Changed
- Compaction UI: Simplified collapsed compaction indicator to show warning-colored text with token count instead of styled banner. Removed redundant success message after compaction. (#108)
Fixed
- Print mode error handling:
-pflag now outputs error messages and exits with code 1 when requests fail, instead of silently producing no output. - Branch selector crash: Fixed TUI crash when user messages contained Unicode characters (like
✔or›) that caused line width to exceed terminal width. Now uses propertruncateToWidthinstead ofsubstring. - Bash output escape sequences: Fixed incomplete stripping of terminal escape sequences in bash tool output.
stripAnsimisses some sequences like standalone String Terminator (ESC \), which could cause rendering issues when displaying captured TUI output. - Footer overflow crash: Fixed TUI crash when terminal width is too narrow for the footer stats line. The footer now truncates gracefully instead of overflowing.
Added
authHeaderoption in models.json: Custom providers can set"authHeader": trueto automatically addAuthorization: Bearer <apiKey>header. Useful for providers that require explicit auth headers. (#81)--append-system-promptFlag: Append additional text or file contents to the system prompt. Supports both inline text and file paths. Complements--system-promptfor layering custom instructions without replacing the base system prompt. (#114 by @markusylisiurunen)- Thinking Block Toggle: Added
Ctrl+Tshortcut to toggle visibility of LLM thinking blocks. When toggled off, shows a static "Thinking..." label instead of full content. Useful for reducing visual clutter during long conversations. (#113 by @markusylisiurunen)