D2: RAG service stores section/section_title/paragraph/paragraph_num/page
from embedding service chunks_with_metadata into Qdrant payloads.
D3: Control generator prefers section > article > section_title from
Qdrant, adds page to source_citation and generation_metadata.
D4: Validated with real BGB §§ 312-312k text. Found and fixed critical
bug where Phase 3 overlap destroyed the [§ ...] section prefix, causing
only the first chunk per document to have metadata. All subsequent
chunks lost section info.
Also fixes pre-existing lint issues (unused imports, ambiguous variable
names, duplicate dict key, bare except).
456 tests passing (58 embedding + 387 pipeline + 11 rag-service).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace plain recursive chunker with legal-aware chunking that:
- Detects legal section headers (§, Art., Section, Chapter, Annex)
- Adds section context prefix to every chunk
- Splits on paragraph boundaries then sentence boundaries
- Protects DE + EN abbreviations (80+ patterns) from false splits
- Supports language detection for locale-specific processing
- Force-splits overlong sentences at word boundaries
The old plain_recursive API option is removed — all non-semantic
strategies now route through chunk_text_legal().
Includes 40 tests covering header detection, abbreviation protection,
sentence splitting, and legal chunking behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Benjamin Admin