- Update MockAgentManager tests to use status-based scenarios
- Change outcome:'crash' to status:'unrecoverable_error' with error field
- Change outcome:'waiting_for_input' to status:'question' with question field
- Change outcome:'success' to status:'done' with result field
- Add tests for structured question data (options, multiSelect)
- Add tests for getPendingQuestion and resume clearing pending question
- Update E2E edge-cases tests with new scenario format
- Update harness tests with new scenario format
- Change MockAgentScenario from outcome-based to status-based discriminated union
- Align with agent output schema: done/question/unrecoverable_error
- Update completeAgent() to handle new status types
- Update resume() to use new scenario format
- Pass --json-schema flag to Claude CLI for validated output
- Parse discriminated union (done/question/unrecoverable_error) in handleAgentCompletion
- Add getPendingQuestion method to AgentManager interface
- Add PendingQuestion type for structured question data
- Store pending question in ActiveAgent for later retrieval
- Remove hacky string matching for waiting_for_input detection
- Update MockAgentManager with getPendingQuestion and options support
- Update tests for new CLI arguments and result format
- Discriminated union with done/question/unrecoverable_error status
- Options schema for structured question choices
- JSON schema export for Claude CLI --json-schema flag
- Type export for runtime validation
- Test spawn with worktree and agent record creation
- Test duplicate name rejection
- Test AgentSpawned event emission
- Test stop with subprocess kill and status update
- Test list, get, getByName operations
- Test resume with session_id and --resume flag
- Test AgentResumed event emission
- Fix: use agent.id from repository for activeAgents tracking
- Use Claude CLI with --output-format json for agent spawning
- Extract session_id from JSON result for resume capability
- Emit lifecycle events: spawned, stopped, crashed, resumed, waiting
- Handle waiting_for_input status for AskUserQuestion pauses
- Uses WorktreeManager for isolated agent workspaces
- AgentStatus type for agent lifecycle states
- SpawnAgentOptions for spawn configuration
- AgentInfo for agent state representation
- AgentResult for execution results
- AgentManager interface with spawn, stop, list, get, getByName, resume, getResult