- StreamingMessageComponent was just a wrapper around AssistantMessageComponent
- AssistantMessageComponent now handles its own stats rendering
- Made AssistantMessageComponent updatable with updateContent()
- Removed duplicate stats handling code from tui-renderer
- All stats are now managed by the component itself
- Create UserMessageComponent - handles user messages with spacing
- Create AssistantMessageComponent - handles complete assistant messages
- Create ThinkingSelectorComponent - wraps selector with borders
- Add setSelectedIndex to SelectList for preselecting current level
- Simplify tui-renderer by using dedicated components
- Much cleaner architecture - each message type is now a component
- Use single Text component with paddingY=1 for green background box
- Add spacer line with transparent background at top
- Header and content in same component with blank line separator
- Move error markers to header line instead of after content
- Add blank spacer line with no background before tool execution
- Apply colored background to header (read/write/edit line)
- Apply same colored background to content
- Use lighter gray (chalk.dim) for file content
- Show first 10 lines of content for write operations
- Use cyan color for file paths (matching markdown code color)
- Add background color support to Text component
- Replace Markdown component with Text in ToolExecutionComponent
- Use chalk.bold for formatting instead of markdown syntax
- Remove unnecessary markdown parsing overhead
- Remove code fences (```) from read output - show raw content
- Show first 10 lines instead of 5 for read
- Only show line count for write if > 10 lines
- Remove indentation from read output
- Cleaner, more minimal tool output display
- Remove "Command aborted by user" message (Aborted already shown separately)
- Remove STDOUT/STDERR labels - just show output cleanly
- Stderr is now separated by newline without labels
- Timeout and error messages moved to end of output
- Switch from exec() to spawn() with detached: true
- Create new process group for spawned commands
- Kill entire process group with process.kill(-pid) on abort
- This ensures commands like "sleep 4 && echo hello" abort immediately
- Previous implementation only killed parent shell, leaving subprocesses running
- Render thinking traces in dark gray italic in final messages
- Show thinking as italic markdown in streaming view
- Remove code fences from bash output for cleaner minimal display
- Remove superfluous empty line after tool executions
- Thinking blocks now render inline in proper order with text
- Add ctrl+k to delete line instruction
- Change all "set x to y" confirmation messages to blue with padding
- Add blue top and bottom borders around thinking selector dialog
- Add /thinking slash command with autocomplete for setting reasoning levels (off, minimal, low, medium, high)
- Fix Ctrl+C behavior: remove hardcoded exit in TUI, let focused component handle it
- Add empty lines before and after tool execution components for better visual separation
- Fix stats rendering: display stats AFTER tool executions complete (matches web-ui behavior)
- Remove "Press Ctrl+C again to exit" message, show "(esc to interrupt)" in loader instead
- Add bash tool abort signal support with immediate SIGKILL on interrupt
- Make Text and Markdown components return empty arrays when no actual text content
- Add setCustomBgRgb() method to Markdown for dynamic background colors
- Added string-width library for proper terminal column width calculation
- Fixed wrapLine() to split by newlines before wrapping (like Text component)
- Fixed Loader interval leak by stopping before container removal
- Changed loader message from 'Loading...' to 'Working...'
- Remove old TUI implementation and components (LoadingAnimation, MarkdownComponent, TextComponent, TextEditor, WhitespaceComponent)
- Rename components-new to components with new API (Loader, Markdown, Text, Editor, Spacer)
- Move Text and Input components to separate files in src/components/
- Add render caching to Text component (similar to Markdown)
- Add proper ANSI code handling in Text component using stripVTControlCharacters
- Update coding-agent to use new TUI API (requires ProcessTerminal, uses custom Editor subclass for key handling)
- Remove old test files, keep only chat-simple.ts and virtual-terminal.ts
- Update README.md with new minimal API documentation
- Switch from tsc to tsgo for type checking
- Update package dependencies across monorepo
- Paste markers now show line count: [paste #1 +50 lines]
- Update replacement logic to handle both old and new marker formats
- Provides better visibility into paste size
- Add paddingX and paddingY support to Text component (default 1, 1)
- Fix padding calculation bug in both Text and Markdown
- Right padding now correctly fills to terminal width
- Remove unused Spacer import from chat-simple
- Enable bracketed paste mode for handling large pastes
- Fix editor duplicate line rendering bug at terminal width
- Add padding support to Markdown component (paddingX/Y)
- Add Spacer component for vertical spacing
- Update chat-simple with spacers between messages
- Add collapsible thinking blocks with shimmer animation during streaming
- Update user messages to use orange gradient pill styling (matching sitegeist)
- Fix cost display to only show for completed messages, not while streaming
- Update tool renderers to use ChevronsUpDown/ChevronUp icons instead of rotating ChevronRight
- Export ThinkingBlock component from public API
- Add inputChanged state to track when user modifies input after save
- Remove Clear button and removeKey() method entirely
- Save button now disables after successful save until input changes
- Save button stays enabled on test failure (allows immediate retry)
- Keep input field showing stars (••••) after successful save instead of clearing
This provides clearer feedback and prevents accidental key deletion.
- Add handling for message_start event to capture initial token usage
- Fix message_delta to use assignment (=) instead of addition (+=)
since Anthropic sends cumulative token counts, not incremental
- Add comprehensive tests for all providers (Google, OpenAI Completions,
OpenAI Responses, Anthropic)
- Document OpenAI limitation: token stats only available at stream end
Fixes issue where aborted streams had zero token counts despite
Anthropic sending input tokens in the initial message_start event.
