feat: release 2.4.0 with original cases and automatic human review

apps/admin_console/services/report_export.py

@@ -36,7 +36,7 @@ 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"
-BATCH_ARCHIVE_SIGNATURE = "artemis-batch-layout-2"
+BATCH_ARCHIVE_SIGNATURE = "artemis-batch-layout-3"
 
 
 def batch_archive_signature(batch_id: str | None = None) -> str:
@@ -234,11 +234,14 @@ def session_report(session_id: str, db_path=None) -> dict:
     if status in {"failed", "interrupted"} and verification.startswith("未验证"):
         verification = "未验证（任务异常终止）"
     if not content:
-        content = (
-            "本任务未生成最终结论。请查看异常原因和已记录的执行步骤。"
-            if status in {"failed", "interrupted"}
-            else "本任务没有保存最终结论。以下内容仅来自已记录的执行状态和证据。"
-        )
+        lines = ["本任务未保存独立输出正文。", f"当前有效判定：{verification}"]
+        if test_result:
+            if test_result.get("reason"):
+                lines.append(f"判定依据：{test_result['reason']}")
+            lines.extend(f"- {item}" for item in test_result.get("evidence") or [])
+        elif error:
+            lines.append(f"异常原因：{error}")
+        content = "\n\n".join(lines)
     return {
         "id": session_id,
         **guidance_details(session_id, db_path=repo.db_path),
@@ -264,6 +267,7 @@ def session_report(session_id: str, db_path=None) -> dict:
         "category": case.get("category", ""),
         "subcategory": case.get("subcategory", ""),
         "preconditions": case.get("preconditions", ""),
+        "original_case": case.get("original_case"),
         "task_config": case.get("task_config") or {},
         "task_extensions": task_extensions.report_sections(session_id, store),
     }
@@ -330,17 +334,24 @@ def source_text(value: dict) -> str:
     for item in value.get("sources", []):
         references = ", ".join(
             " / ".join(
-                f"{key}={ref[key]}" for key in ("step_id", "call_id", "source_id") if ref.get(key)
+                f"{key}={ref[key]}"
+                for key in ("step_id", "call_id", "source_id", "trace_id")
+                if ref.get(key)
             )
             or "编号未记录"
             for ref in item.get("references", [])
         )
+        variation = "（来源标签随步骤变化，详见原始步骤）" if item.get("label_varies") else ""
         lines.append(
-            f"{labels.get(item['kind'], '其他')} · {item['label'] or item['target_id']} · {references}"
+            f"{labels.get(item['kind'], '其他')} · {item['label'] or item['target_id']}"
+            f"{variation} · {references}"
         )
     if value.get("sources_omitted"):
         lines.append(f"另 {value['sources_omitted']} 个来源见原始步骤记录。")
-    lines.append(f"来源未完整记录的步骤：{value.get('unattributed_step_count', '未知')}。")
+    lines.append(
+        f"未关联到单一来源的步骤：{value.get('unattributed_step_count', '未知')}。"
+        "窗口枚举等操作可能没有单一目标；此计数不表示截图丢失。"
+    )
     lines.append(value.get("note") or "来源清单不代表断言已验证。")
     return "\n".join(lines)
 
@@ -367,6 +378,15 @@ def metadata(report: dict) -> list[tuple]:
         ("检测项目", report.get("category") or "—"),
         ("测试子项", report.get("subcategory") or "—"),
         ("前置约束提取", report.get("preconditions") or "—"),
+        *(
+            [
+                ("原始用例 · 预置条件", report["original_case"].get("preconditions") or "未填写"),
+                ("原始用例 · 操作步骤", report["original_case"].get("steps") or "未填写"),
+                ("原始用例 · 预期结果", report["original_case"].get("expected") or "未填写"),
+            ]
+            if report.get("original_case") is not None
+            else []
+        ),
         ("任务配置", config_text(report.get("task_config"))),
         ("任务目标", report["goal"]),
         ("预期结果", report["expected"] or "未指定"),
@@ -949,8 +969,7 @@ def session_videos(report: dict) -> list[tuple[Path, str]]:
         return []
     source = Path(str(candidate)).resolve()
     trace_root = TRACES_PATH.resolve()
-    # Workers save recordings in their finalized web_<time>_<id>_PASS/FAIL
-    # folder. The recording row already ties that path to this session.
+    # The recording row already ties the finalized trace folder to this session.
     if not source.is_relative_to(trace_root):
         return []
     # A resumed recording lives under resume_NNNN; the initial recording is