Split Analysis into Analysis+ToolUse and Observation, add message_id

Refactor agent provenance so that the decision (thought + tool
selection) and the result (observation) are separate DAG entities:

  Question ← Analysis+ToolUse ← Observation ← ... ← Conclusion

Analysis gains tg:ToolUse as a mixin RDF type and is emitted
before tool execution via an on_action callback in react().
This ensures sub-traces (e.g. GraphRAG) appear after their
parent Analysis in the streaming event order.

Observation becomes a standalone prov:Entity with tg:Observation
type, emitted after tool execution. The linear DAG chain runs
through Observation — subsequent iterations and the Conclusion
derive from it, not from the Analysis.

message_id is populated on streaming AgentResponse for thought
and observation chunks, using the provenance URI of the entity
being built. This lets clients group streamed chunks by entity.

Wire changes:
- provenance/agent.py: Add ToolUse type, new
  agent_observation_triples(), remove observation from iteration
- agent_manager.py: Add on_action callback between reason() and
  tool execution
- orchestrator/pattern_base.py: Split emit, wire message_id,
  chain through observation URIs
- orchestrator/react_pattern.py: Emit Analysis via on_action
  before tool runs
- agent/react/service.py: Same for non-orchestrator path
- api/explainability.py: New Observation class, updated dispatch
  and chain walker
- api/types.py: Add message_id to AgentThought/AgentObservation
- cli: Render Observation separately, [analysis: tool] labels

tests/unit/test_provenance/test_triples.py

@@ -500,7 +500,7 @@ class TestQuestionTriples:
 
     def test_question_types(self):
         triples = question_triples(self.Q_URI, "What is AI?", "2024-01-01T00:00:00Z")
-        assert has_type(triples, self.Q_URI, PROV_ACTIVITY)
+        assert has_type(triples, self.Q_URI, PROV_ENTITY)
         assert has_type(triples, self.Q_URI, TG_QUESTION)
         assert has_type(triples, self.Q_URI, TG_GRAPH_RAG_QUESTION)
 
@@ -543,11 +543,11 @@ class TestGroundingTriples:
         assert has_type(triples, self.GND_URI, PROV_ENTITY)
         assert has_type(triples, self.GND_URI, TG_GROUNDING)
 
-    def test_grounding_generated_by_question(self):
+    def test_grounding_derived_from_question(self):
         triples = grounding_triples(self.GND_URI, self.Q_URI, ["AI"])
-        gen = find_triple(triples, PROV_WAS_GENERATED_BY, self.GND_URI)
-        assert gen is not None
-        assert gen.o.iri == self.Q_URI
+        derived = find_triple(triples, PROV_WAS_DERIVED_FROM, self.GND_URI)
+        assert derived is not None
+        assert derived.o.iri == self.Q_URI
 
     def test_grounding_concepts(self):
         triples = grounding_triples(self.GND_URI, self.Q_URI, ["AI", "ML", "robots"])
@@ -730,7 +730,7 @@ class TestDocRagQuestionTriples:
 
     def test_docrag_question_types(self):
         triples = docrag_question_triples(self.Q_URI, "Find info", "2024-01-01T00:00:00Z")
-        assert has_type(triples, self.Q_URI, PROV_ACTIVITY)
+        assert has_type(triples, self.Q_URI, PROV_ENTITY)
         assert has_type(triples, self.Q_URI, TG_QUESTION)
         assert has_type(triples, self.Q_URI, TG_DOC_RAG_QUESTION)