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.

dev-tools/tests/agent_dag/analyse_trace.py

@@ -131,21 +131,21 @@ async def analyse(path, url, flow, user, collection):
 
     for i, msg in enumerate(messages):
         resp = msg.get("response", {})
-        chunk_type = resp.get("chunk_type", "?")
+        message_type = resp.get("message_type", "?")
 
-        if chunk_type == "explain":
+        if message_type == "explain":
             explain_id = resp.get("explain_id", "")
             explain_ids.append(explain_id)
-            print(f"  {i:3d}  {chunk_type}  {explain_id}")
+            print(f"  {i:3d}  {message_type}  {explain_id}")
         else:
-            print(f"  {i:3d}  {chunk_type}")
+            print(f"  {i:3d}  {message_type}")
 
         # Rule 7: message_id on content chunks
-        if chunk_type in ("thought", "observation", "answer"):
+        if message_type in ("thought", "observation", "answer"):
             mid = resp.get("message_id", "")
             if not mid:
                 errors.append(
-                    f"[msg {i}] {chunk_type} chunk missing message_id"
+                    f"[msg {i}] {message_type} chunk missing message_id"
                 )
 
     print()