feat: add shared test acceptance and release 1.5.0

tests/unit/admin_console/test_automation.py

@@ -780,7 +780,9 @@ def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolat
     )
     report = reports.session_report(job["session_id"])
     assert "连续 3 次" in report["error"]
-    assert report["verdict"] == "未验证（任务异常终止）"
+    assert report["verdict"] == "测试阻塞"
+    assert report["test_result"]["status"] == "blocked"
+    assert "连续 3 次" in report["test_result"]["reason"]
     assert "abc123secret" not in reports.failure_reason(
         folder, "failed", "认证失败 OPENAI_API_KEY=abc123secret Authorization: Bearer abc123secret"
     )
@@ -796,7 +798,10 @@ def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolat
         cell.text == "分类" for table in doc.tables for row in table.rows for cell in row.cells
     )
     wb = load_workbook(next(path for path in paths if path.suffix == ".xlsx"))
-    assert "连续 3 次" in wb["任务结果"]["B15"].value
+    assert any(
+        row[0].value == "异常原因" and "连续 3 次" in row[1].value
+        for row in wb["任务结果"].iter_rows()
+    )
     assert wb["结论"]["B2"].value == "结果"
     assert wb["结果表1"]["A2"].value == "系统"
     assert wb["执行证据"]["A1"].font.name == "微软雅黑"
@@ -810,6 +815,51 @@ def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolat
     ]
 
 
+def test_prompt_based_verdict_is_consistent_in_history_batch_and_reports(
+    client, isolated, monkeypatch
+):
+    from artemis.runtime import case_result
+
+    monkeypatch.setattr(case_result, "TRACES_PATH", reports.TRACES_PATH)
+    batch = service.create_batch(payload())
+    job = isolated.jobs(batch["id"])[0]
+    isolated.save_job(
+        {**job, "status": "completed", "started_at": time.time() - 50, "ended_at": time.time()}
+    )
+    result = {
+        "status": "failed",
+        "reason": "预期出现成功提示，实际显示错误",
+        "evidence": ["步骤 3 点击后截图显示错误提示"],
+    }
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "run_outcome.json").write_text(
+        json.dumps(
+            {"task_status": "completed", "tests": {}, "test_result": result}, ensure_ascii=False
+        ),
+        encoding="utf-8",
+    )
+    history = client.get("/api/automation/history").json()["items"][0]
+    batch_job = client.get(f"/api/automation/batches/{batch['id']}").json()["jobs"][0]
+    report = client.get(f"/api/automation/reports/{job['session_id']}").json()
+    for item in (history, batch_job, report):
+        assert item["status"] == "completed"
+        assert item["test_result"] == result
+    assert report["verdict"] == "测试不通过"
+    paths = reports.export_session(job["session_id"])
+    doc = Document(next(path for path in paths if path.suffix == ".docx"))
+    doc_text = "\n".join(
+        cell.text for table in doc.tables for row in table.rows for cell in row.cells
+    )
+    doc_text += "\n" + "\n".join(paragraph.text for paragraph in doc.paragraphs)
+    assert result["reason"] in doc_text
+    assert result["evidence"][0] in doc_text
+    wb = load_workbook(next(path for path in paths if path.suffix == ".xlsx"))
+    values = [cell.value for row in wb["任务结果"].iter_rows() for cell in row]
+    assert "测试不通过" in values
+    assert result["reason"] in values
+
+
 def test_task_material_zip_contains_ordered_evidence_and_reports(
     client, isolated, tmp_path, monkeypatch
 ):