Add concurrent agent limiting to kugetsu CLI

- 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

tools/parallel-capacity-test/results/report_20260331_035130.md

@@ -0,0 +1,29 @@
+# Parallel Capacity Test Report
+
+**Generated:** 2026-03-31 03:51:30
+
+## Summary
+
+| Agents | Duration | Success | Failed | Timeout | Avg Response | Peak Mem (MB) | Mem/Agent | Cost Score |
+|--------|----------|---------|--------|---------|--------------|---------------|-----------|------------|
+| 1 | 1.0s | 0 | 1 | 0 | 0.0s | 2177MB | -0.0MB | 0.00 |
+| 2 | 1.0s | 0 | 2 | 0 | 0.0s | 2176MB | 0.3MB | 0.00 |
+| 3 | 1.0s | 0 | 3 | 0 | 0.0s | 2175MB | 0.1MB | 0.00 |
+| 5 | 1.0s | 0 | 5 | 0 | 0.0s | 2175MB | 0.0MB | 0.00 |
+| 8 | 1.0s | 0 | 8 | 0 | 0.0s | 2176MB | 0.2MB | 0.00 |
+
+## Cost Analysis
+
+| Metric | Value |
+|--------|-------|
+| Baseline Memory | 2177.1 MB |
+| Avg Memory per Agent | 0.1 MB |
+| Memory Limit | 1024 MB |
+| Estimated Max Capacity | 9729 agents |
+
+## Key Findings
+
+## Recommendations
+
+2. **Monitor closely:** 5+ agents
+3. **Implement circuit breaker** when failure rate exceeds threshold