feat(benchmarking): add model-scoped query and neighbor expansion

Why:
- Queries and Experiments must hit the Corpus Embedding Model's collections and optionally widen fixed_size context.

Changes:
- Resolve corpus model per request; apply Neighbor Expansion with Expansion Tree; persist and report expansion provenance.

Co-authored-by: Cursor <cursoragent@cursor.com>

src/benchmarking/routes.py

@@ -42,6 +42,9 @@ async def create_query(request: QueryRequest):
         strategy_name=request.strategy,
         question=request.question,
         top_k=request.top_k,
+        neighbor_prev=request.neighbor_prev,
+        neighbor_next=request.neighbor_next,
+        corpus_model_id=request.corpus_model_id,
     )
 
     return QueryResponse(
@@ -53,6 +56,9 @@ async def create_query(request: QueryRequest):
         retrieved_chunks=[
             RetrievedChunk(**chunk) for chunk in result["retrieved_chunks"]
         ],
+        expansion_tree=result.get("expansion_tree") or [],
+        neighbor_prev=result.get("neighbor_prev", 0),
+        neighbor_next=result.get("neighbor_next", 0),
         latency_breakdown=result["latency_breakdown"],
         token_usage=result["token_usage"],
         created_at=result["created_at"],
@@ -73,6 +79,7 @@ async def get_query(query_id: str):
         question=result["question"],
         answer=result["answer"],
         retrieved_chunks=result["retrieved_chunks"],
+        expansion_tree=result.get("expansion_tree") or [],
         latency_breakdown=result["latency_breakdown"],
         token_usage=result["token_usage"],
         created_at=result["created_at"],
@@ -130,6 +137,9 @@ async def create_benchmark(request: BenchmarkRequest):
         strategies=request.strategies,
         questions=questions,
         top_k=request.top_k,
+        neighbor_prev=request.neighbor_prev,
+        neighbor_next=request.neighbor_next,
+        corpus_model_id=request.corpus_model_id,
     )
 
     return BenchmarkResponse(
@@ -183,6 +193,11 @@ async def list_experiments(document_id: str | None = None):
     for item in result.get("items", []):
         doc = db.get_document(item.get("document_id", ""))
         item["document_filename"] = doc.get("filename", "Unknown") if doc else "Deleted"
+        questions = item.get("questions") or []
+        item["questions_count"] = (
+            item.get("benchmark_config", {}).get("num_questions")
+            or (len(questions) if isinstance(questions, list) else 0)
+        )
         # Calculate best_strategy from aggregate_metrics
         aggs = item.get("aggregate_metrics", {})
         best_strat, best_score = "N/A", -1
@@ -195,6 +210,11 @@ async def list_experiments(document_id: str | None = None):
                 best_score = adjusted
                 best_strat = strat
         item["best_strategy"] = best_strat
+        # Surface embedding on list even if only in benchmark_config
+        if not item.get("embedding_model_id"):
+            cfg = item.get("benchmark_config") or {}
+            item["embedding_model_id"] = cfg.get("embedding_model_id")
+            item["embedding_provider"] = cfg.get("embedding_provider")
     return result