fix: session resume, config_set schema, metrics chart, subagent logging

- Fix session resume: remove messages.length>1 guard so sessionStorage
  ID is used as resumeSessionId on first message (prevents new session
  creation when user sends "继续")
- Fix config_set tool schema: add missing `items: {}` to array type in
  oneOf (Azure OpenAI strict validation rejects it otherwise)
- Metrics chart: use actual target set filename from trigger text
  instead of generic "target_subset" key
- Add sub-agent skill call logging to agent_runtime.py (full
  prompt/response, no truncation)
- Various metric enrichment and dedup fixes in server.py

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

frontend/app/app/assistant.tsx

@@ -66,8 +66,7 @@ export const Assistant = ({ initialSessionId }: AssistantProps = {}) => {
 					const lastSessionId = getLastSessionId(messages);
 					const pendingWorkspaceSessionId =
 						messages.length <= 1 ? readPendingWorkspaceSessionId() : null;
-					const selectedResumeSessionId =
-						messages.length > 1 ? selectedSessionId : null;
+					const selectedResumeSessionId = selectedSessionId;
 					const outgoingSessionId =
 						lastSessionId ??
 						selectedResumeSessionId ??

frontend/app/components/training/metrics-chart-panel.tsx

@@ -28,9 +28,14 @@ const METRIC_LABELS: Record<string, string> = {
 	req_set_car: "需求集合(车载)",
 	dapan_car: "大盘车载",
 	specific_test: "Specific Test",
+	target_subset: "目标集合",
+	icl_test: "ICL Test",
+	overall: "大盘整体",
 	triage_err_rate: "Triage 错误率",
 	bvt_nav: "导航BVT",
 	talkable_controllable: "可聊可控",
+	badcase_2025: "Badcase 2025",
+	autotask: "自动任务",
 	target_subset_count: "目标子集数量",
 	target_subset_wrong: "目标子集错误数",
 	target_subset_correct: "目标子集正确数",