Revision history for Acme-Claude-Shell

0.04    2026-10-17
	- Require Claude::Agent 0.14: hooks now run through the CLI and command output is printed from the tool results.
	- Add verbose, audit_log and effort options and the --verbose and --effort flags.
	- Turn off the CLI built-in tools so every command goes through execute_command.
	- Read the approval from STDIN when output is not colorful; end of input cancels.
	- Declare utf8 in Hooks.pm so the statistics rule prints.

0.01    2026-01-11
        First version - AI-powered interactive shell showcasing Claude::Agent SDK

        [Features]
        - shell() for interactive multi-turn sessions using session()
        - run() for single-shot commands using query()
        - SDK MCP tools: execute_command, list_files, read_file
        - Safety hooks with dangerous command detection
        - Colorful terminal UI with spinners and menus
        - Dry-run mode for previewing commands
        - Command history tracking

        [SDK Features Demonstrated]
        - query() - Single-shot commands via run()
        - session() - Multi-turn context via shell()
        - SDK MCP Tools - Custom shell execution tools
        - Hooks (PreToolUse) - Safety confirmation menus
        - Hooks (PostToolUse) - Command logging
        - Dry-run mode - Preview without executing
        - IO::Async - Non-blocking spinners
        - CLI utilities - Colored output, menus, status messages

