- Add MAX_CONCURRENT_AGENTS (default: 3) to limit concurrent agents
- Implement acquire_agent_slot() and release_agent_slot() with flock
- Wrap cmd_start, cmd_continue, and cmd_delegate with slot management
- cmd_delegate holds slot until background task completes (fire-and-forget + blocking)
- Add basic concurrency tests to test suite
This tool tests the practical limits of parallel agent execution
by spawning N concurrent opencode run tasks and measuring:
- Response time
- CPU and memory usage
- Success/failure rates
Includes both bash (run_test.sh) and Python (parallel_capacity_test.py)
implementations with full metrics collection and reporting.
Fixes#3