feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

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>

rag-service/embedding_client.py

@@ -1,6 +1,6 @@
 import logging
 import os
-from typing import Optional
+from dataclasses import dataclass
 
 import httpx
 
@@ -19,6 +19,14 @@ _OLLAMA_EMBED_MODEL = os.getenv("OLLAMA_EMBED_MODEL", "bge-m3")
 _EMBED_BATCH_SIZE = int(os.getenv("EMBED_BATCH_SIZE", "32"))
 
 
+@dataclass
+class ChunkResult:
+    """Result from the embedding service /chunk endpoint."""
+
+    chunks: list[str]
+    chunks_with_metadata: list[dict]
+
+
 class EmbeddingClient:
     """
     Hybrid client:
@@ -120,10 +128,10 @@ class EmbeddingClient:
         strategy: str = "recursive",
         chunk_size: int = 512,
         overlap: int = 50,
-    ) -> list[str]:
+    ) -> ChunkResult:
         """
         Ask the embedding service to chunk a long text.
-        Returns a list of chunk strings.
+        Returns ChunkResult with plain chunks and structural metadata.
         """
         async with httpx.AsyncClient(timeout=_TIMEOUT) as client:
             response = await client.post(
@@ -137,7 +145,10 @@ class EmbeddingClient:
             )
             response.raise_for_status()
             data = response.json()
-            return data.get("chunks", [])
+            return ChunkResult(
+                chunks=data.get("chunks", []),
+                chunks_with_metadata=data.get("chunks_with_metadata") or [],
+            )
 
     # ------------------------------------------------------------------
     # PDF extraction (via embedding-service)