- Refactor reviewPass function to identify states with review checks instead of specific review types.
- Introduce review policies (HUMAN, AGENT, AUTO) to control PR review processes based on developer levels.
- Update projectTick to handle review policies and step routing labels for reviewers and testers.
- Add detailed reviewer instructions to templates for clarity on review responsibilities.
- Implement role:level label management, allowing dynamic creation of labels based on project configuration.
- Enhance task_update tool to support state and level updates, ensuring at least one parameter is provided.
- Update work_finish tool to include reviewer actions (approve, reject) in task completion.
- Modify work_start tool to utilize role-level detection for better level assignment.
- Add tests for new functionalities, including review routing and level detection from labels.
- Introduced ExecutionMode type for project execution modes (parallel, sequential).
- Updated SetupOpts to use ExecutionMode instead of string literals.
- Enhanced workflow states to include a new "In Review" state with appropriate transitions.
- Implemented TestHarness for end-to-end testing, including command interception and workspace setup.
- Created TestProvider for in-memory issue tracking during tests.
- Refactored project registration and setup tools to utilize ExecutionMode.
- Updated various tools to ensure compatibility with new workflow and execution modes.
- Added new dependencies: cockatiel for resilience and zod for schema validation.
Adds test file with validation scenarios:
- Schema validation for required/optional params
- All 8 state labels are supported
- Same-state transitions handled gracefully
- Audit logging verification
Includes manual test scenarios for integration verification.
Addresses issue #71 acceptance criteria:
✅ Can transition any issue to any valid state
✅ Logs reason to audit trail
✅ Updates GitHub label (projects.json managed by session_health)
✅ Documented as orchestrator-only in AGENTS.md
