- Add Rule 9 (Anti-Loop Guardrail) to 01-bigmind-core.md: detect 2+ identical
partial sessions and surface the loop to user instead of auto-resuming
- Add partial=history clause to Rule 1: partial/blocked/abandoned outcomes are
historical records only, never task queue items
- Add focus guard to memory_announce_focus: must reflect current user message,
not prior session outcome; use 'Awaiting user task assignment' if no task yet
- Add .roo/rules/06-anti-loop.md: global injection for ALL modes overriding
any mode-specific 'do the task immediately' behavior
- Add mode interaction safety clause to 00-identity.md: session ritual does not
authorize beginning any task — only explicit user message does
Root cause: pic-gen 'do the task' personality + BigMind context inference
produced 6 identical partial branding sessions in a loop.
- Fix syntax error in server.py (dangling docstring lines)
- Correct model filename: flux-2-klein-4b.safetensors (without -fp8)
- Fix _WORKFLOW_REGISTRY key to match actual downloaded filename
- Update get_models() to always include registry models as fallback
- Fix test expectations to match corrected model names
- All 37 tests passing
BUG-1: fix test_server_tools.py assert "ALWAYS" → "Always" (case mismatch)
BUG-2: export_memory() now includes hypotheses, upgrade_requests, token_saves,
people tables; renamed bigmind_version → bigmind_schema_version (int)
BUG-3: auto_close.py replaced CURRENT_TIMESTAMP (SQLite) with Python
datetime.now(timezone.utc).isoformat() for consistent UTC timestamps
PERF-1: context_builder.py caps get_facts() at _MAX_CONTEXT_FACTS=50 with
overflow hint to prevent unbounded context growth
All 297 tests passing. Upgrade requests #6-9 resolved.
Health report: plans/BIGMIND_HEALTH_REPORT_2026-04-04.md
Patrick Plate