles the entire force push operation internally
1. User attempts push
2. Push rejected with `force_push_required` error
3. Dialog appears with warning
4. User clicks "Force Push"
5. **Button shows spinner and "Force Pushing..."** ← New!
6. **Buttons disabled during operation** ← New!
7. On success: dialog closes
8. On error: error displayed in dialog, user can retry
This matches the pattern used by CreatePRDialog, GhCliSetupDialog, and other async dialogs in the codebase.
* Force push i18n (vibe-kanban 5519a7db)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to vk/607c-add-pre-flight-c
Force push i18n (vibe-kanban 5519a7db)
Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to vk/607c-add-pre-flight-c
* fix tests
|
||
|
Alex Netsch
|
1ef162416d |
Add pre-flight check for target branch existence before PR creation (vibe-kanban) (#1341)
* Excellent! I've successfully implemented the pre-flight check for target branch existence before PR creation. Here's what I did: ## Summary I've added a pre-flight check that verifies the target branch exists on the remote before attempting to create a pull request. This provides a clear, early error message instead of failing during the GitHub API call. ### Changes Made 1. **Added `fetch_and_check_branch_exists()` method** in `crates/services/src/services/git.rs:1414-1446`: - Fetches from the remote to update tracking refs - Checks if the target branch exists (both local and remote branches) - Uses best-effort fetching (doesn't fail if fetch fails) - Returns `Ok(true)` if branch exists, `Ok(false)` if not 2. **Added pre-flight check** in `crates/server/src/routes/task_attempts.rs:639-667`: - Placed before pushing the branch to GitHub - Fetches and verifies the target branch exists - Returns a clear error message if the branch doesn't exist - Continues with PR creation even if the check fails (fallback to GitHub API error) - Includes logging for debugging ### Key Features - **Fail-fast approach**: Catches missing target branch before wasting time on the GitHub API call - **Clear error messages**: Users get an actionable error message: "Target branch 'X' does not exist on remote. Please ensure the branch exists before creating a pull request." - **Graceful degradation**: If the fetch/check fails for any reason, the code continues and lets the GitHub API handle the error (existing fallback behavior) - **Works with all git remotes**: Not GitHub-specific, uses git fetch - **Performance trade-off**: Adds 1-3 seconds for the fetch operation, but provides better UX ### Testing All checks passed: - ✅ Rust compilation (cargo clippy) - ✅ TypeScript type generation (npm run generate-types:check) The implementation follows the "Option A - Fetch-then-check" approach from the task description, providing early detection of missing target branches while maintaining backward compatibility with the existing error handling. * Cleanup script changes for task attempt 607cef96-2669-46e6-bee9-fd2d524be0bd * Perfect! All the review comments have been addressed: ## Changes Made 1. **Simplified `fetch_and_check_branch_exists()` in git.rs** - Now uses the existing `Self::find_branch()` helper method instead of manually calling `repo.find_branch()` twice, making the code cleaner and more consistent with the rest of the codebase. 2. **Removed all comments** from both files - The code is now self-explanatory without the verbose comments. 3. **Removed all logging** from task_attempts.rs - No more `tracing::info!`, `tracing::warn!`, or `tracing::error!` calls for the pre-flight check. 4. **Simplified control flow** - Changed from a match statement to a cleaner if-let pattern as suggested by clippy. The implementation is now more concise while maintaining the same functionality: - Fetches from remote and checks if the target branch exists - Returns a clear error if the branch doesn't exist - Silently continues on success or fetch errors (letting GitHub API handle any remaining issues) All compilation checks pass successfully. * Perfect! All checks pass. Let me create a summary of the changes: I've successfully added a typed error for the missing target branch case. Here's what was changed: 1. **Added `TargetBranchNotFound` variant to `GitHubServiceError`** in `crates/services/src/services/github.rs:38-40`: - Takes a `String` parameter for the branch name - Includes a clear error message - Marked with `#[ts(skip)]` since it has a parameter 2. **Updated `is_api_data()` method** in `crates/services/src/services/github.rs:93`: - Added `GitHubServiceError::TargetBranchNotFound(_)` to the match pattern - This ensures the error is properly typed and won't be retried 3. **Updated `create_github_pr()`** in `crates/server/src/routes/task_attempts.rs:643-645`: - Replaced the string error message with `GitHubServiceError::TargetBranchNotFound(target_branch.clone())` - Now uses `ApiResponse::error_with_data()` instead of `ApiResponse::error()`, consistent with other typed errors in the function - **Type-safe error handling**: Frontend can now properly discriminate this error type - **Consistent with existing patterns**: Follows the same pattern as `TokenInvalid`, `InsufficientPermissions`, etc. - **Better API design**: The error is now part of the function's return type signature All compilation and type generation checks pass successfully! * Great! All checks pass. Let me create a summary: I've successfully added frontend error handling for the `target_branch_not_found` error. Here's what was done: 1. **Added translation key** in `frontend/src/i18n/locales/en/tasks.json:345`: - Key: `createPrDialog.errors.targetBranchNotFound` - Message: `"Target branch '{{branch}}' does not exist on remote. Please ensure the branch exists before creating a pull request."` - Uses interpolation to inject the branch name dynamically 2. **Added error handler** in `frontend/src/components/dialogs/tasks/CreatePRDialog.tsx:187-195`: - Checks if `result.error.type === 'target_branch_not_found'` - Extracts the `branch` field from the error object - Displays localized error message with the branch name interpolated - Clears the GH CLI helper UI state When a user tries to create a PR with a non-existent target branch: 1. **Backend pre-flight check** fetches from remote and checks if the target branch exists 2. **If branch doesn't exist**: Returns `CreatePrError::TargetBranchNotFound { branch: "xyz" }` 3. **Frontend receives** typed error with discriminant `type: "target_branch_not_found"` and `branch: "xyz"` 4. **Dialog displays**: "Target branch 'xyz' does not exist on remote. Please ensure the branch exists before creating a pull request." All checks pass (TypeScript compilation, linting, type generation). * Excellent! All checks pass. Here's the summary: I've successfully added the `targetBranchNotFound` translation key to all 3 missing locale files: 1. **Spanish (es)** - `frontend/src/i18n/locales/es/tasks.json:121`: - `"La rama objetivo '{{branch}}' no existe en el remoto. Por favor, asegúrese de que la rama exista antes de crear una solicitud de extracción."` 2. **Japanese (ja)** - `frontend/src/i18n/locales/ja/tasks.json:121`: - `"ターゲットブランチ '{{branch}}' がリモートに存在しません。プルリクエストを作成する前にブランチが存在することを確認してください。"` 3. **Korean (ko)** - `frontend/src/i18n/locales/ko/tasks.json:121`: - `"대상 브랜치 '{{branch}}'이(가) 원격에 존재하지 않습니다. 풀 리퀘스트를 생성하기 전에 브랜치가 존재하는지 확인하세요."` All translations follow the same pattern with the `{{branch}}` interpolation parameter and maintain consistency with the existing error messages in each locale. All checks pass (TypeScript compilation, frontend and backend checks)! Fix i18n * Perfect! All checks pass. Here's the complete summary: ## Summary I've successfully fixed the branch name format handling issue in `check_remote_branch_exists()`. ### The Problem The method only tried the exact branch name provided (e.g., "main"), but git2's `find_branch()` with `BranchType::Remote` requires the full remote branch name (e.g., "origin/main"). This meant: - ❌ User provides "main" → check fails (should succeed if origin/main exists) - ✅ User provides "origin/main" → check succeeds ### The Fix Updated `check_remote_branch_exists()` in `crates/services/src/services/git.rs:1414-1428` to try both formats: 1. **First attempt**: Try the branch name as-is (handles "origin/main" format) 2. **Fallback**: Prepend default remote name (handles "main" format → "origin/main") This follows the same pattern used by `find_branch()`, `find_branch_type()`, and `check_branch_exists()` throughout the codebase. ### Complete Implementation The full pre-flight check implementation now includes: **Backend:** - ✅ Fetches from remote to get latest refs - ✅ Checks if target branch exists (handles both "main" and "origin/main" formats) - ✅ Returns typed error `CreatePrError::TargetBranchNotFound { branch }` - ✅ Handles auth errors during fetch → `CreatePrError::GitCliNotLoggedIn` - ✅ Handles missing git CLI → `CreatePrError::GitCliNotInstalled` **Frontend:** - ✅ Handles `target_branch_not_found` error type in CreatePRDialog - ✅ Displays localized error message with branch name - ✅ Translations added for all 4 locales (en, es, ja, ko) All checks pass! * Lint * Change pre-flight check for create PR (vibe-kanban 4f79fbc8) to use git ls-remote --branches to check for remote branche existence instead of libgit2. To do this add an appropriate method to crates/services/src/services/git/cli.rs and modify the preflight check. * Perfect! All checks pass. The implementation is now complete: ## Complete Implementation Summary ### What Was Built A pre-flight check for PR creation that verifies the target branch exists on the remote before attempting to create the pull request. ### Key Changes **Backend:** 1. **`check_remote_branch_exists()`** in `git.rs:1414-1428` - Checks if a branch exists remotely, handles both "main" and "origin/main" formats 2. **`fetch_and_check_branch_exists()`** in `git.rs:1430-1439` - Fetches from remote then checks existence, propagates errors 3. **`CreatePrError::TargetBranchNotFound`** in `task_attempts.rs:616` - New typed error variant with branch name 4. **Pre-flight check** in `create_github_pr()` in `task_attempts.rs:639-662` - Validates target branch exists, handles auth errors **Frontend:** 1. **Error handler** in `CreatePRDialog.tsx:187-195` - Displays localized error message 2. **Translations** in all 4 locales (en, es, ja, ko) - Localized error messages with branch name interpolation ### What Works - ✅ Detects missing target branches before push/PR creation - ✅ Handles "main" and "origin/main" branch name formats - ✅ Fails fast on auth errors during fetch - ✅ Returns typed errors the frontend can handle - ✅ Displays clear, localized error messages with the branch name - ✅ All checks pass (Rust clippy, TypeScript, type generation) |
||
|
Solomon
|
37f8f3c74f |
Gemini fixes (#1349)
* Fix gemini yolo * limit diff unchanged lines context to 3 lines * fix shell command parsing * remove the GeminiModel struct |
||
|
Alex Netsch
|
1933bb463c |
Decouple git from github errors (#1347)
* Decouple git from github errors
* Fix git error display (vibe-kanban 7352dadc)
After the last few commits git cli not logged in error does not get displayed to the user. Network tab shows this:
{
"success": false,
"data": null,
"error_data": {
"type": "git_cli_not_logged_in"
},
"message": null
}
|
||
|
Solomon
|
83602590e9 |
Droid agent (#1318)
* droid research (vibe-kanban 054135e9)
<droid-docs>
# Overview
> Non-interactive execution mode for CI/CD pipelines and automation scripts.
# Droid Exec (Headless CLI)
Droid Exec is Factory's headless execution mode designed for automation workflows. Unlike the interactive CLI, `droid exec` runs as a one-shot command that completes a task and exits, making it ideal for CI/CD pipelines, shell scripts, and batch processing.
## Summary and goals
Droid Exec is a one-shot task runner designed to:
* Produce readable logs, and structured artifacts when requested
* Enforce opt-in for mutations/command execution (secure-by-default)
* Fail fast on permission violations with clear errors
* Support simple composition for batch and parallel work
<CardGroup cols={2}>
<Card title="Non-Interactive" icon="terminal">
Single run execution that writes to stdout/stderr for CI/CD integration
</Card>
<Card title="Secure by Default" icon="lock">
Read-only by default with explicit opt-in for mutations via autonomy levels
</Card>
<Card title="Composable" icon="puzzle">
Designed for shell scripting, parallel execution, and pipeline integration
</Card>
<Card title="Clean Output" icon="file-export">
Structured output formats and artifacts for automated processing
</Card>
</CardGroup>
## Execution model
* Non-interactive single run that writes to stdout/stderr.
* Default is spec-mode: the agent is only allowed to execute read-only operations.
* Add `--auto` to enable edits and commands; risk tiers gate what can run.
CLI help (excerpt):
```
Usage: droid exec [options] [prompt]
Execute a single command (non-interactive mode)
Arguments:
prompt The prompt to execute
Options:
-o, --output-format <format> Output format (default: "text")
-f, --file <path> Read prompt from file
--auto <level> Autonomy level: low|medium|high
--skip-permissions-unsafe Skip ALL permission checks (unsafe)
-s, --session-id <id> Existing session to continue (requires a prompt)
-m, --model <id> Model ID to use
-r, --reasoning-effort <level> Reasoning effort: off|low|medium|high
--cwd <path> Working directory path
-h, --help display help for command
```
Supported models (examples):
* gpt-5-codex (default)
* gpt-5-2025-08-07
* claude-sonnet-4-20250514
* claude-opus-4-1-20250805
## Installation
<Steps>
<Step title="Install Droid CLI">
<CodeGroup>
```bash macOS/Linux theme={null}
curl -fsSL https://app.factory.ai/cli | sh
```
```powershell Windows theme={null}
irm https://app.factory.ai/cli/windows | iex
```
</CodeGroup>
</Step>
<Step title="Get Factory API Key">
Generate your API key from the [Factory Settings Page](https://app.factory.ai/settings/api-keys)
</Step>
<Step title="Set Environment Variable">
Export your API key as an environment variable:
```bash theme={null}
export FACTORY_API_KEY=fk-...
```
</Step>
</Steps>
## Quickstart
* Direct prompt:
* `droid exec "analyze code quality"`
* `droid exec "fix the bug in src/main.js" --auto low`
* From file:
* `droid exec -f prompt.md`
* Pipe:
* `echo "summarize repo structure" | droid exec`
* Session continuation:
* `droid exec --session-id <session-id> "continue with next steps"`
## Autonomy Levels
Droid exec uses a tiered autonomy system to control what operations the agent can perform. By default, it runs in read-only mode, requiring explicit flags to enable modifications.
### DEFAULT (no flags) - Read-only Mode
The safest mode for reviewing planned changes without execution:
* ✅ Reading files or logs: cat, less, head, tail, systemctl status
* ✅ Display commands: echo, pwd
* ✅ Information gathering: whoami, date, uname, ps, top
* ✅ Git read operations: git status, git log, git diff
* ✅ Directory listing: ls, find (without -delete or -exec)
* ❌ No modifications to files or system
* **Use case:** Safe for reviewing what changes would be made
```bash theme={null}
# Analyze and plan refactoring without making changes
droid exec "Analyze the authentication system and create a detailed plan for migrating from session-based auth to OAuth2. List all files that would need changes and describe the modifications required."
# Review code quality and generate report
droid exec "Review the codebase for security vulnerabilities, performance issues, and code smells. Generate a prioritized list of improvements needed."
# Understand project structure
droid exec "Analyze the project architecture and create a dependency graph showing how modules interact with each other."
```
### `--auto low` - Low-risk Operations
Enables basic file operations while blocking system changes:
* ✅ File creation/editing in project directories
* ❌ No system modifications or package installations
* **Use case:** Documentation updates, code formatting, adding comments
```bash theme={null}
# Safe file operations
droid exec --auto low "add JSDoc comments to all functions"
droid exec --auto low "fix typos in README.md"
```
### `--auto medium` - Development Operations
Operations that may have significant side effects, but these side effects are typically harmless and straightforward to recover from.
Adds common development tasks to low-risk operations:
* Installing packages from trusted sources: npm install, pip install (without sudo)
* Network requests to trusted endpoints: curl, wget to known APIs
* Git operations that modify local repositories: git commit, git checkout, git pull (but not git push)
* Building code with tools like make, npm run build, mvn compile
* ❌ No git push, sudo commands, or production changes
* **Use case:** Local development, testing, dependency management
```bash theme={null}
# Development tasks
droid exec --auto medium "install deps, run tests, fix issues"
droid exec --auto medium "update packages and resolve conflicts"
```
### `--auto high` - Production Operations
Commands that may have security implications such as data transfers between untrusted sources or execution of unknown code, or major side effects such as irreversible data loss or modifications of production systems/deployments.
* Running arbitrary/untrusted code: curl | bash, eval, executing downloaded scripts
* Exposing ports or modifying firewall rules that could allow external access
* Git push operations that modify remote repositories: git push, git push --force
* Irreversible actions to production deployments, database migrations, or other sensitive operations
* Commands that access or modify sensitive information like passwords or keys
* ❌ Still blocks: sudo rm -rf /, system-wide changes
* **Use case:** CI/CD pipelines, automated deployments
```bash theme={null}
# Full workflow automation
droid exec --auto high "fix bug, test, commit, and push to main"
droid exec --auto high "deploy to staging after running tests"
```
### `--skip-permissions-unsafe` - Bypass All Checks
<Warning>
DANGEROUS: This mode allows ALL operations without confirmation. Only use in completely isolated environments like Docker containers or throwaway VMs.
</Warning>
* ⚠️ Allows ALL operations without confirmation
* ⚠️ Can execute irreversible operations
* Cannot be combined with --auto flags
* **Use case:** Isolated environments
```bash theme={null}
# In a disposable Docker container for CI testing
docker run --rm -v $(pwd):/workspace alpine:latest sh -c "
apk add curl bash &&
curl -fsSL https://app.factory.ai/cli | sh &&
droid exec --skip-permissions-unsafe 'Install all system dependencies, modify system configs, run integration tests that require root access, and clean up test databases'
"
# In ephemeral GitHub Actions runner for rapid iteration
# where the runner is destroyed after each job
droid exec --skip-permissions-unsafe "Modify /etc/hosts for test domains, install custom kernel modules, run privileged container tests, and reset network interfaces"
# In a temporary VM for security testing
droid exec --skip-permissions-unsafe "Run penetration testing tools, modify firewall rules, test privilege escalation scenarios, and generate security audit reports"
```
### Fail-fast Behavior
If a requested action exceeds the current autonomy level, droid exec will:
1. Stop immediately with a clear error message
2. Return a non-zero exit code
3. Not perform any partial changes
This ensures predictable behavior in automation scripts and CI/CD pipelines.
## Output formats and artifacts
Droid exec supports three output formats for different use cases:
### text (default)
Human-readable output for direct consumption or logs:
```bash theme={null}
$ droid exec --auto low "create a python file that prints 'hello world'"
Perfect! I've created a Python file named `hello_world.py` in your home directory that prints 'hello world' when executed.
```
### json
Structured JSON output for parsing in scripts and automation:
```bash theme={null}
$ droid exec "summarize this repository" --output-format json
{
"type": "result",
"subtype": "success",
"is_error": false,
"duration_ms": 5657,
"num_turns": 1,
"result": "This is a Factory documentation repository containing guides for CLI tools, web platform features, and onboarding procedures...",
"session_id": "8af22e0a-d222-42c6-8c7e-7a059e391b0b"
}
```
Use JSON format when you need to:
* Parse the result in a script
* Check success/failure programmatically
* Extract session IDs for continuation
* Process results in a pipeline
### debug
Streaming messages showing the agent's execution in real-time:
```bash theme={null}
$ droid exec "run ls command" --output-format debug
{"type":"message","role":"user","text":"run ls command"}
{"type":"message","role":"assistant","text":"I'll run the ls command to list the contents..."}
{"type":"tool_call","toolName":"Execute","parameters":{"command":"ls -la"}}
{"type":"tool_result","value":"total 16\ndrwxr-xr-x@ 8 user staff..."}
{"type":"message","role":"assistant","text":"The ls command has been executed successfully..."}
```
Debug format is useful for:
* Monitoring agent behavior
* Troubleshooting execution issues
* Understanding tool usage patterns
* Real-time progress tracking
For automated pipelines, you can also direct the agent to write specific artifacts:
```bash theme={null}
droid exec --auto low "Analyze dependencies and write to deps.json"
droid exec --auto low "Generate metrics report in CSV format to metrics.csv"
```
## Working directory
* Use `--cwd` to scope execution:
```
droid exec --cwd /home/runner/work/repo "Map internal packages and dump graphviz DOT to deps.dot"
```
## Models and reasoning effort
* Choose a model with `-m` and adjust reasoning with `-r`:
```
droid exec -m claude-sonnet-4-20250514 -r medium -f plan.md
```
## Batch and parallel patterns
Shell loops (bounded concurrency):
```bash theme={null}
# Process files in parallel (GNU xargs -P)
find src -name "*.ts" -print0 | xargs -0 -P 4 -I {} \
droid exec --auto low "Refactor file: {} to use modern TS patterns"
```
Background job parallelization:
```bash theme={null}
# Process multiple directories in parallel with job control
for path in packages/ui packages/models apps/factory-app; do
(
cd "$path" &&
droid exec --auto low "Run targeted analysis and write report.md"
) &
done
wait # Wait for all background jobs to complete
```
Chunked inputs:
```bash theme={null}
# Split large file lists into manageable chunks
git diff --name-only origin/main...HEAD | split -l 50 - /tmp/files_
for f in /tmp/files_*; do
list=$(tr '\n' ' ' < "$f")
droid exec --auto low "Review changed files: $list and write to review.json"
done
rm /tmp/files_* # Clean up temporary files
```
Workflow Automation (CI/CD):
```yaml theme={null}
# Dead code detection and cleanup suggestions
name: Code Cleanup Analysis
on:
schedule:
- cron: '0 1 * * 0' # Weekly on Sundays
workflow_dispatch:
jobs:
cleanup-analysis:
strategy:
matrix:
module: ['src/components', 'src/services', 'src/utils', 'src/hooks']
steps:
- uses: actions/checkout@v4
- run: droid exec --cwd "${{ matrix.module }}" --auto low "Identify unused exports, dead code, and deprecated patterns. Generate cleanup recommendations in cleanup-report.md"
```
## Unique usage examples
License header enforcer:
```bash theme={null}
git ls-files "*.ts" | xargs -I {} \
droid exec --auto low "Ensure {} begins with the Apache-2.0 header; add it if missing"
```
API contract drift check (read-only):
```bash theme={null}
droid exec "Compare openapi.yaml operations to our TypeScript client methods and write drift.md with any mismatches"
```
Security sweep:
```bash theme={null}
droid exec --auto low "Run a quick audit for sync child_process usage and propose fixes; write findings to sec-audit.csv"
```
## Exit behavior
* 0: success
* Non-zero: failure (permission violation, tool error, unmet objective). Treat non-zero as failed in CI.
## Best practices
* Favor `--auto low`; keep mutations minimal and commit/push in scripted steps.
* Avoid `--skip-permissions-unsafe` unless fully sandboxed.
* Ask the agent to emit artifacts your pipeline can verify.
* Use `--cwd` to constrain scope in monorepos.
</droid-docs>
Use the oracle to research how we support custom executors.
AMP and Claude Code would likely be good references here as I believe that they both operate via JSON.
Save your findings in a single markdown file.
* begin droid
* add plan
* droid implementation (vibe-kanban 90e6c8f6)
Read tasks/droid-agent/plan.md and execute the plan.
* document droid (vibe-kanban 0a7f8590)
we have introduced a new coding agent
Installation instructions are at https://factory.ai/product/cli
We expect that users have the `droid` cli installed and that they have logged in.
docs/supported-coding-agents.mdx
There may also be other docs or references.
* red gh action (vibe-kanban f0c8b6c4)
Run cargo fmt --all -- --check
cargo fmt --all -- --check
npm run generate-types:check
cargo test --workspace
cargo clippy --all --all-targets -- -D warnings
the checks step is failing, can you see what's up with the rust codebase and resolve it?
* droid | settings bug (vibe-kanban 7deec8df)
We have a new coding agent called Droid and it has a variety of different settings including the autonomy level and we default this to medium and users can update this by going to settings and then using the drop down to change it and then hitting the save button. And this works, however, when users return back to settings the displayed autonomy level is reset to medium rather than the correct level. So can you investigate why this is happening and plan how we can improve it, how we can verify it, do we need to introduce some logging, other things to consider. Write up your plan in a new markdown file.
* glob
* tool call parsing & display (vibe-kanban e3f65a74)
droid.rs has `fn map_tool_to_action`
The problem is that we're doing a poor job at displaying these tool calls e.g. glob. In `claude.rs`, we use `ClaudeToolData`, a struct that matches the real JSON data. Once we do that, we have a type safe way to map tool calls to the `ActionType` struct.
You can run `droid exec --output-format=stream-json --auto medium "YOUR MESSAGE MERE"` in a temporary directory to instruct the agent to generate custom outputs in case you need more sample data.
I just added glob.jsonl under droid-json, there are other json files in there too.
I recommend using sub agents as some of these files (e.g. claude.rs) are large.
cursor.rs might also be a useful reference.
You're done once we properly handle these tools.
* show droid model (vibe-kanban 8fdbc630)
The first JSON object emitted from the droid executor is a system message with a `model` field. We should capture and display this.
I believe that we're already doing something similar with Codex.
Here's a sample system message:
{"type":"system","subtype":"init","cwd":"/Users/britannio/projects/vibe-kanban","session_id":"59a75629-c0c4-451f-a3c7-8e9eab05484a","tools":["Read","LS","Execute","Edit","MultiEdit","ApplyPatch","Grep","Glob","Create","ExitSpecMode","WebSearch","TodoWrite","FetchUrl","slack_post_message"],"model":"gpt-5-codex"}
* reliable apply patch display (vibe-kanban 3710fb65)
The crates/executors/src/executors/droid.rs ApplyPatch tool call contains an `input` string which isn't very helpful, but the tool call result is a JSON object with a `value` object with the fields success, content, diff, and file_path.
Here's a parsed example of `value`:
{
"success": true,
"content": "def bubble_sort(arr):\n \"\"\"\n Bubble Sort Algorithm\n Time Complexity: O(n^2)\n Space Complexity: O(1)\n\n Repeatedly steps through the list, compares adjacent elements and swaps them\n if they are in the wrong order.\n \"\"\"\n n = len(arr)\n arr = arr.copy() # Create a copy to avoid modifying the original\n\n for i in range(n):\n # Flag to optimize by stopping if no swaps occur\n swapped = False\n\n for j in range(0, n - i - 1):\n if arr[j] > arr[j + 1]:\n arr[j], arr[j + 1] = arr[j + 1], arr[j]\n swapped = True\n\n # If no swaps occurred, array is already sorted\n if not swapped:\n break\n\n return arr\n\n\ndef insertion_sort(arr):\n \"\"\"\n Insertion Sort Algorithm\n Time Complexity: O(n^2)\n Space Complexity: O(1)\n\n Builds the sorted portion of the array one element at a time by inserting\n each element into its correct position.\n \"\"\"\n arr = arr.copy() # Create a copy to avoid modifying the original\n\n for i in range(1, len(arr)):\n key = arr[i]\n j = i - 1\n\n while j >= 0 and arr[j] > key:\n arr[j + 1] = arr[j]\n j -= 1\n\n arr[j + 1] = key\n\n return arr\n\n\nif __name__ == \"__main__\":\n # Example usage\n test_array = [64, 34, 25, 12, 22, 11, 90]\n\n print(\"Original array:\", test_array)\n print(\"\\nBubble Sort result:\", bubble_sort(test_array))\n print(\"Insertion Sort result:\", insertion_sort(test_array))\n\n # Test with different arrays\n print(\"\\n--- Additional Tests ---\")\n test_cases = {\n \"Reverse sorted\": [5, 4, 3, 2, 1],\n \"Empty array\": [],\n \"Already sorted\": [1, 2, 3, 4, 5],\n }\n\n for description, case in test_cases.items():\n print(f\"{description} (Bubble):\", bubble_sort(case))\n print(f\"{description} (Insertion):\", insertion_sort(case))\n",
"diff": "--- previous\t\n+++ current\t\n@@ -26,14 +26,46 @@\n return arr\n \n \n+def insertion_sort(arr):\n+ \"\"\"\n+ Insertion Sort Algorithm\n+ Time Complexity: O(n^2)\n+ Space Complexity: O(1)\n+\n+ Builds the sorted portion of the array one element at a time by inserting\n+ each element into its correct position.\n+ \"\"\"\n+ arr = arr.copy() # Create a copy to avoid modifying the original\n+\n+ for i in range(1, len(arr)):\n+ key = arr[i]\n+ j = i - 1\n+\n+ while j >= 0 and arr[j] > key:\n+ arr[j + 1] = arr[j]\n+ j -= 1\n+\n+ arr[j + 1] = key\n+\n+ return arr\n+\n+\n if __name__ == \"__main__\":\n # Example usage\n test_array = [64, 34, 25, 12, 22, 11, 90]\n \n print(\"Original array:\", test_array)\n print(\"\\nBubble Sort result:\", bubble_sort(test_array))\n+ print(\"Insertion Sort result:\", insertion_sort(test_array))\n \n # Test with different arrays\n print(\"\\n--- Additional Tests ---\")\n- print(\"Reverse sorted:\", bubble_sort([5, 4, 3, 2, 1]))\n- print(\"Empty array:\", bubble_sort([]))\n+ test_cases = {\n+ \"Reverse sorted\": [5, 4, 3, 2, 1],\n+ \"Empty array\": [],\n+ \"Already sorted\": [1, 2, 3, 4, 5],\n+ }\n+\n+ for description, case in test_cases.items():\n+ print(f\"{description} (Bubble):\", bubble_sort(case))\n+ print(f\"{description} (Insertion):\", insertion_sort(case))",
"file_path": "/Users/britannio/projects/droid-simple/sorting_algorithms.py"
}
This formatting should be deterministic and thus we can use it to show more informative tool call data.
The first thing to understand is if this will naturally fit with the current architecture, as we only reliably know how the file has changed (and what the target file was) after receiving the tool call result.
* droid failed tool call handling (vibe-kanban bd7feddb)
crates/executors/src/executors/droid.rs
droid-json/insufficient-perms.jsonl
the insufficient-perms file contains the JSON output log of a run where it runs a command to create a file but the tool call fails due to a permission error.
I'd expect that the failed tool result would be correlated with the tool call and thus i'd see an ARGS block and a RESULTS block within the tool call on the front-end.
Instead, I see the tool call only with the ARGS block, then I see a separate UI element with the JSON tool result as if it failed to be correlated.
Firstly, I want to follow TDD by creating a failing test that confirms this behaviour. It might be hard though because we haven't designed the code in droid.rs with testability in mind.
Lets first analyse the code to consider if it's already testable or if we need to do any refactoring & introduce harnesses etc.
My perspective of the coding agent is that we send it a command, and it streams JSON objects one by one so some form of reducer pattern seems natural (previous list of json objects + previous state + new json object => new state). Either 'new state' or 'new delta'.
When we resume a session, it will emit a system message object, then a message object with role user (repeating what we sent it), then the new actions that it takes.
* droid default (vibe-kanban 2f8a19cc)
the default autonomy level is currently medium. Lets change it to the highest (unsafe)
* droid globbing rendering (vibe-kanban 76d372ea)
See droid-json/glob.jsonl
Notice the `patterns` field. Unfortunately, we seems to not be using this data as glob tool calls are being rendered exclusively via a file name of some sort rather than `Globbing README.md, readme.md,docs/**,*.md`
Use the oracle to investigate this.
* droid todo list text (vibe-kanban b1bdeffc)
Use the text 'TODO list updated' for the droid agent when it makes a change to the todo list.
* droid workspace path (vibe-kanban 0486b74a)
See how claude.rs uses worktree_path (from normalize_logs).
We should be doing the same for the droid executor so that the tool calls we generate have relative paths.
* mcp settings (vibe-kanban 2031d8f4)
Quick fix: Filter that agent from the dropdown in the frontend.
// In McpSettings.tsx, line 282-289
<SelectContent>
{profiles &&
Object.entries(profiles)
.filter(([key]) => key !== 'DROID') // or whatever the agent name is
.sort((a, b) => a[0].localeCompare(b[0]))
.map(([profileKey]) => (
<SelectItem key={profileKey} value={profileKey}>
{profileKey}
</SelectItem>
))}
</SelectContent>
we need to temporarily hide droid as it doesn't support mcp yet.
* clean up (vibe-kanban 6b1a8e2e)
remove all references to 'britannio' from the droid module.
* delete droid json
* droid agent code review (vibe-kanban 6820ffd1)
We added Droid to crates/services/src/services/config/versions/v1.rs but presumably we should've used the latest reasonable version. See what we used for Copilot.
Delete docs/adr-droid-architecture.md
Delete docs/droid-improvements-summary.md
docs/supported-coding-agents.mdx the default was medium, it's now skip-permissions-unsafe
Delete the tasks/ folder
* remove unnecessary v1 change
* updated droid.json schema
* tweak command
* droid model suggestions (vibe-kanban 120f87d2)
crates/executors/src/executors/droid/types.rs
Valid model IDs are:
gpt-5-codex OpenAI GPT-5-Codex (Auto)
claude-sonnet-4-5-20250929 Claude Sonnet 4.5
gpt-5-2025-08-07 OpenAI GPT-5
claude-opus-4-1-20250805 Claude Opus 4.1
claude-haiku-4-5-20251001 Claude Haiku 4.5
glm-4.6 Droid Core (GLM-4.6)
We currently mention gpt-5-codex, claude-sonnet-4
* remove dead code
* droid automated testing (vibe-kanban f836b4a4)
lets start brainstorming this, starting with tests in crates/executors/src/executors/droid/types.rs to ensure that we correctly generate a command
* create exec_command_with_prompt
* Add logging to error paths in action_mapper.rs (vibe-kanban 76cc5d71)
Add tracing logging (warn/error) to error paths in `crates/executors/src/executors/droid/action_mapper.rs` following existing logging patterns in the codebase.
Key locations:
- Line 32-35: DroidToolData parsing failure (currently silent)
- Any other error paths that swallow errors
Use `tracing::warn!` with structured fields for context (tool_name, error details, etc.)
* droid automated testing (DroidJSON -> NormalizedEntry) (vibe-kanban cf325d24)
We have example agent from /Users/britannio/Downloads/droid-json
Read crates/executors/src/executors/droid/events.rs
Use the oracle to plan tests that we could introduce.
* preserve timestamp
* droid reasoning effort (vibe-kanban 47dae2db)
in settings, we're showing a dropdown for the droid autonomy level. We should be doing the same for the reasoning level. It should default to being empty if possible.
* droid path (vibe-kanban d8370535)
Droid file edits (presumably ApplyPatch?) aren't using relative paths. E.g. i'm seeing `/private/var/folders/5q/5vgq75y92dz0k7n62z93299r0000gn/T/vibe-kanban-dev/worktrees/11dc-setup/next.config.mjs`
* fix warning
* fix warning
* whitespace update
* DomainEvent -> LogEvent
* remove msg store stream -> line converter
* normalise the diff generated when the droid ApplyPatch tool call is
parsed
* refactor process_event to mutate a reference to ProcessorState
* remove EntryIndexProvider abstraction
* remove dead code
* remove JSON indirection when invoking extract_path_from_patch
* converting DroidJson -> LogEvent produces Option instead of Vec
DroidJson mapping tests removed in favour of snapshot testing delete
emit_patches (now redundant) update match syntax in
compute_updated_action_type make process_event a member of
ProcessorState
* simplify droid build_command_builder
* simplify droid types tests
* remove droid type tests
* rename events.rs -> log_event_converter.rs
rename patch_emitter -> patch_converter
remove ParsedLine indirection from processor.rs
handle Edit, MultiEdit, and Create tool calls (only used by some models like claude)
move action mapper logic to log_event_converter
introduce a claude snapshot
update snapshots
* add error log for failed parsing of DroidJson
* update snapshots
* Fix clippy warnings in droid executor
- Change &String to &str in extract_path_from_patch
- Rename to_patch to process_event for correct self convention
Amp-Thread-ID: https://ampcode.com/threads/T-81d4f5ac-6d3a-4da5-9799-de724f3df1e3
Co-authored-by: Amp <amp@ampcode.com>
* update cargo lock
* droid tool call result parsing (vibe-kanban 514d27de)
the droid executor has a regression where the `droid exec` command is no longer producing an `id` field for tool_result messages. Fortunately, in most cases, it's safe to stick to FIFO behaviour whereby if we get a tool result, we can match it with the earliest tool call. This won't always work but it's a reasonable solution for the next few days while the droid team fixes their executor.
Start by using the oracle to trace and understand the codepaths involved, and to make a plan. We likely need to update the DroidJson struct so that the tool call result id becomes optional.
To test this, we can take an existing snapshot test and create a variant of it without ids in the tool call results, and see if we still produce equivalent log events.
* refactor: collapse nested if statements in log_event_converter
Amp-Thread-ID: https://ampcode.com/threads/T-b9ad8aac-0fd5-44c5-b2f8-317d79b623a6
Co-authored-by: Amp <amp@ampcode.com>
* format
* Cleanup droid executor implementation
* Implement session forking
* linter
---------
Co-authored-by: Britannio Jarrett <britanniojarrett@gmail.com>
Co-authored-by: Test User <test@example.com>
Co-authored-by: Amp <amp@ampcode.com>
|
||
|
Solomon
|
84454b54a1 | JWT: separate access tokens and refresh tokens (#1315) | ||
|
Alex Netsch
|
f3d963c285 |
Add org events (vibe-kanban) (#1339)
* Excellent! All tests pass. Let me create a summary of the changes:
## Summary
I've successfully added analytics events for organization-related actions in the Vibe Kanban codebase. Here's what was implemented:
### Changes Made
**1. `crates/server/src/routes/organizations.rs`:**
- Added `Deployment` trait import
- **Organization Created** (`create_organization` at line 90-110):
- Event: `"organization_created"`
- Properties: `org_id`, `is_personal`
- **Invitation Created** (`create_invitation` at line 134-155):
- Event: `"invitation_created"`
- Properties: `invitation_id`, `org_id`, `role`
- ✅ No sensitive data (invitee email excluded)
**2. `crates/server/src/routes/projects.rs`:**
- **Project Linked to Remote** (`apply_remote_project_link` at line 168-197):
- Event: `"project_linked_to_remote"`
- Properties: `project_id`, `link_type` ("existing" or "new")
- Tracks both linking to existing projects and creating new remote projects
- Added `link_type` parameter to distinguish between the two use cases
### Implementation Details
- All events follow the existing PostHog analytics pattern using `deployment.track_if_analytics_allowed()`
- Events are tracked **after** successful operations, **before** returning responses
- UUIDs are converted to strings with `.to_string()`
- Event names use snake_case convention
- No sensitive data (like invitee emails) is tracked
- All code compiles successfully and passes existing tests ✅
* Excellent! I've successfully removed the `link_type` parameter. Here's the updated summary of the changes:
## Final Summary
I've successfully added analytics events for organization-related actions and addressed your feedback. Here's what was implemented:
### Changes Made
**1. `crates/server/src/routes/organizations.rs`:**
- Added `Deployment` trait import
- **Organization Created** (line 90-109):
- Event: `"organization_created"`
- Properties: `org_id`, `is_personal`
- **Invitation Created** (line 124-144):
- Event: `"invitation_created"`
- Properties: `invitation_id`, `org_id`, `role`
- ✅ No sensitive data (invitee email excluded)
**2. `crates/server/src/routes/projects.rs`:**
- **Project Linked to Remote** (line 168-195):
- Event: `"project_linked_to_remote"`
- Properties: `project_id` only
- Simplified analytics - removed `link_type` parameter per your feedback
### Implementation Details
- All events follow the existing PostHog analytics pattern using `deployment.track_if_analytics_allowed()`
- Events are tracked **after** successful operations, **before** returning responses
- UUIDs are converted to strings with `.to_string()`
- Event names use snake_case convention
- No sensitive data tracked
- All code compiles successfully ✅
* Perfect! I've successfully removed the `is_personal` property. Here's the final summary:
## Updated Summary
I've successfully added analytics events for organization-related actions and incorporated all your feedback. Here's the final implementation:
### Changes Made
**1. `crates/server/src/routes/organizations.rs`:**
- Added `Deployment` trait import
- **Organization Created** (line 90-109):
- Event: `"organization_created"`
- Properties: `org_id` only
- **Invitation Created** (line 124-144):
- Event: `"invitation_created"`
- Properties: `invitation_id`, `org_id`, `role`
- ✅ No sensitive data (invitee email excluded)
**2. `crates/server/src/routes/projects.rs`:**
- **Project Linked to Remote** (line 168-195):
- Event: `"project_linked_to_remote"`
- Properties: `project_id` only
### Implementation Details
- All events follow the existing PostHog analytics pattern using `deployment.track_if_analytics_allowed()`
- Events are tracked **after** successful operations, **before** returning responses
- UUIDs are converted to strings with `.to_string()`
- Event names use snake_case convention
- No sensitive data tracked
- Minimal properties tracked per your feedback
- All code compiles successfully ✅
|