M10: harden knowledge trust and telemetry

backend/app/services/knowledge/ragcore.py

@@ -21,6 +21,54 @@ _LEAD_ANSWER_TEMPLATE = {
 }
 _DEFAULT_LANGUAGE = "en-GB"
 
+_DOMAIN_CONCEPTS: dict[str, tuple[str, ...]] = {
+    "damage": ("damage", "damaged", "schade", "beschadigd", "dommage", "endommagé"),
+    "vehicle": ("vehicle", "car", "voertuig", "wagen", "véhicule", "voiture"),
+    "return": ("return", "returned", "retour", "terugbrengen", "restitution"),
+    "fuel": ("fuel", "brandstof", "carburant"),
+    "booking": ("booking", "reservation", "boeking", "réservation"),
+    "odometer": ("odometer", "mileage", "kilometer", "kilométrage", "compteur"),
+    "customer": ("customer", "client", "klant"),
+    "cleaning": ("cleaning", "reiniging", "poetsen", "nettoyage"),
+    "maintenance": ("maintenance", "service", "onderhoud", "entretien"),
+    "conflict": ("conflict", "overlap", "overlapping", "conflit", "chevauchement"),
+    "checkout": ("checkout", "departure", "vertrek", "départ"),
+    "availability": ("available", "availability", "beschikbaar", "disponible", "disponibilité"),
+    "technical": ("technical", "warning", "technisch", "waarschuwing", "technique", "alerte"),
+}
+
+
+def _question_concepts(question: str) -> set[str]:
+    normalized = question.casefold()
+    return {
+        concept
+        for concept, terms in _DOMAIN_CONCEPTS.items()
+        if any(term in normalized for term in terms)
+    }
+
+
+def _deduplicate_sources(sources: list[SourceCard]) -> list[SourceCard]:
+    seen: set[tuple[str, str]] = set()
+    unique: list[SourceCard] = []
+    for source in sources:
+        key = (source.document_id, source.section)
+        if key in seen:
+            continue
+        seen.add(key)
+        unique.append(source)
+    return unique
+
+
+def _rank_sources_for_concepts(sources: list[SourceCard], concepts: set[str]) -> list[SourceCard]:
+    if "damage" not in concepts:
+        return sources
+    return sorted(
+        sources,
+        key=lambda source: (
+            0 if "damage" in f"{source.document_id} {source.title}".casefold() else 1
+        ),
+    )
+
 
 class RAGcoreKnowledgeProvider:
     """Adapter for the central RAGcore service, against its real `/v1/*` contract
@@ -199,6 +247,9 @@ class RAGcoreKnowledgeProvider:
         except (TypeError, KeyError, ValueError):
             return unavailable
 
+        sources = _deduplicate_sources(sources)
+        concepts = _question_concepts(question)
+        sources = _rank_sources_for_concepts(sources, concepts)
         if not sources:
             return GroundedAnswer(
                 answer="",
@@ -208,6 +259,15 @@ class RAGcoreKnowledgeProvider:
                 correlation_id=correlation_id,
             )
 
+        if not concepts:
+            return GroundedAnswer(
+                answer="",
+                evidence_state="insufficient",
+                sources=sources,
+                provider=self.name,
+                correlation_id=correlation_id,
+            )
+
         template = _LEAD_ANSWER_TEMPLATE.get(language, _LEAD_ANSWER_TEMPLATE[_DEFAULT_LANGUAGE])
         lead = sources[0]
         answer = template.format(title=lead.title, excerpt=lead.excerpt)