- Fixed issue where agents were adding future cycle comments to old tracking issues
- Updated 12 agent definitions to use automation-tracking-manager subagent
- Removed custom tracking functions from all agents
- Ensures one tracking issue per cycle with proper cleanup
- Added helper scripts for tracking system updates
- Created comprehensive update summary documentation
This prevents agents from incorrectly reporting multiple cycles on the same
tracking issue and ensures consistent tracking behavior across all agents.
- 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.
freemo