M41: harden trust boundaries and delivery

backend/app/services/knowledge/ragcore.py

@@ -92,6 +92,17 @@ def _rank_sources_for_concepts(sources: list[SourceCard], concepts: set[str]) ->
     )
 
 
+def _retrieval_score(result: dict) -> float | None:
+    scores = result.get("scores")
+    if not isinstance(scores, dict):
+        return None
+    for name in ("rerank", "fused"):
+        value = scores.get(name)
+        if isinstance(value, int | float) and not isinstance(value, bool):
+            return float(value)
+    return None
+
+
 class RAGcoreKnowledgeProvider:
     """Adapter for the central RAGcore service, against its real `/v1/*` contract
     (see `docs/contracts/openapi.yaml` in the RAGcore checkout -- RAGcore is built and
@@ -338,6 +349,8 @@ class RAGcoreKnowledgeProvider:
 
         try:
             results = body.get("results", [])
+            if not isinstance(results, list):
+                raise TypeError("results must be a list")
             sources = [
                 SourceCard(
                     document_id=str(result["citation"]["document_id"]),
@@ -351,10 +364,21 @@ class RAGcoreKnowledgeProvider:
         except (TypeError, KeyError, ValueError):
             return unavailable
 
-        sources = _deduplicate_sources(sources)
+        all_sources = _deduplicate_sources(sources)
         concepts = _question_concepts(question)
-        sources = _rank_sources_for_concepts(sources, concepts)
-        if not sources:
+        qualified_sources = [
+            SourceCard(
+                document_id=str(result["citation"]["document_id"]),
+                title=result["citation"]["title"],
+                version=str(result["citation"]["document_version_id"]),
+                section=result["citation"].get("section") or "",
+                excerpt=result["citation"]["excerpt"],
+            )
+            for result in results
+            if (_retrieval_score(result) or 0.0) >= self._settings.ragcore_min_search_score
+        ]
+        sources = _rank_sources_for_concepts(_deduplicate_sources(qualified_sources), concepts)
+        if not all_sources:
             return GroundedAnswer(
                 answer="",
                 evidence_state="insufficient",
@@ -363,11 +387,19 @@ class RAGcoreKnowledgeProvider:
                 correlation_id=correlation_id,
             )
 
-        if not concepts:
+        damage_evidence = any(
+            term
+            in (
+                f"{source.document_id} {source.title} {source.section} {source.excerpt}"
+            ).casefold()
+            for source in sources
+            for term in _DOMAIN_CONCEPTS["damage"]
+        )
+        if not concepts or not sources or ("damage" in concepts and not damage_evidence):
             return GroundedAnswer(
                 answer="",
                 evidence_state="insufficient",
-                sources=sources,
+                sources=all_sources,
                 provider=self.name,
                 correlation_id=correlation_id,
             )