Benjamin Admin
42ab5ead26
feat(pipeline): implement Control Dependency Engine (Block 9)
...
Core engine (dependency_engine.py):
- 5 dependency types: prerequisite, supersedes, compensating_control,
conditional_requirement, scope_exclusion
- Generic condition evaluator (JSONB rules with AND/OR/NOT/field ops)
- Priority-based conflict resolution
- Cycle detection (DFS) + topological sort
- Full evaluation with MCP-compatible dependency_resolution trace
- 39 tests all passing (incl. GHV scenario from user requirements)
Automatic generator (dependency_generator.py):
- Ontology-based: same normalized_object + phase sequence -> prerequisite
- Pattern-based: define->implement, implement->monitor, etc.
- Domain packs: YAML rules for GDPR, AI Act, CRA, Security, Labor Contracts
- 14 tests all passing
API routes (dependency_routes.py):
- CRUD for dependencies
- POST /evaluate with dependency resolution
- POST /generate (auto-generation with dry_run)
- POST /validate (cycle detection)
- GET /graph (nodes + edges for visualization)
Prompt enhancement (decomposition_pass.py):
- Added dependency_hints + lifecycle_phase_order to Pass 0b prompt
- Stored in generation_metadata for post-processing
DB migration: control_dependencies + control_evaluation_results tables
126 tests total, all passing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-26 20:28:10 +02:00
Benjamin Admin
e3ab428b91
feat: control-pipeline Service aus Compliance-Repo migriert
...
Control-Pipeline (Pass 0a/0b, BatchDedup, Generator) als eigenstaendiger
Service in Core, damit Compliance-Repo unabhaengig refakturiert werden kann.
Schreibt weiterhin ins compliance-Schema der shared PostgreSQL.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-09 14:40:47 +02:00
