conflict-detector

> **AI-consumed reference.** Optimized for Claude to read during execution. > Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md) > or [docs/getting-started/](../../../docs/getting-started/) depending on topic. # Conflict Detector **STATUS — v3.7.0-beta.2.** L1+L2 functional; L3+L4 stubbed pending LLM-dispatch infrastructure in rc.1. ## Five conflict types (per spec §21.1) ```toon types[5]{type,definition,detection_layer,cost}: C1,File-level overlap,L1,free C2,Function/region overlap,L2,cheap (~10ms regex) C3,Schema/contract conflict,L2,cheap C4,Semantic intent conflict,L3,LLM (stubbed in beta.2) C5,Architectural conflict,L4,LLM-rare (stubbed in beta.2) ``` ## Layer dispatch (per spec §21.3) ``` ON dispatch_request(task): L1 = check-l1-files.sh ← always run, free IF L1.overlap AND L1.confidence >= 0.95: RETURN conflict(L1) IF L1.overlap (low confidence): L2 = check-l2-syntactic.sh ← drill into overlapping files IF L2.overlap: RETURN conflict(L2) IF task.tier <= 2 OR task.creates_new_pattern: L4 = check-architectural (LLM, stubbed) ← skipped in beta.2 IF L4.contradicts: RETURN conflict(L4) IF task.parent has any pending-confirm sibling: L3 = check-semantic (LLM, stubbed) ← skipped in beta.2 IF L3.contradicts: RETURN conflict(L3) RETURN clear ``` ## Disable Set `AF_CONFLICT_LLM_DISABLED=tru...