ADR-001: Ron Guardian Operates in Detective Mode¶
Status¶
ACCEPTED - 2026-01-22
Context¶
During Foundation Audit 17 (Ron Enforcement), we discovered that Ron Guardian validates 10+ patterns but operates in detective mode (post-execution) rather than preventive mode (pre-execution).
Current Behavior: - Ron monitors agent sessions AFTER they complete - Validates: HALT integrity, file hashes, boundaries, dangerous patterns, team violations - Creates notifications and alerts when violations detected - Cannot PREVENT violations, only DETECT them
The Question: Should Ron be redesigned to block violations before they occur?
Decision¶
We accept detective mode for the current phase.
Ron will continue to operate post-facto, detecting and reporting violations rather than preventing them.
Rationale¶
Arguments FOR Detective Mode (Current)¶
- Simplicity: No latency added to agent execution path
- No false positives blocking work: Agents can proceed, violations caught and fixed
- Learning opportunity: Violations provide data for improving agent instructions
- Low violation rate expected: Well-designed agent identities should rarely violate
- Human review available: Dirk-Jan reviews violations and applies fixes
- Enterprise-grade later: Can add preventive layer when evidence shows need
Arguments AGAINST (Rejected for now)¶
- Violations occur before detection: Damage may be done
- Rollback complexity: May need to undo agent work
- Security posture: Preventive is theoretically stronger
Why Detective Mode is Acceptable¶
- Agent count is low (7 active currently)
- No critical violations observed in testing
- Human-in-the-loop catches issues quickly
- Tiered identity system provides guardrails at instruction level
- Complexity cost of preventive mode not justified yet
Consequences¶
Positive¶
- Simpler architecture
- No execution latency
- Violations become learning data
- Can upgrade later with evidence
Negative¶
- Violations not prevented, only detected
- Potential for brief periods of non-compliance
- Requires human vigilance on notifications
Mitigation¶
- Ron runs integrity sweeps every 10 seconds (spot checks)
- Full sweep every hour
- File-based notifications for immediate visibility
- Redis metrics for tracking violation counts
- Escalation to HALT if critical patterns detected
Review Trigger¶
Re-evaluate this decision when: - Violation count exceeds 5 per week - Critical violation occurs that causes data loss or security breach - Agent count exceeds 20 active concurrent - Client work begins (higher stakes)
Related¶
- Audit 17: Ron Enforcement (17-ron-enforcement-20260121-2354.md)
- Foundation Report (22-foundation-report-20260122-1132.md)
Decision Made By: Dirk-Jan Huizingh (CEO) Documented By: Foundation Audit Process Date: 2026-01-22