Benjamin Admin b151951448 fix(pipeline): make dedup Phase 2 resilient — paginated, timeout, per-control error handling ...

- Paginated DB queries (100 rows/page) instead of loading all 166k rows
- Individual timeout (30s) per embedding + qdrant call
- Per-control try/except — one failure doesn't kill the job
- Sequential processing (no asyncio.gather) for stability
- Progress logging every 500 controls

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-28 15:31:28 +02:00

..

__init__.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

anchor_finder.py

fix(anchor-finder): use correct Qdrant payload fields (regulation_id, regulation_name_de)

2026-04-21 18:17:36 +02:00

applicability_engine.py

feat(control-pipeline): add Assessment Layer to Applicability Engine

2026-04-23 20:36:11 +02:00

batch_dedup_runner.py

fix(pipeline): make dedup Phase 2 resilient — paginated, timeout, per-control error handling

2026-04-28 15:31:28 +02:00

citation_backfill.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

control_composer.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

control_dedup.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

control_generator.py

feat(control-pipeline): replace similarity-only dedup with LLM-verified dedup in pipeline

2026-04-23 16:57:37 +02:00

control_ontology.py

feat(pipeline): implement Control Dependency Engine (Block 9)

2026-04-26 20:28:10 +02:00

control_status_machine.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

decomposition_pass.py

perf(pipeline): switch back to v4 prompt — backfill costs nearly the same

2026-04-27 00:44:23 +02:00

dependency_engine.py

feat(pipeline): implement Control Dependency Engine (Block 9)

2026-04-26 20:28:10 +02:00

dependency_generator.py

fix(pipeline): use action_type-derived phase order in ontology generator

2026-04-26 20:32:58 +02:00

document_scope_resolver.py

feat(control-pipeline): add Document Compliance Engine — scope detection + document requirements

2026-04-24 08:39:55 +02:00

framework_decomposition.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

license_gate.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

llm_provider.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

normative_patterns.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

obligation_extractor.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

pattern_matcher.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

pipeline_adapter.py

feat(control-pipeline): JSONB migration for generation_metadata

2026-04-22 07:49:11 +02:00

rag_client.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

reranker.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

similarity_detector.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00

v1_enrichment.py

feat: control-pipeline Service aus Compliance-Repo migriert

2026-04-09 14:40:47 +02:00