- Add deriveExportColors() to compute page/card/info backgrounds from userMessageBg
- Use luminance detection to adapt colors for light/dark themes
- Use info-bg for model-change, compaction, system-prompt sections
- Use selectedBg for hover states and summary backgrounds
- Add scroll-to-message with highlight when clicking tree nodes
- Fix mobile overlay to close sidebar on click
- Wider sidebar (400px) with search and filter controls
- Add tree sidebar with search and filter (Default/All/Labels)
- Client-side markdown/syntax highlighting via vendored marked.js + highlight.js
- Base64 encode session data to avoid escaping issues
- Reuse theme.ts color tokens via getResolvedThemeColors()
- Sticky sidebar, responsive mobile layout with overlay
- Click tree node to scroll to message
- Keyboard shortcuts: Esc to reset, Ctrl/Cmd+F to search
Added glob pattern support (e.g., github-copilot/*, *sonnet*) to --models
and enabledModels. Patterns are matched against both provider/modelId and
just modelId, so *sonnet* works without requiring anthropic/*sonnet*.
The existing fuzzy substring matching for non-glob patterns is preserved.
fixes#337
- Add configurable thinkingText color for thinking blocks (defaults to muted)
- Make 'Thinking...' label italic when collapsed
- Fix Ctrl+T during streaming hiding the current message
- Track streamingMessage to properly re-render on toggle
Based on #366 by @paulbettner
- Add setEditorText() and getEditorText() to HookUIContext for prompt generator pattern
- custom() now accepts async factories for fire-and-forget work
- Add CancellableLoader component to tui package
- Add BorderedLoader component for hooks with cancel UI
- Export HookAPI, HookContext, HookFactory from main package
- Update all examples to import from packages instead of relative paths
- Update hooks.md and custom-tools.md documentation
fixes#350
When creating a new session, initial model and thinking level were set
on the agent but never saved to session file. This caused --resume to
default thinking level to 'off'.
fixes#342
- Simplify compaction section, link to docs/compaction.md for details
- Clarify that branch summaries are optional (user is prompted)
- Change /branch to /tree in compaction note
- Mark as breaking for custom themes
- Explain that custom themes must add new tokens or fail to load
- Note total color count increased from 46 to 50
- Reference theme.md and built-in themes
- New tui.md covers component system for hooks and custom tools
- Update hooks.md intro with 'Key capabilities' highlighting UI
- Update custom-tools.md intro with 'Key capabilities' highlighting UI
- Reference tui.md from both docs
- Remove timeout logic from HookRunner
- Remove hookTimeout from Settings interface
- Remove getHookTimeout/setHookTimeout methods
- Update CHANGELOG.md and hooks.md
Timeouts were inconsistently applied and caused issues with
legitimate slow operations (LLM calls, user prompts). Users can
use Ctrl+C to abort hung hooks.
- New compaction.md covers auto-compaction and branch summarization
- Explains cut points, split turns, data model, file tracking
- Documents session_before_compact and session_before_tree hooks
- Rewritten hooks.md matches actual API (separate event names)
- Correct ctx.ui.custom() signature (returns handle, not callback)
- Documents all session events including tree events
- Adds sessionManager and modelRegistry usage
- Updates all examples to use correct API
- Add custom tools API rework to CHANGELOG breaking changes
- Update docs/custom-tools.md with new types and signatures
- Update README quick example with correct execute signature
- CustomAgentTool renamed to CustomTool
- ToolAPI renamed to CustomToolAPI
- ToolContext renamed to CustomToolContext
- ToolSessionEvent renamed to CustomToolSessionEvent
- Added CustomToolContext parameter to execute() and onSession()
- CustomToolFactory now returns CustomTool<any, any> for type compatibility
- dispose() replaced with onSession({ reason: 'shutdown' })
- Added wrapCustomTool() to convert CustomTool to AgentTool
- Session exposes setToolUIContext() instead of leaking internals
- Fix ToolExecutionComponent to sync with toolOutputExpanded state
- Update all custom tool examples for new API
Previously, the Editor component used character-level (grapheme-level)
wrapping, which broke words mid-character at line boundaries. This
created an ugly visual experience when typing or pasting long text.
Now the Editor uses word-aware wrapping:
- Wraps at word boundaries when possible
- Falls back to character-level wrapping for tokens wider than the
available width (e.g., long URLs)
- Strips leading whitespace at line starts
- Preserves multiple spaces within lines
Added wordWrapLine() helper function that tokenizes text into words
and whitespace runs, then builds chunks that fit within the specified
width while respecting word boundaries.
Also updated buildVisualLineMap() to use the same word wrapping logic
for consistent cursor navigation.
Added tests for:
- Word boundary wrapping
- Leading whitespace stripping
- Long token (URL) character-level fallback
- Multiple space preservation
- Edge cases (empty string, exact fit)