Split Analysis into Analysis+ToolUse and Observation, add message_id (#747)

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

trustgraph-cli/trustgraph/cli/invoke_agent.py

@@ -12,6 +12,7 @@ from trustgraph.api import (
     ProvenanceEvent,
     Question,
     Analysis,
+    Observation,
     Conclusion,
     Decomposition,
     Finding,
@@ -206,13 +207,13 @@ def question_explainable(
                         print(f"    Time: {entity.timestamp}", file=sys.stderr)
 
                 elif isinstance(entity, Analysis):
-                    print(f"\n  [iteration] {prov_id}", file=sys.stderr)
-                    if entity.action:
-                        print(f"    Action: {entity.action}", file=sys.stderr)
-                    if entity.thought:
-                        print(f"    Thought: {entity.thought}", file=sys.stderr)
-                    if entity.observation:
-                        print(f"    Observation: {entity.observation}", file=sys.stderr)
+                    action_label = f": {entity.action}" if entity.action else ""
+                    print(f"\n  [analysis{action_label}] {prov_id}", file=sys.stderr)
+
+                elif isinstance(entity, Observation):
+                    print(f"\n  [observation] {prov_id}", file=sys.stderr)
+                    if entity.document:
+                        print(f"    Document: {entity.document}", file=sys.stderr)
 
                 elif isinstance(entity, Decomposition):
                     print(f"\n  [decompose] {prov_id}", file=sys.stderr)

trustgraph-cli/trustgraph/cli/show_explain_trace.py

@@ -26,6 +26,7 @@ from trustgraph.api import (
     Focus,
     Synthesis,
     Analysis,
+    Observation,
     Conclusion,
     Decomposition,
     Finding,
@@ -379,11 +380,13 @@ def print_agent_text(trace, explain_client, api, user):
                         print(f"    {line}")
                 except Exception:
                     print(f"  Arguments: {step.arguments}")
+            print()
 
-            obs = step.observation or 'N/A'
-            if obs and len(obs) > 200:
-                obs = obs[:200] + "... [truncated]"
-            print(f"  Observation: {obs}")
+        elif isinstance(step, Observation):
+            print("--- Observation ---")
+            _print_document_content(
+                explain_client, api, user, step.document, "Content",
+            )
             print()
 
         elif isinstance(step, Synthesis):
@@ -437,6 +440,12 @@ def trace_to_dict(trace, trace_type):
                     "step": step.step,
                     "document": step.document,
                 }
+            elif isinstance(step, Observation):
+                return {
+                    "type": "observation",
+                    "id": step.uri,
+                    "document": step.document,
+                }
             elif isinstance(step, Analysis):
                 return {
                     "type": "analysis",
@@ -444,7 +453,6 @@ def trace_to_dict(trace, trace_type):
                     "action": step.action,
                     "arguments": step.arguments,
                     "thought": step.thought,
-                    "observation": step.observation,
                 }
             elif isinstance(step, Synthesis):
                 return {