Previously, parallel tasks assigned to the same role (e.g., multiple
EXPLORE-* tasks with owner: 'explorer') executed serially because only
one agent instance existed per role name. This adds conditional parallel
agent spawning with instance-specific names (explorer-1, explorer-2) and
--agent-name arg for role task discovery filtering.
Affected skills: team-ultra-analyze, team-quality-assurance,
team-brainstorm, team-issue. Single-task modes preserve backward
compatibility with original agent names.
- Removed obsolete ccw-test command file.
- Updated ccw command to include new team workflows and collaborative planning features.
- Enhanced review-cycle skill with unified auto mode detection for streamlined user experience.
- Improved team-quality-assurance monitoring command to utilize consistent auto mode detection.
- Standardized auto mode detection across workflow-execute and workflow-multi-cli-plan skills.
- Introduced cycle workflows for integration testing and refactoring with self-iterating capabilities.
- Added detailed usage examples for new team workflows and collaborative planning commands.
- Updated QueueCard tests to use getAllByText for better resilience against multiple occurrences.
- Modified useCodexLens tests to check for error existence instead of specific message.
- Added mock for ResizeObserver in test setup to support components using it.
- Introduced integration tests for appStore and hooks interactions, covering locale and theme flows.
- Created layout-utils tests to validate pane manipulation functions.
- Added queryKeys tests to ensure correct key generation for workspace queries.
- Implemented utils tests for class name merging and memory metadata parsing.
