Deliver explainability triples inline in retrieval response stream (#763)

Provenance triples are now included directly in explain messages from
GraphRAG, DocumentRAG, and Agent services, eliminating the need for
follow-up knowledge graph queries to retrieve explainability details.

Each explain message in the response stream now carries:
- explain_id: root URI for this provenance step (unchanged)
- explain_graph: named graph where triples are stored (unchanged)
- explain_triples: the actual provenance triples for this step (new)

Changes across the stack:
- Schema: added explain_triples field to GraphRagResponse,
  DocumentRagResponse, and AgentResponse
- Services: all explain message call sites pass triples through
  (graph_rag, document_rag, agent react, agent orchestrator)
- Translators: encode explain_triples via TripleTranslator for
  gateway wire format
- Python SDK: ProvenanceEvent now includes parsed ExplainEntity
  and raw triples; expanded event_type detection
- CLI: invoke_graph_rag, invoke_agent, invoke_document_rag use
  inline entity when available, fall back to graph query
- Tech specs updated

Additional explainability test

trustgraph-base/trustgraph/schema/services/agent.py

@@ -2,7 +2,7 @@
 from dataclasses import dataclass, field
 from typing import Optional
 
-from ..core.primitives import Error
+from ..core.primitives import Error, Triple
 
 ############################################################################
 
@@ -57,8 +57,9 @@ class AgentResponse:
     end_of_dialog: bool = False    # Entire agent dialog is complete
 
     # Explainability fields
-    explain_id: str | None = None     # Provenance URI (announced as created)
-    explain_graph: str | None = None  # Named graph where explain was stored
+    explain_id: str | None = None     # Root URI for this explain step
+    explain_graph: str | None = None  # Named graph (e.g., urn:graph:retrieval)
+    explain_triples: list[Triple] = field(default_factory=list)  # Provenance triples for this step
 
     # Orchestration fields
     message_id: str = ""              # Unique ID for this response message

trustgraph-base/trustgraph/schema/services/retrieval.py

@@ -1,5 +1,5 @@
-from dataclasses import dataclass
-from ..core.primitives import Error, Term
+from dataclasses import dataclass, field
+from ..core.primitives import Error, Term, Triple
 
 ############################################################################
 
@@ -24,8 +24,9 @@ class GraphRagResponse:
     error: Error | None = None
     response: str = ""
     end_of_stream: bool = False       # LLM response stream complete
-    explain_id: str | None = None     # Single explain URI (announced as created)
-    explain_graph: str | None = None  # Named graph where explain was stored (e.g., urn:graph:retrieval)
+    explain_id: str | None = None     # Root URI for this explain step
+    explain_graph: str | None = None  # Named graph (e.g., urn:graph:retrieval)
+    explain_triples: list[Triple] = field(default_factory=list)  # Provenance triples for this step
     message_type: str = ""            # "chunk" or "explain"
     end_of_session: bool = False      # Entire session complete
 
@@ -46,7 +47,8 @@ class DocumentRagResponse:
     error: Error | None = None
     response: str | None = ""
     end_of_stream: bool = False       # LLM response stream complete
-    explain_id: str | None = None     # Single explain URI (announced as created)
-    explain_graph: str | None = None  # Named graph where explain was stored (e.g., urn:graph:retrieval)
+    explain_id: str | None = None     # Root URI for this explain step
+    explain_graph: str | None = None  # Named graph (e.g., urn:graph:retrieval)
+    explain_triples: list[Triple] = field(default_factory=list)  # Provenance triples for this step
     message_type: str = ""            # "chunk" or "explain"
     end_of_session: bool = False      # Entire session complete