- Titlebar only keeps toggle and close buttons
- Toggle button wider to use freed space
- Nav bar opens as popup below terminal (no internal space change)
- Added Start/Restart agent buttons to TerminalNavButtons
- Backdrop blur on popup bar
- Extract nav buttons (MCP, Claude, Continue, Resume, Clear, Refresh, keys, arrows, scroll) into TerminalNavButtons.vue
- Add toggle button in AgentTerminal titlebar to show/hide nav bar
- Add sendRaw() to useAgentTerminal for raw PTY input (no \r append)
- Add touch drag support for AgentTerminal on mobile
- Skip auto-focus on small screens to prevent virtual keyboard popup
- Connect WebSocket BEFORE loading history to catch real-time permissions
- loadHistory() now preserves unresolved intervention cards
- loadPendingPermissions() runs AFTER loadHistory() to avoid race condition
PromptBar now auto-opens when a permission request arrives and it's hidden.
Permission cards show rich contextual info: tool badge, description, code
blocks for Bash, diff preview for Edit, file paths for Write, and icons
on Allow/Deny buttons.
- Broadcast PermissionRequest hook as claude-permission WS event
- Fix dedup bug where undefined requestId blocked all permission cards
- Add sendInput() to AgentTerminal for char-by-char PTY responses
- Make AskUserQuestion options clickable (sends option number to PTY)
- Add Approve/Reject buttons for ExitPlanMode plan cards
- Permission Allow/Deny now sends y/n to PTY instead of broken HTTP call
- Add :key to PromptBar to force remount on agent switch, fixing shared terminal session bug
- Raise AgentTerminal z-index above PromptBar backdrop so floating terminal is visible/clickable
- Send prompt text char-by-char (15ms delay) matching FloatingVoice pattern for Claude Code compat
- Guard xterm dispose against unloaded addons to prevent errors on agent switch
- Widen PromptBar panel from 360px to 420px to fit all ChatInput buttons
Extract voice recording logic from FloatingVoice.vue into useVoiceCapture
composable. TranscriptCard now does real recording instead of mock typing.
InputSettings allows voice mode toggle (WebSpeech/Whisper GPU), mic
selection, and debug audio playback. ChatInput gets a settings gear button.
Long-press on FloatBubble shows a floating TranscriptCard (push-to-talk)
instead of opening the full PromptBar. Release stops recording after a
500ms buffer. Click still opens PromptBar normally.
Parallel MediaRecorder captures raw audio in WebSpeech mode for DB save
and debug playback. Transient errors (no-speech) no longer kill sessions.
Touch selection prevention on FloatBubble for tablets.
- Add transcript-engine service that parses Claude Code JSONL transcripts
with session listing, message extraction, token/stats analysis, and caching
- Add transcript REST routes (sessions list, latest, by session ID, section filtering)
- Rewrite ConversationHistory to fetch from /api/transcript/* instead of mock data
- Add session pills for switching between conversation sessions
- Add stats bar footer with model, duration, tokens, and tool count
- Add TranscriptSession/TranscriptMessage types, ChatInput, InputSettings,
PromptBar updates, TranscriptCard, and useVoiceCapture composable
