GraphRAG Query-Time Explainability (#677)

Implements full explainability pipeline for GraphRAG queries, enabling
traceability from answers back to source documents.

Renamed throughout for clarity:
- provenance_callback → explain_callback
- provenance_id → explain_id
- provenance_collection → explain_collection
- message_type "provenance" → "explain"
- Queue name "provenance" → "explainability"

GraphRAG queries now emit explainability events as they execute:
1. Session - query text and timestamp
2. Retrieval - edges retrieved from subgraph
3. Selection - selected edges with LLM reasoning (JSONL with id +
   reasoning)
4. Answer - reference to synthesized response

Events stream via explain_callback during query(), enabling
real-time UX.

- Answers stored in librarian service (not inline in graph - too large)
- Document ID as URN: urn:trustgraph:answer:{session_id}
- Graph stores tg:document reference (IRI) to librarian document
- Added librarian producer/consumer to graph-rag service

- get_labelgraph() now returns (labeled_edges, uri_map)
- uri_map maps edge_id(label_s, label_p, label_o) →
  (uri_s, uri_p, uri_o)
- Explainability data stores original URIs, not labels
- Enables tracing edges back to reifying statements via tg:reifies

- Added serialize_triple() to query service (matches storage format)
- get_term_value() now handles TRIPLE type terms
- Enables querying by quoted triple in object position:
  ?stmt tg:reifies <<s p o>>

- Displays real-time explainability events during query
- Resolves rdfs:label for edge components (s, p, o)
- Traces source chain via prov:wasDerivedFrom to root document
- Output: "Source: Chunk 1 → Page 2 → Document Title"
- Label caching to avoid repeated queries

GraphRagResponse:
- explain_id: str | None
- explain_collection: str | None
- message_type: str ("chunk" or "explain")
- end_of_session: bool

trustgraph-base/trustgraph/provenance/:
- namespaces.py - Added TG_DOCUMENT predicate
- triples.py - answer_triples() supports document_id reference
- uris.py - Added edge_selection_uri()

trustgraph-base/trustgraph/schema/services/retrieval.py:
- GraphRagResponse with explain_id, explain_collection, end_of_session

trustgraph-flow/trustgraph/retrieval/graph_rag/:
- graph_rag.py - URI preservation, streaming answer accumulation
- rag.py - Librarian integration, real-time explain emission

trustgraph-flow/trustgraph/query/triples/cassandra/service.py:
- Quoted triple serialization for query matching

trustgraph-cli/trustgraph/cli/invoke_graph_rag.py:
- Full explainability display with label resolution and source tracing

tests/contract/test_translator_completion_flags.py

@@ -17,16 +17,18 @@ from trustgraph.messaging import TranslatorRegistry
 class TestRAGTranslatorCompletionFlags:
     """Contract tests for RAG response translator completion flags"""
 
-    def test_graph_rag_translator_is_final_with_end_of_stream_true(self):
+    def test_graph_rag_translator_is_final_with_end_of_session_true(self):
         """
         Test that GraphRagResponseTranslator returns is_final=True
-        when end_of_stream=True.
+        when end_of_session=True.
         """
         # Arrange
         translator = TranslatorRegistry.get_response_translator("graph-rag")
         response = GraphRagResponse(
             response="A small domesticated mammal.",
+            message_type="chunk",
             end_of_stream=True,
+            end_of_session=True,
             error=None
         )
 
@@ -34,20 +36,23 @@ class TestRAGTranslatorCompletionFlags:
         response_dict, is_final = translator.from_response_with_completion(response)
 
         # Assert
-        assert is_final is True, "is_final must be True when end_of_stream=True"
+        assert is_final is True, "is_final must be True when end_of_session=True"
         assert response_dict["response"] == "A small domesticated mammal."
-        assert response_dict["end_of_stream"] is True
+        assert response_dict["end_of_session"] is True
+        assert response_dict["message_type"] == "chunk"
 
-    def test_graph_rag_translator_is_final_with_end_of_stream_false(self):
+    def test_graph_rag_translator_is_final_with_end_of_session_false(self):
         """
         Test that GraphRagResponseTranslator returns is_final=False
-        when end_of_stream=False.
+        when end_of_session=False (even if end_of_stream=True).
         """
         # Arrange
         translator = TranslatorRegistry.get_response_translator("graph-rag")
         response = GraphRagResponse(
             response="Chunk 1",
+            message_type="chunk",
             end_of_stream=False,
+            end_of_session=False,
             error=None
         )
 
@@ -55,9 +60,55 @@ class TestRAGTranslatorCompletionFlags:
         response_dict, is_final = translator.from_response_with_completion(response)
 
         # Assert
-        assert is_final is False, "is_final must be False when end_of_stream=False"
+        assert is_final is False, "is_final must be False when end_of_session=False"
         assert response_dict["response"] == "Chunk 1"
-        assert response_dict["end_of_stream"] is False
+        assert response_dict["end_of_session"] is False
+
+    def test_graph_rag_translator_provenance_message(self):
+        """
+        Test that GraphRagResponseTranslator handles provenance messages.
+        """
+        # Arrange
+        translator = TranslatorRegistry.get_response_translator("graph-rag")
+        response = GraphRagResponse(
+            response="",
+            message_type="explain",
+            explain_id="urn:trustgraph:session:abc123",
+            end_of_stream=False,
+            end_of_session=False,
+            error=None
+        )
+
+        # Act
+        response_dict, is_final = translator.from_response_with_completion(response)
+
+        # Assert
+        assert is_final is False
+        assert response_dict["message_type"] == "explain"
+        assert response_dict["explain_id"] == "urn:trustgraph:session:abc123"
+
+    def test_graph_rag_translator_end_of_stream_not_final(self):
+        """
+        Test that end_of_stream=True alone does NOT make is_final=True.
+        The session continues with provenance messages after LLM stream completes.
+        """
+        # Arrange
+        translator = TranslatorRegistry.get_response_translator("graph-rag")
+        response = GraphRagResponse(
+            response="Final chunk",
+            message_type="chunk",
+            end_of_stream=True,
+            end_of_session=False,  # Session continues with provenance
+            error=None
+        )
+
+        # Act
+        response_dict, is_final = translator.from_response_with_completion(response)
+
+        # Assert
+        assert is_final is False, "end_of_stream=True should NOT make is_final=True"
+        assert response_dict["end_of_stream"] is True
+        assert response_dict["end_of_session"] is False
 
     def test_document_rag_translator_is_final_with_end_of_stream_true(self):
         """