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.

trustgraph-base/trustgraph/clients/agent_client.py

@@ -58,23 +58,23 @@ class AgentClient(BaseClient):
 
         def inspect(x):
             # Handle errors
-            if x.chunk_type == 'error' or x.error:
+            if x.message_type == 'error' or x.error:
                 if error_callback:
                     error_callback(x.content or (x.error.message if x.error else ""))
                 # Continue to check end_of_dialog
 
             # Handle thought chunks
-            elif x.chunk_type == 'thought':
+            elif x.message_type == 'thought':
                 if think:
                     think(x.content, x.end_of_message)
 
             # Handle observation chunks
-            elif x.chunk_type == 'observation':
+            elif x.message_type == 'observation':
                 if observe:
                     observe(x.content, x.end_of_message)
 
             # Handle answer chunks
-            elif x.chunk_type == 'answer':
+            elif x.message_type == 'answer':
                 if x.content:
                     accumulated_answer.append(x.content)
                 if answer_callback: