Commit Graph
43 Commits
Author SHA1 Message Date
Mohamed Boudra edf47a24bc refactor(agent): consolidate agent type definitions and add multi-agent-type support 2025-10-26 18:03:03 +01:00
Mohamed Boudra 700840da5a refactor(agent-stream): convert ScrollView to inverted FlatList for better performance 2025-10-26 17:04:22 +01:00
Mohamed Boudra 2c1b5b13fe fix(agent): track initialization state to prevent duplicate agent initialization 2025-10-26 16:28:55 +01:00
Mohamed Boudra cf7e14e36b fix(keyboard): use transform instead of padding for keyboard animation 2025-10-26 16:19:30 +01:00
Mohamed BoudraandClaude 985e9db6db fix(chat): maintain scroll position when keyboard appears
When the keyboard appeared, the chat content would get pushed up and the user would lose sight of what they were viewing. This happened because the outer container had keyboard-aware padding, but the ScrollView's content padding was static.

Now the ScrollView's contentContainerStyle receives animated padding that matches the keyboard height, ensuring the content maintains its relative position and the user keeps seeing the same messages when the keyboard appears.

Changes:
- Pass keyboardHeight SharedValue to AgentStreamView
- Add animated contentPaddingStyle that adjusts for keyboard
- Apply dynamic padding to ScrollView contentContainerStyle
- Content now smoothly adjusts as keyboard animates in/out

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 15:08:52 +01:00
Mohamed BoudraandClaude e82a7410e7 fix(agent-stream): prevent visible scroll animation on initial load
When loading an agent chat with existing messages, the ScrollView would render at the top and then animate scrolling to the bottom, creating a jarring user experience.

Now the initial scroll to bottom happens instantly (no animation), and only subsequent auto-scrolls (when new messages arrive) are animated. This provides a smooth loading experience while maintaining smooth animations for new content.

Changes:
- Add hasScrolledInitially ref to track first scroll
- Use animated: false for initial scroll, animated: true for subsequent scrolls
- Remove debug console.log from scroll handler

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 15:05:11 +01:00
Mohamed BoudraandClaude d47019919e refactor(ui): improve footer controls layout and add scroll-to-bottom button
Simplify agent screen layout by removing redundant status bar container and consolidating all footer controls into the input area component. Add smooth fade animations for realtime mode transitions and a floating scroll-to-bottom button for better UX.

Changes:
- Consolidate status bar and controls into AgentInputArea for cleaner layout hierarchy
- Add scroll-to-bottom button to AgentStreamView with fade animations
- Fix realtime controls stacking on non-agent screens
- Add lastActivityAt serialization to MCP server agent responses
- Remove unnecessary layout wrapper in agent screen

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 15:03:33 +01:00
Mohamed Boudra c4bb10d3c9 feat: add voice note recording overlay with transcription feedback and worktree support 2025-10-26 13:48:14 +01:00
Mohamed BoudraandClaude dcfdccf07f fix(worktree): implement worktree creation for agent isolation
- Add worktree utility functions for git worktree management
- Fix stale closure issue in create-agent-modal causing worktreeName to not be sent
- Refactor create-agent-modal to use useCallback for all functions in proper order
- Add tilde path expansion before worktree creation to fix "Not in a git repository" error
- Add worktreeName parameter to create_agent_request WebSocket message
- Add debug logging for worktree creation flow
- Remove noisy logging (message chunk updates, session updates, agent update notifications)

The worktree feature allows creating isolated git worktrees for each agent,
enabling work on different branches simultaneously without conflicts.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 13:28:05 +01:00
Mohamed Boudra a3224175ee feat: add image upload support to agent chat with attachment preview 2025-10-26 07:35:06 +01:00
Mohamed Boudra faf087b3a6 refactor: standardize footer height calculations and alignment across components 2025-10-25 22:14:15 +02:00
Mohamed BoudraandClaude a405c29ab1 feat: replace single realtime button with three-button footer navigation
Replace the centered realtime button in the global footer with three buttons:
- Agents: Navigate to home screen
- New Agent: Open create agent modal
- Realtime: Start realtime mode (existing functionality)

This provides easier access to core navigation actions from any non-agent screen.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-25 21:59:10 +02:00
Mohamed Boudra 8d591da671 refactor: add dynamic input height, agent sorting, and last activity tracking 2025-10-25 21:56:44 +02:00
Mohamed Boudra ff02b500e0 feat: add voice detection gating for TTS playback and optimize agent screen rendering 2025-10-24 15:52:47 +02:00
Mohamed BoudraandClaude ce2ca53c58 feat: restore keyboard animation for footer controls
Added useReanimatedKeyboardAnimation to GlobalFooter to animate the entire
footer (status bar + controls) up when keyboard opens. Uses translateY
transform to shift footer above keyboard with smooth native timing.

Applied to all footer variants:
- Agent screen with registered controls
- Realtime mode on non-agent screens
- Button mode on non-agent screens

Maintains all recent fixes (portal architecture, tight spacing, smooth
transitions) while restoring the keyboard avoidance behavior.

Implementation by Codex.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 11:47:37 +02:00
Mohamed BoudraandClaude f2fe25de23 refactor: implement footer controls context for smooth transitions
Codex implemented a portal/context architecture to eliminate layout jank:

- Created FooterControlsProvider context with register/unregister methods
- GlobalFooter now reserves fixed height (88px + insets) for all modes
- Both AgentInputArea and RealtimeControls stack absolutely in same space
- Single shared Reanimated value drives cross-fade (250ms)
- Agent screen registers controls via context instead of rendering inline
- Content padding adjusted to account for footer height
- Borders and safe area moved to shared container
- AgentInputArea simplified to pure component (no internal animations)

This guarantees:
- No layout shifts during transitions
- Smooth cross-fade between control modes
- No gaps or double borders
- Both controls never occupy layout space simultaneously

Implementation by OpenAI Codex per architectural recommendation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 11:36:17 +02:00
Mohamed BoudraandClaude 6f4d47848c fix: use absolute positioning for hidden AgentInputArea to prevent layout space
AgentInputArea was still taking up 88px height when opacity was 0, creating
a gap between status bar and realtime controls. Now switches to position
absolute when hidden (opacity < 0.5) to remove from layout flow completely.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 11:25:12 +02:00
Mohamed BoudraandClaude 465aa1cd78 fix: smooth transition between text and realtime controls with coordinated animations
- Keep AgentInputArea always mounted, animate opacity (0→1 / 1→0) instead of unmounting
- Use controlled opacity animation for GlobalFooter's RealtimeControls on agent screen
- Both controls fade in/out over 250ms, synchronized for smooth cross-fade
- Disable pointer events on hidden controls to prevent interaction issues
- Keep FadeIn/FadeOut behavior on non-agent screens (home, orchestrator) unchanged

This eliminates the layout "push" effect where GlobalFooter would take up space
while fading in, causing visible jank. Now both controls overlay and cross-fade
smoothly without affecting layout.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 11:23:37 +02:00
Mohamed BoudraandClaude 9299bb5d4c refactor: restore agent status bar and clean up input area layout
- Add AgentStatusBar back to agent screen layout above controls
- Remove duplicate mode badge from AgentInputArea (now only in status bar)
- Simplify AgentInputArea to horizontal layout matching RealtimeControls
- Set both controls to height: 88 for consistent sizing
- Remove conditional rendering that caused component to unmount

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 11:19:19 +02:00
Mohamed BoudraandClaude 3483bd9afd fix: improve realtime controls layout and add agent status bar
- Change realtime controls to horizontal layout with fixed height (88px)
- Add orientation prop to VolumeMeter for horizontal/vertical modes
- Create AgentStatusBar component showing mode badge and agent status
- Add agent persistence system for managing agent state across restarts
- Fix bottom sheet dismiss handling to clear state properly
- Remove debug timer from realtime controls

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 11:17:05 +02:00
Mohamed Boudra d24bf65fe9 refactor: improve UI consistency across message components and theme styles 2025-10-23 22:46:09 +02:00
Mohamed Boudra 29e6da8536 feat: add screenshot and settings for Claude, refactor agent stream and orchestrator views
- Introduced a new screenshot image for the app.
- Added local settings for Claude permissions.
- Refactored AgentStreamView and OrchestratorMessagesView to utilize new types for tool calls and permissions.
- Updated ToolCallBottomSheet to handle selected tool calls more efficiently.
- Enhanced type definitions for shared data structures related to tool calls and permissions.
2025-10-23 22:12:02 +02:00
Mohamed Boudra a0f45f2cfc fix: correct typescript ref types for bottom sheet and audio player 2025-10-23 20:06:11 +02:00
Mohamed Boudra 15320819a7 fix: migrate to @boudra/expo-two-way-audio and add tool call details bottom sheet 2025-10-23 20:01:52 +02:00
Mohamed BoudraandClaude 74fffcd8a3 refactor: optimize audio initialization and fix agent interactions
- Lazy initialize audio (on-demand instead of mount) in both player and Speechmatics hooks
- Add audio session teardown on stop for proper cleanup
- Implement agent audio recording with sendAgentAudio in AgentInputArea
- Fix Android navigation race condition in CreateAgentModal (navigate before closing)
- Add animations to global footer and agent screen (FadeIn/FadeOut)
- Auto-cancel stuck agents when sending new messages
- Fix permission request ID propagation from AgentManager to Session
- Apply theme background color via AppContainer wrapper

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-23 13:15:18 +02:00
Mohamed Boudra 10189514dd ```
refactor: centralize global footer and simplify agent screen input handling
```
2025-10-23 12:35:28 +02:00
Mohamed Boudra 027ae59ae7 ```
fix: stop audio playback when ending realtime session
```
2025-10-23 12:29:21 +02:00
Mohamed Boudra 91d691f31d ```
refactor: reset message IDs on new turn and add activity log handlers

- Reset assistant message and thought IDs when starting new agent turn
- Add comprehensive activity log handlers in session context
- Handle tool calls, results, and errors with proper state updates
- Add transcription and assistant chunk streaming handlers
- Improve audio playback with proper error handling and confirmation
- Use generateMessageId() for consistent ID generation
- Filter out transcription activity logs from chat
- Stop audio playback when real speech is detected
```
2025-10-23 12:22:42 +02:00
Mohamed Boudra 41be2d4096 ```
refactor: implement async agent creation flow with loading states

- Add loading states and request tracking to agent creation modal
- Move agent creation logic from parent to modal component
- Add automatic navigation to agent page after creation
- Implement requestId-based response matching for agent_created events
- Add audio output handling in session context
- Improve modal UX with disabled states during creation
```
2025-10-23 12:04:12 +02:00
Mohamed Boudra 542707ecdd feat: add bottom sheet modal for agent creation UI 2025-10-23 11:53:38 +02:00
Mohamed Boudra 85a0e46ba9 ```
feat: add recent paths suggestions and improve UX polish

- Add recent paths hook to persist and suggest working directories
- Update Android icon assets and simplify adaptive icon configuration
- Remove background styling from header icon buttons for cleaner look
- Export expandTilde utility for path normalization in agent creation
- Add horizontal scrollable chips for recent path suggestions
```
2025-10-23 11:26:36 +02:00
Mohamed Boudra 8177aa0c2a feat: add home screen with agent list and orchestrator navigation 2025-10-23 11:11:20 +02:00
Mohamed Boudra a930c4156a docs: add Codex integration guide and improve agent creation UX 2025-10-23 09:22:11 +02:00
Mohamed Boudra 0893a9dc33 ```
refactor: improve agent notification types and fix activity curator

- Convert agent notifications to discriminated union (session/permission/status)
- Fix activity curator to properly handle typed session updates
- Serialize Date objects in AgentInfo for JSON compatibility
- Use activity curator for title generation context
- Reduce console.error to console.warn for non-critical WebSocket errors
- Improve spacing in agent stream views
- Delay title generation until 15+ updates available
```
2025-10-23 09:01:38 +02:00
Mohamed Boudra c6cdc09a0b ```
refactor: deduplicate messages using stable IDs and add permission UI with gesture-based sidebar
```
2025-10-23 08:37:53 +02:00
Mohamed Boudra 70bdbd74eb refactor: deduplicate user messages and sync agent history on reconnection 2025-10-22 22:38:15 +02:00
Mohamed Boudra b86e5fbb3f Based on the changes, I can see this is a significant feature addition that adds the ability to create agents and communicate with them through both text and audio, with a modal UI for agent creation and mode switching.
```
feat: add agent creation modal and agent-specific messaging

- Add CreateAgentModal component for creating new agents with mode selection
- Implement agent-specific text and audio message routing
- Add mode selector modal with visual mode switching UI
- Introduce unified stream reducer pattern for agent activity
- Refactor AgentStreamView to use StreamItem[] instead of raw notifications
- Update ActiveProcesses to show orchestrator pill and support mode switching
- Add message types: send_agent_message, send_agent_audio, create_agent_request, set_agent_mode
- Implement agent audio transcription and message forwarding in session handler
- Add mode badge UI showing current agent mode
- Update tmux capture-pane to allowed commands

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
```
2025-10-22 22:06:00 +02:00
Mohamed Boudra 8b9561b379 ```
feat: add realtime mode drift protection and improve voice UX
```
2025-10-22 19:06:59 +02:00
015d0f0e27 feat: merge tool calls with their updates into single unified view
Instead of showing tool_call and tool_call_update as separate events,
now merge them by toolCallId into a single MergedToolCall that updates
as new information comes in.

**Changes:**
- Added MergedToolCall type with start/end timestamps
- Renamed groupTextChunks to groupActivities with tool call merging logic
- Track tool calls by ID and merge all updates into single entry
- Replace ToolCallItem with MergedToolCallItem component
- AgentStreamView now uses groupActivities for unified grouping

**User Experience:**
- Each tool call appears once and updates in place
- Status changes from pending → in_progress → completed
- Input/output merge as they become available
- Cleaner, less noisy activity view

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2025-10-22 18:17:53 +02:00
674977d6f8 feat: improve agent activity UI and fix status update propagation
**Agent Activity UI Improvements:**
- Create typed discriminated unions for SessionNotification updates
- Add AgentActivity component with specialized rendering for each update type
- Group consecutive text chunks into single messages (like main chat)
- Add collapsible tool call rendering with input/output details
- Add plan rendering with task status indicators
- Add fallback rendering for unknown activity types (badge + drawer)

**Agent Status Update Fix:**
- Fix agent killing not updating UI status
- Session now detects status change notifications and emits agent_status messages
- Agent manager delays agent deletion to allow status updates to propagate
- Frontend agent_status handler now receives proper updates

**Technical Details:**
- Created /packages/app/src/types/agent-activity.ts with typed session updates
- Created /packages/app/src/components/agent-activity.tsx with activity renderers
- Updated AgentStreamView to use grouped activities with useMemo
- Modified session.ts subscribeToAgent to emit agent_status on status changes
- Modified agent-manager.ts killAgent to delay deletion for status propagation

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2025-10-22 18:10:29 +02:00
e1e14b1473 feat: improve UI/UX with volume meter and refine input area styling
- Add VolumeMeter component for realtime audio visualization
- Refactor input area to show volume meter in realtime mode
- Update button styling and layout for cleaner interface
- Improve text input integration with better visual hierarchy
- Add volume state tracking to Speechmatics audio hook
- Add agent working directory validation on creation
- Update agent prompt with better orchestration guidelines

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2025-10-22 18:00:59 +02:00
Mohamed Boudra de5aba4186 docs: update tmux commands formatting and add Android screenshot instructions 2025-10-22 16:50:07 +02:00
Mohamed Boudra 89641a18e7 feat: refactor app structure and components for improved organization and functionality
- Moved components and hooks into a new directory structure under `src/app` for better organization.
- Updated the main entry point to use `index.ts` and adjusted routing accordingly.
- Introduced new components such as `ActiveProcesses`, `AgentStreamView`, and `ConnectionStatus` to enhance the app's functionality.
- Removed deprecated components and hooks to streamline the codebase.
- Updated styles to align with the new theme structure and ensure consistency across the app.

This refactor aims to improve maintainability and scalability of the application.
2025-10-22 15:48:53 +02:00