feat(trace): finish run-aware demo verification

mvp/architecture/harness-quality-gates.md

@@ -36,7 +36,7 @@ flowchart TB
     Tools --> Invocation["tool_invocation"]
     Agent --> StepHook["AgentLoggingHook"]
     StepHook --> Step["agent_step"]
-    Agent --> Session["diagnosis_session"]
+    Agent --> Run["diagnosis_run"]
 
     Invocation --> EvidenceRefs["retrieval_details.evidence_refs"]
     EvidenceRefs --> Gatekeeper["ExecutorGatekeeperService"]
@@ -49,7 +49,7 @@ flowchart TB
     Invocation --> AiOpsRule["AiOpsRuleEvaluationService"]
     AiOpsRule --> AiOpsEval["self_evaluation.aiops_rule_evaluation"]
 
-    Session --> TraceAPI["DiagnosisTraceService"]
+    Run --> TraceAPI["DiagnosisTraceService"]
     Step --> TraceAPI
     Invocation --> TraceAPI
     SelfEval --> TraceAPI
@@ -210,7 +210,7 @@ Verifier 不再逐字核验 excerpt 真伪；这由 Gatekeeper 完成。Verifier
 结果写入：
 
 ```text
-diagnosis_session.self_evaluation.verifier_evaluation
+diagnosis_run.self_evaluation.verifier_evaluation
 ```
 
 其中同时持久化 `executor_structured_output`、`gatekeeper_result`、`tool_trace_summary`、`prompt_audit` 和 `composer_output`，用于 Trace 回放。
@@ -229,7 +229,7 @@ AIOps 当前不走 Chat Verifier，而是用 `AiOpsRuleEvaluationService` 做轻
 结果写入：
 
 ```text
-diagnosis_session.self_evaluation.aiops_rule_evaluation
+diagnosis_run.self_evaluation.aiops_rule_evaluation
 ```
 
 ## 8. Eval Baseline