cf5b04d3b8dc1c010b8a0ea20757bac95f0b6e1f
1308 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Britannio Jarrett
|
ddb21f969d |
update github docs (vibe-kanban) (#1388)
* I have explored the codebase and confirmed that the GitHub integration now relies on the `gh` CLI instead of a Personal Access Token (PAT) configured in the settings. The setup process is "just-in-time", prompting the user to install or authenticate the CLI when they attempt to create a Pull Request. I have updated the documentation to reflect these changes: 1. **`docs/integrations/github-integration.mdx`**: Rewrote the guide to explain the CLI-based workflow, including automatic setup on macOS and manual setup instructions for other platforms, as well as troubleshooting steps. 2. **`docs/getting-started.mdx`**: Updated the installation steps to remove the instruction to "Connect to GitHub in Settings" and instead mention the `gh` CLI requirement. 3. **`docs/configuration-customisation/global-settings.mdx`**: Removed the "GitHub Integration" section (since it no longer exists in Global Settings) and replaced it with a "Git Configuration" section describing the "Branch Prefix" setting, which is present in the UI. I also verified that `docs/core-features/completing-a-task.mdx` remains accurate with the new workflow. No images were needed as the process is now primarily CLI-driven or standard dialog-based, and I removed the outdated screenshots from the documentation files. I ran `pnpm run check` to ensure no regressions were introduced, and it passed successfully. ### Summary of Changes | File | Change | | :--- | :--- | | `docs/integrations/github-integration.mdx` | Rewritten to document `gh` CLI usage and troubleshooting | | `docs/getting-started.mdx` | Removed outdated "Connect GitHub" step; added CLI info | | `docs/configuration-customisation/global-settings.mdx` | Removed GitHub section; added Git Branch Prefix section | * The "Troubleshooting" section has been removed from `docs/integrations/github-integration.mdx`. * I have performed a comprehensive search for "github" across the documentation and codebase. I found and updated a few more references to ensure consistency: 1. **`docs/core-features/completing-a-task.mdx`**: Updated the link text to "Set up GitHub CLI integration" instead of "Set up GitHub authentication". 2. **`docs/index.mdx`**: Updated the Settings card description to remove "GitHub integration" and replace it with "git settings". 3. **`docs/configuration-customisation/global-settings.mdx`**: Updated the alt text of the settings screenshot to remove the mention of "GitHub integration settings". I verified other references in `docs/core-features/creating-tasks.mdx`, `docs/core-features/monitoring-task-execution.mdx`, and `docs/supported-coding-agents.mdx` and confirmed they are either correct (referring to platform features like polling or agents like Copilot) or generic examples that don't need changing. The documentation now fully reflects the shift to the CLI-based GitHub integration workflow. |
||
|
Britannio Jarrett
|
c4f4bf8318 |
I've updated the documentation image as requested. (#1390)
Here's what I did: 1. Copied the new image from `vk-task-dialog.png` to `docs/images/vk-task-dialog.png`. 2. Updated `docs/core-features/creating-tasks.mdx` to reference the new image. 3. Removed the old `docs/images/screenshot-create-task.png` file. The documentation now uses the new task dialog image. |
||
Alex Netsch
|
82d04642fb | Fix push notification when dev server stop (#1389) | ||
potable-anarchy
|
14fe26f72d |
feat: Add setting to use Claude subscription when API key is detected (#1229)
* feat: Add setting to use Claude subscription when API key is detected This commit adds a new optional setting `use_claude_subscription` to the ClaudeCode executor configuration. When enabled, this setting removes the ANTHROPIC_API_KEY environment variable before spawning the Claude Code agent, ensuring that users with Claude Pro/Team subscriptions can opt to use their subscription instead of being charged API fees. ## Changes - Added `use_claude_subscription` optional field to the `ClaudeCode` struct - Implemented logic in `spawn_internal` to conditionally remove `ANTHROPIC_API_KEY` from the environment when the setting is enabled - Added tracing log when API key is removed for better debugging ## Implementation Details - The field is optional (`Option<bool>`) and defaults to `false` when not set, maintaining backward compatibility - Uses `#[serde(skip_serializing_if = "Option::is_none")]` to keep JSON clean - The setting is automatically exposed in the frontend via the JSON Schema auto-generation from Rust structs - TypeScript bindings are auto-generated via the `#[derive(TS)]` macro ## Benefits - Prevents unexpected API charges for users with Claude subscriptions - Gives users explicit control over authentication method - Backward compatible - existing configurations continue to work unchanged - No frontend changes needed - the setting appears automatically in the ExecutorConfigForm ## Related - Addresses feature request in discussion #1228 - Design document: https://github.com/potable-anarchy/vibe-kanban-launcher/blob/main/DESIGN_PROPOSAL.md * cleanups rename the config parameter to `disable_api_key`. regenerate type bindings. * suggest using the setting in the api-key warning --------- Co-authored-by: Solomon <abcpro11051@disroot.org> |
||
GitHub Action
|
9dabff0752 | chore: bump version to 0.0.124 | ||
Ryosuke Hayashi
|
ae9425b96b |
Fetch initial diffs asynchronously in diff stream (#1376)
Move the blocking get_diffs call into a spawned task so the WebSocket stream is returned immediately. This prevents timeouts when fetching diffs for repositories with many changed files. Also remove a duplicate useEffect in DiffsPanel. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Alex Netsch
|
d430f37475 | Strip remote prefix for remote branches (#1373) | ||
|
Alex Netsch
|
e6a55a9b6e | Bump claude code to 2.0.54 (#1377) | ||
|
Alex Netsch
|
b93cf5dacf | Parse tool_use_id in canusetool control request (#1370) | ||
Louis Knight-Webb
|
17e0acc906 |
Bump amp (vibe-kanban) (#1372)
* Done. Updated Amp version to `0.0.1764081384-g1961a83` in [crates/executors/src/executors/amp.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/ba61-bump-amp/crates/executors/src/executors/amp.rs#L36). * Updated to `0.0.1764081384-g1961a8`. |
||
|
GitHub Action
|
43bfe63931 | chore: bump version to 0.0.123 | ||
Solomon
|
6d2819490f |
Remove log truncation (#1368)
`[truncated]` corrupts json logs. |
||
|
Ryosuke Hayashi
|
581a4df645 |
chore: bump @anthropic-ai/claude-code to 2.0.53 (#1364)
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com> |
||
|
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) |
||
Stephan Fitzpatrick
|
f651c64f7d |
Perfect! I've successfully added a text wrap toggle to the frontend diff viewer. Here's a summary of the changes: (#1219)
## Changes Made ### 1. **State Management** (`frontend/src/stores/useDiffViewStore.ts:11-13,22-23,29`) - Added `wrapText` boolean state (defaults to `false`) - Added `setWrapText` action to update the state - Exported `useWrapTextDiff` hook for components to access the state ### 2. **UI Toggle Component** (`frontend/src/components/diff-view-switch.tsx:1,8,28-29,32,100-121`) - Imported `WrapText` icon from `lucide-react` - Added a new toggle group for the text wrap feature - The toggle appears alongside the existing view mode and whitespace toggles - Uses the same UI pattern as the "Ignore Whitespace" toggle - Includes tooltip with internationalization support ### 3. **Diff Viewer Integration** (`frontend/src/components/DiffCard.tsx:31,84,300`) - Imported and used the `useWrapTextDiff` hook - Connected the `wrapText` state to the `DiffView` component's `diffViewWrap` prop - The `DiffView` component now responds to the toggle state ## How It Works - The toggle button appears in the diff view controls with a `WrapText` icon - Clicking the toggle switches between wrapped and unwrapped text in the diff viewer - The state is managed globally via Zustand, so all diff viewers share the same wrap preference - The default is set to `false` (no wrapping), preserving the original behavior - The feature follows the existing architectural patterns for the ignore whitespace and view mode toggles The implementation is complete and ready to use! |
||
|
Solomon
|
44b7f749c5 |
Allow auth redirect to non-localhost (#1346)
Allow non-localhost clients to complete OAuth. |
||
|
Solomon
|
c2a10aaf72 |
fix: Copilot session resume (#1355)
GitHub Copilot CLI changed the the name of session files, which broke session resume. |
||
|
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
}
|
||
René Simonsen
|
037302c62f | Improved multi-process support of --mcp command (#1343) | ||
|
Solomon
|
c375560353 | followup: Prefer runtime env variable VK_SHARED_API_BASE (#1342) | ||
|
GitHub Action
|
f691fbd9cb | chore: bump version to 0.0.122 | ||
|
Louis Knight-Webb
|
40252b6ea7 |
Bump codex (#1345)
* Done. Bumped codex from 0.58.0 to 0.60.1 in [codex.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8d60-bump-codex/crates/executors/src/executors/codex.rs#L171). * Added `gpt-5.1-codex-max` model variant as a new `MAX` profile in [default_profiles.json](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8d60-bump-codex/crates/executors/default_profiles.json#L62-L68). |
||
|
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>
|
||
|
Louis Knight-Webb
|
a3c134b4a6 | Done. Version bumped to 0.0.1763625676-g928988. (#1344) | ||
|
GitHub Action
|
853b178ebf | chore: bump version to 0.0.121 | ||
|
Solomon
|
9a5323b3b4 |
Prefer runtime env variable VK_SHARED_API_BASE (#1340)
Enables testing a pre-release with a dev version of remote. |
||
|
Alex Netsch
|
6e5cb34f7e |
Better worktree errors (#1338)
* Info log if first create fails, properly clean up after first fail * Show stdout on git cli error * Fix swapped stderr/stdout |
||
|
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 ✅
|
||
|
Alex Netsch
|
23b0d9c0af | Fix ts compile (#1337) | ||
|
Louis Knight-Webb
|
5ac6c2b462 |
I've removed the touch-pan-y class from the Kanban board wrapper in frontend/src/pages/ProjectTasks.tsx. This enables horizontal scrolling on touch devices while maintaining vertical scrolling, which solves the issue. (#1334)
I also ran the type checks to ensure no regressions, and everything passed. The provided file path `crates/remote/src/db/project_tasks.rs` was not relevant to the UI scrolling issue, so no changes were made there. |
||
|
Alex Netsch
|
4b1af8cdc5 |
Show editor availability (vibe-kanban) (#1325)
* Perfect! I've successfully refactored the editor opening code to use the `CommandBuilder` pattern. Here's a summary of the changes: - Added `use executors::command::CommandBuilder;` - Changed return type from `Vec<String>` to `CommandBuilder` - Now returns a proper `CommandBuilder` that handles shell word splitting correctly - Supports quoted strings in custom commands (via `shlex` on Unix, `winsplit` on Windows) - Uses `CommandBuilder` pattern: `build_initial()` → `into_resolved()` - Resolves executables properly on **both Unix and Windows** (previously only Windows had resolution) - Better error messages that show which executable couldn't be found - Maps `ExecutorError` to `io::Error` for consistency with the function signature ✅ **Consistent cross-platform behavior**: Unix now also resolves executables properly ✅ **Sophisticated PATH resolution**: Uses login shell refresh logic for finding executables ✅ **Proper shell word splitting**: Handles quoted strings correctly in custom commands ✅ **Better error messages**: Shows exactly which executable couldn't be found ✅ **Follows established patterns**: Uses the same proven pattern as other executors in the codebase All checks pass: compilation, tests, and Clippy linting. The code is ready! Perfect! All changes have been successfully implemented and tested. Here's what was done: - Changed from: `Result<ResponseJson<ApiResponse<OpenEditorResponse>>, StatusCode>` - Changed to: `Result<ResponseJson<ApiResponse<OpenEditorResponse>>, ApiError>` - Changed from: `Err(StatusCode::INTERNAL_SERVER_ERROR)` (generic 500 error) - Changed to: `Err(ApiError::Io(e))` (passes actual error message) Now when the editor command fails (e.g., executable not found), the API will return a proper error response with the actual error message like: - `"IoError: Editor command not found: Executable 'cursor' not found in PATH"` This matches the pattern already used in `task_attempts.rs` and provides meaningful feedback to the frontend, which can display the error to users or fall back to the editor selection dialog. All checks pass: compilation, TypeScript type checking, and Clippy linting! Perfect! All changes have been successfully implemented and tested. Here's a summary: - New `EditorOpenError` enum with `ExecutableNotFound` variant - Contains structured fields: `executable` (the command that wasn't found) and `editor_type` (the configured editor) - Exports to TypeScript with discriminated union type - Changed `open_file()` return type: `Result<Option<String>, io::Error>` → `Result<Option<String>, EditorOpenError>` - Changed `spawn_local()` return type: `io::Result<()>` → `Result<(), EditorOpenError>` - Maps `ExecutorError::ExecutableNotFound` to structured `EditorOpenError::ExecutableNotFound` - Removed unused `io` import - Added `EditorOpen(#[from] EditorOpenError)` variant - Maps to `StatusCode::BAD_REQUEST` (400) instead of 500 - Returns proper error type: `"EditorOpenError"` - **`crates/server/src/routes/projects.rs:452`**: Changed from `ApiError::Io(e)` to `ApiError::EditorOpen(e)` - **`crates/server/src/routes/task_attempts.rs:965`**: Changed from generic `TaskAttemptError::ValidationError` to `ApiError::EditorOpen(e)` ```typescript export type EditorOpenError = { "type": "executable_not_found", executable: string, editor_type: string, }; ``` Now when an editor executable isn't found, the frontend receives: ```json { "type": "executable_not_found", "executable": "cursor", "editor_type": "CURSOR" } ``` Instead of a generic 500 error. This allows the frontend to: - Show specific error messages ("Cursor not found in PATH") - Suggest alternative editors - Provide installation links or PATH setup instructions - Offer to open the editor settings dialog All checks pass: compilation, TypeScript type checking, Clippy linting, and tests! Cleanup script changes for task attempt f9923e07-9b3b-4d18-b4d1-d4235cf0e12d * Refactor editor config (vibe-kanban a60c079b) Currently edit config is defined in crates/services/src/services/config/versions/v2.rs, we should consider moving it into a module instead. Weigh pros and cons, best practices and the current architecture * Review editor refactor (vibe-kanban 829ba3e5) Review the last 5 commits There's a rebase conflict in `GeneralSettings.tsx` that needs resolution. The conflict is in the imports: **Conflict (lines 41-49):** - **Your branch (HEAD)**: Imports from `ThemeProvider` and `ConfigProvider` (PascalCase) - **Main branch**: Imports from `theme-provider` and `config-provider` (kebab-case) + adds new editor availability features **Resolution needed:** Keep the main branch version because it: 1. Uses the newer kebab-case file naming convention 2. Adds `useEditorAvailability` and `EditorAvailabilityIndicator` features that complement your error handling work The resolved imports should be: ```typescript import { useEditorAvailability } from '@/hooks/useEditorAvailability'; import { EditorAvailabilityIndicator } from '@/components/EditorAvailabilityIndicator'; import { useTheme } from '@/components/theme-provider'; import { useUserSystem } from '@/components/config-provider'; ``` Would you like me to resolve this conflict and continue the rebase? Show available editors at startup (vibe-kanban 9f1ea85f) When onboarding, show a green checkmark next to installed editors. Use the editor struct refactored in the last 6 commits to make it work. Check eveyer editor in the enum at vk startup. Mkae sure editors being unailable does NOT break anything Fix imports after rebase - use PascalCase for ThemeProvider and ConfigProvider Perfect! All changes complete. Let me create a summary: ✅ **Changes made:** - Added `CheckEditorAvailabilityQuery::decl()` - Added `CheckEditorAvailabilityResponse::decl()` New types exported: ```typescript export type CheckEditorAvailabilityQuery = { editor_type: EditorType }; export type CheckEditorAvailabilityResponse = { available: boolean }; ``` - Added import for `CheckEditorAvailabilityResponse` - Updated `checkEditorAvailability` method: - Parameter type: `string` → `EditorType` (type-safe enum) - Return type: `{ available: boolean }` → `CheckEditorAvailabilityResponse` - ✅ Full type safety for editor availability checking - ✅ Frontend uses typed `EditorType` enum instead of strings - ✅ Consistent with other query/response type patterns - ✅ All checks pass (TypeScript + Rust compilation) The editor availability feature now has complete type safety from backend to frontend! * Fix i18n (vibe-kanban 57188642) For new editory avilability added in the last 3 commits. Run @scripts/check-i18n.sh until it passes. Make sure to check the script and set GITHUB_BASE_REF to main * Fix import: use github not github_service after rebase |
||
|
Alex Netsch
|
85690d6ac9 |
Cleanup dead code (#1336)
* Remove unused delete file endpoint, move test helpers to test files Fix missing git id in tests * Remove unused gh cli methods * Remove unused replace_process * Fix open editor exports, remove unused struct Fix compile * Remove unused get_tasks endpoint Re-add get tasks, used by mcp * Remove unused get_execution_processes endpoint * Remove unused get tag endpoint |
||
|
Louis Knight-Webb
|
20b8de95d2 |
I have successfully updated the amp version in crates/executors/src/executors/amp.rs to 0.0.1763539290-g33c1d8. (#1333)
Verified the changes by running `cargo check -p executors`, which completed successfully. |
||
|
Gabriel Gordon-Hall
|
44351a8931 |
refactor: unify Git and Github interfaces (#1327)
* unify git and github interfaces * move test helpers into test files * Update crates/services/src/services/git.rs Co-authored-by: Alex Netsch <alex@bloop.ai> * Update crates/services/src/services/git.rs Co-authored-by: Alex Netsch <alex@bloop.ai> --------- Co-authored-by: Alex Netsch <alex@bloop.ai> |
||
|
Britannio Jarrett
|
4e6dc1790b |
tags in showcase (vibe-kanban) (#1268)
* Done! I've added the 5th slide for the tags feature: 1. Added the slide configuration in [showcases.ts](file:///private/var/folders/xw/pvvt9zw954zbk1304cvjlnz00000gn/T/vibe-kanban/worktrees/20bc-tags-in-showcase/frontend/src/config/showcases.ts) with the video URL 2. Added English translations for the tags feature in [tasks.json](file:///private/var/folders/xw/pvvt9zw954zbk1304cvjlnz00000gn/T/vibe-kanban/worktrees/20bc-tags-in-showcase/frontend/src/i18n/locales/en/tasks.json) The showcase now has 5 slides with the tags feature explaining how users can save custom prompts and embed them in tasks or follow-ups. * Done! Updated the video URL and added translations to all locales: - Updated video URL in [showcases.ts](file:///private/var/folders/xw/pvvt9zw954zbk1304cvjlnz00000gn/T/vibe-kanban/worktrees/20bc-tags-in-showcase/frontend/src/config/showcases.ts) - Added English translations - Added Spanish translations - Added Japanese translations - Added Korean translations --------- Co-authored-by: Vibe Kanban <noreply@vibekanban.com> |
||
|
GitHub Action
|
050d832dad | chore: bump version to 0.0.120 | ||
|
Louis Knight-Webb
|
7fb00530c5 |
I have applied the fix to frontend/src/components/dialogs/tasks/CreateAttemptDialog.tsx. (#1329)
The new logic checks if the `latestAttempt`'s executor matches your configured default executor. If it does, it applies your configured variant (e.g. `VARIANT1`) instead of defaulting to `null`. If the executors differ, it safely falls back to the default variant. This ensures that when you create a new attempt on a task where you previously used your preferred agent, your preferred variant is now correctly pre-selected. |
||
|
GitHub Action
|
078554b5c7 | chore: bump version to 0.0.119 | ||
|
Louis Knight-Webb
|
4eab641db1 |
Done! The runner has been fixed. Changed macos-13 to macos-15-intel for the x86_64-apple-darwin build, with a comment explaining this is the last Intel runner image. (#1326)
|
||
|
Louis Knight-Webb
|
79a3d26278 |
Done. Bumped Amp from 0.0.1763179276-g784b75 to 0.0.1763482408-g51ddaa. (#1324)
|
||
|
Louis Knight-Webb
|
fea5a1b7ce |
Done. Updated [gemini.rs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/8fc7-bump-gemini-to-n/crates/executors/src/executors/gemini.rs#L24) to use @google/gemini-cli@0.16.0. (#1323)
|
||
|
Louis Knight-Webb
|
36bde0b4b9 |
Frontend file naming eslint rule (vibe-kanban) (#1322)
* Perfect! Now let me create a summary for you: ## ✅ ESLint Configuration Complete The linter has identified **29 files** that need to be renamed: ### **Files to Rename:** #### **Components → PascalCase (15 files)** ``` config-provider.tsx → ConfigProvider.tsx diff-view-switch.tsx → DiffViewSwitch.tsx logo.tsx → Logo.tsx navbar.tsx → Navbar.tsx (in layout/) search-bar.tsx → SearchBar.tsx theme-provider.tsx → ThemeProvider.tsx style-override.tsx → StyleOverride.tsx copy-files-field.tsx → CopyFilesField.tsx (in projects/) project-detail.tsx → ProjectDetail.tsx (in projects/) project-form-fields.tsx → ProjectFormFields.tsx (in projects/) project-list.tsx → ProjectList.tsx (in projects/) ``` #### **Contexts → PascalCase (2 files)** ``` project-context.tsx → ProjectContext.tsx search-context.tsx → SearchContext.tsx ``` #### **Pages → PascalCase (3 files)** ``` full-attempt-logs.tsx → FullAttemptLogs.tsx project-tasks.tsx → ProjectTasks.tsx projects.tsx → Projects.tsx ``` #### **Lib → camelCase (2 files)** ``` caret-position.ts → caretPosition.ts mcp-strategies.ts → mcpStrategies.ts ``` #### **Utils → camelCase (3 files)** ``` companion-install-task.ts → companionInstallTask.ts script-placeholders.ts → scriptPlaceholders.ts status-labels.ts → statusLabels.ts ``` #### **UI (shadcn) → kebab-case (4 files)** ``` ActionsDropdown.tsx → actions-dropdown.tsx ImageUploadSection.tsx → image-upload-section.tsx TitleDescriptionEditor.tsx → title-description-editor.tsx DataTable.tsx → data-table.tsx (in table/) Table.tsx → table.tsx (in table/) ImageChipNode.tsx → image-chip-node.tsx (in wysiwyg/) imageChipMarkdown.ts → image-chip-markdown.ts (in wysiwyg/) ``` #### **Entry Point (special case - 1 file)** ``` main.tsx → can stay as main.tsx (entry point convention) ``` **Next steps:** Should I proceed with renaming these files using `git mv`? * ## ✅ Complete! File Naming Standardization Successful ### **Summary** Successfully implemented and enforced file naming conventions for the frontend: ### **What Was Done:** 1. ✅ **Installed** `eslint-plugin-check-file@^2.8.0` 2. ✅ **Configured ESLint** with file naming rules: - **Components (.tsx)**: `PascalCase` - **Hooks (.ts)**: `camelCase` (with `use` prefix) - **Utils/Lib (.ts)**: `camelCase` - **Shadcn UI**: `kebab-case` (library convention) - **Entry points**: Excluded (`main.tsx`, `vite-env.d.ts`) 3. ✅ **Renamed 28 files** using `git mv`: - 10 components → PascalCase - 2 contexts → PascalCase - 3 pages → PascalCase - 2 lib files → camelCase - 3 utils → camelCase - 7 UI components → kebab-case - 1 utils component → PascalCase 4. ✅ **Fixed all imports** across the codebase (77 files modified) 5. ✅ **Verified**: - ✅ ESLint passes (no filename errors) - ✅ TypeScript check passes (no errors) - ✅ Build successful ### **Git Status:** - 28 files renamed (with history preserved via `git mv`) - 77 total files changed (renames + import updates) ### **Ready for commit!** The codebase now has consistent, enforceable file naming conventions that will prevent future inconsistencies. * Cleanup script changes for task attempt 11f8d7b9-99b5-41ce-934c-5ce75008a200 |
||
|
Louis Knight-Webb
|
0bd36a3b3a |
disable eslint-disable comments (vibe-kanban) (#1321)
* Done! All eslint-disable comments are now banned and the codebase is clean. **Summary of changes:** 1. **Installed** `eslint-plugin-eslint-comments` 2. **Updated** [frontend/.eslintrc.cjs](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/.eslintrc.cjs) to enforce the ban 3. **Fixed 3 files** by refactoring code instead of suppressing rules: - [FeatureShowcaseModal.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/src/components/showcase/FeatureShowcaseModal.tsx): Added ref to track activeScopes snapshot - [ShareDialog.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/src/components/dialogs/tasks/ShareDialog.tsx): Added shareTask object to dependencies - [wysiwyg.tsx](file:///private/var/folders/m1/9q_ct1913z10v6wbnv54j25r0000gn/T/vibe-kanban/worktrees/2550-disable-eslint-d/frontend/src/components/ui/wysiwyg.tsx): Added didInit ref guard for run-once effect All checks pass ✓ * lint fix |