Add agent explainability instrumentation and unify envelope field naming (#795)

Addresses recommendations from the UX developer's agent experience report.
Adds provenance predicates, DAG structure changes, error resilience, and
a published OWL ontology.

Explainability additions:

- Tool candidates: tg:toolCandidate on Analysis events lists the tools
  visible to the LLM for each iteration (names only, descriptions in config)
- Termination reason: tg:terminationReason on Conclusion/Synthesis events
  (final-answer, plan-complete, subagents-complete)
- Step counter: tg:stepNumber on iteration events
- Pattern decision: new tg:PatternDecision entity in the DAG between
  session and first iteration, carrying tg:pattern and tg:taskType
- Latency: tg:llmDurationMs on Analysis events, tg:toolDurationMs on
  Observation events
- Token counts on events: tg:inToken/tg:outToken/tg:llmModel on
  Grounding, Focus, Synthesis, and Analysis events
- Tool/parse errors: tg:toolError on Observation events with tg:Error
  mixin type. Parse failures return as error observations instead of
  crashing the agent, giving it a chance to retry.

Envelope unification:

- Rename chunk_type to message_type across AgentResponse schema,
  translator, SDK types, socket clients, CLI, and all tests.
  Agent and RAG services now both use message_type on the wire.

Ontology:

- specs/ontology/trustgraph.ttl — OWL vocabulary covering all 26 classes,
  7 object properties, and 36+ datatype properties including new predicates.

DAG structure tests:

- tests/unit/test_provenance/test_dag_structure.py verifies the
  wasDerivedFrom chain for GraphRAG, DocumentRAG, and all three agent
  patterns (react, plan, supervisor) including the pattern-decision link.

tests/integration/conftest.py

@@ -418,55 +418,55 @@ def sample_streaming_agent_response():
     """Sample streaming agent response chunks"""
     return [
         {
-            "chunk_type": "thought",
+            "message_type": "thought",
             "content": "I need to search",
             "end_of_message": False,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "thought",
+            "message_type": "thought",
             "content": " for information",
             "end_of_message": False,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "thought",
+            "message_type": "thought",
             "content": " about machine learning.",
             "end_of_message": True,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "action",
+            "message_type": "action",
             "content": "knowledge_query",
             "end_of_message": True,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "observation",
+            "message_type": "observation",
             "content": "Machine learning is",
             "end_of_message": False,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "observation",
+            "message_type": "observation",
             "content": " a subset of AI.",
             "end_of_message": True,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "final-answer",
+            "message_type": "final-answer",
             "content": "Machine learning",
             "end_of_message": False,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "final-answer",
+            "message_type": "final-answer",
             "content": " is a subset",
             "end_of_message": False,
             "end_of_dialog": False
         },
         {
-            "chunk_type": "final-answer",
+            "message_type": "final-answer",
             "content": " of artificial intelligence.",
             "end_of_message": True,
             "end_of_dialog": True
@@ -494,10 +494,10 @@ def streaming_chunk_collector():
             """Concatenate all chunk content"""
             return "".join(self.chunks)
 
-        def get_chunk_types(self):
+        def get_message_types(self):
             """Get list of chunk types if chunks are dicts"""
             if self.chunks and isinstance(self.chunks[0], dict):
-                return [c.get("chunk_type") for c in self.chunks]
+                return [c.get("message_type") for c in self.chunks]
             return []
 
         def verify_streaming_protocol(self):