- Fix automation-tracking.md to use new pool supervisor names
- Update session_state.md to reference implementation-pool-supervisor
- Fix pr-status-analyzer.md to reference pr-ci-test-fixer
- Fix implementation-pool-supervisor references to '32 workers'
- Remove hardcoded comment about '10 for this session'
- Update remaining old agent name references in tracking files
- Ensure all pool supervisors reference CA_MAX_PARALLEL_WORKERS env var
- Remove maximum cap (16) on CA_MAX_PARALLEL_WORKERS in resources.yaml
- Can now be set to any positive value (32, 64, etc.)
- Only minimum validation remains (must be > 0)
- Remove dynamic backpressure/throttling from implementation-orchestrator
- Dispatch always runs at full configured speed
- Resource monitoring remains for visibility only
- No automatic reduction of slots_available based on failures
- Convert system-watchdog from auto-degradation to monitoring + suggestions
- Renamed DEGRADATION_THRESHOLDS to HEALTH_THRESHOLDS
- Removed apply_system_degradation() and check_degradation_recovery()
- Changed findings to include suggestions instead of actions
- Watchdog now reports issues with fix recommendations
- No automatic throttling or pausing of agents
The system now operates at maximum configured speed at all times,
with the watchdog providing diagnostic insights when issues arise.
clever-agent
freemo