feat: release 1.5.1 with human review and batch filters

apps/admin_console/services/report_export.py

@@ -24,6 +24,7 @@ from apps.admin_console.database.repositories.step_repository import StepReposit
 from apps.admin_console.services.automation_store import store, identifier
 from apps.admin_console.services.task_import import execution_title
 from artemis.runtime.case_result import RESULT_LABELS, resolve_case_result
+from apps.admin_console.services.case_review import reviewed_result
 
 EXPORT_ROOT = WORKSPACE_ROOT / "artifacts" / "reports"
 EXPORT_LOCK = threading.RLock()
@@ -65,7 +66,10 @@ def text(value) -> str:
 def verdict(outcome: dict | None) -> str:
     result = (outcome or {}).get("test_result")
     if isinstance(result, dict) and result.get("status") in RESULT_LABELS:
-        return RESULT_LABELS[result["status"]]
+        label = RESULT_LABELS[result["status"]]
+        if result.get("source"):
+            label += "（人工确认）" if result["source"] == "human" else "（AI确认）"
+        return label
     tests = (outcome or {}).get("tests") or {}
     if tests.get("failed", 0):
         return "验证失败"
@@ -183,9 +187,10 @@ def session_report(session_id: str, db_path=None) -> dict:
     case = meta.get("case") or {}
     status = meta.get("terminal_status") or meta.get("status") or session.get("status", "unknown")
     error = failure_reason(directory, status, meta.get("error"))
-    test_result = resolve_case_result(outcome, status, error)
+    ai_result = resolve_case_result(outcome, status, error)
+    test_result = reviewed_result(session_id, ai_result.model_dump() if ai_result else None, store)
     if test_result:
-        outcome = {**outcome, "test_result": test_result.model_dump()}
+        outcome = {**outcome, "test_result": test_result}
     verification = verdict(outcome)
     if status in {"failed", "interrupted"} and verification.startswith("未验证"):
         verification = "未验证（任务异常终止）"
@@ -204,7 +209,7 @@ def session_report(session_id: str, db_path=None) -> dict:
         "expected": case.get("expected", ""),
         "status": status,
         "verdict": verification,
-        "test_result": test_result.model_dump() if test_result else None,
+        "test_result": test_result,
         "outcome": outcome,
         "content": content,
         "steps": steps,
@@ -241,6 +246,13 @@ def metadata(report: dict) -> list[tuple]:
         ("预期结果", report["expected"] or "未指定"),
         ("执行状态", STATUS.get(report["status"], report["status"])),
         ("验证结论", report["verdict"]),
+        ("人工复验时间", time_text((report.get("test_result") or {}).get("reviewed_at"))),
+        (
+            "原 AI 结论",
+            verdict({"test_result": (report.get("test_result") or {}).get("ai_result")})
+            if (report.get("test_result") or {}).get("source") == "human"
+            else "—",
+        ),
         ("判定依据", (report.get("test_result") or {}).get("reason") or "未记录"),
         (
             "验收证据",