- Add question card builder and answer handling in feishu.py
- Extend SDKSession with pending question state and answer method
- Update card callback handler to support question answers
- Add test cases for question flow and card responses
- Document usage with test_can_use_tool_ask.py example
Add visual feedback for card actions by returning toast messages and updated cards per Feishu requirements. The handler now responds within 3 seconds with appropriate success/warning toasts and card updates showing approval/denial status. Also added operator tracking in logs and comprehensive tests.
- Implement SDK session with secretary model for tool approval flow
- Add audit logging for tool usage and permission decisions
- Support Feishu card interactions for approval requests
- Add new commands for task interruption and progress checking
- Remove old test files and update documentation
- Add "default" permission mode: no flags passed to CC, uses its own
built-in default (asks about everything). Now the system default.
- Rename "accept" alias to "edit" (acceptEdits) for clarity
- Remove "skip" alias (duplicate of "bypass")
- Update all help text, error messages, tests, and LLM prompts
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
The module has long since moved away from PTY technology, using
claude -p with --output-format stream-json and --resume instead.
Rename to cc_runner to accurately reflect what it does.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
