feat: release 2.4.0 with original cases and automatic human review

tests/unit/admin_console/test_automation.py

@@ -908,6 +908,85 @@ def test_reports_do_not_execute_formulas_or_invent_pass(isolated):
         assert "未验证".encode() in doc.read("word/document.xml")
 
 
+@pytest.mark.parametrize("result_status", ["passed", "failed", "blocked", "inconclusive"])
+def test_report_without_output_body_uses_effective_verdict_and_evidence(isolated, result_status):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job({**job, "status": "completed"})
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "run_outcome.json").write_text(
+        json.dumps(
+            {
+                "task_status": "completed",
+                "test_result": {
+                    "status": result_status,
+                    "reason": "实际验收依据",
+                    "evidence": ["记录中的证据"],
+                },
+            }
+        ),
+        encoding="utf-8",
+    )
+    report = reports.session_report(job["session_id"])
+    assert report["verdict"] in report["content"]
+    assert "实际验收依据" in report["content"]
+    assert "记录中的证据" in report["content"]
+    assert "未保存独立输出正文" in report["content"]
+    assert "没有保存最终结论" not in report["content"]
+    assert report["test_result"]["status"] == result_status
+
+
+def test_report_without_output_body_keeps_human_review_authoritative(isolated):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job({**job, "status": "completed"})
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "run_outcome.json").write_text(
+        json.dumps(
+            {
+                "test_result": {"status": "passed", "reason": "AI 原判通过"},
+            }
+        ),
+        encoding="utf-8",
+    )
+    isolated.save_case_review(job["session_id"], "failed", "用户确认实际结果不符合预期")
+    report = reports.session_report(job["session_id"])
+    assert "人工确认" in report["content"]
+    assert "用户确认实际结果不符合预期" in report["content"]
+    assert "AI 原判通过" not in report["content"]
+    assert report["test_result"]["status"] == "failed"
+
+
+def test_report_projects_stored_android_receipts_without_rewriting_history(isolated):
+    from tests.unit.data_engine.test_evidence_sources import android_receipt
+
+    sid = isolated.jobs(service.create_batch(payload())["id"])[0]["session_id"]
+    receipt = android_receipt()["payload"]["result"]
+    raw_payload = json.dumps({"args": {"action": "screenshot"}, "result": json.dumps(receipt)})
+    with sqlite3.connect(isolated.path) as conn:
+        conn.execute(
+            "INSERT INTO sessions(session_id,initial_goal,start_time,status) VALUES (?,?,?,?)",
+            (sid, "跨端截图", 1, "completed"),
+        )
+        conn.execute(
+            "INSERT INTO steps(step_id,session_id,step_number) VALUES (?,?,?)", ("s", sid, 1)
+        )
+        conn.execute(
+            "INSERT INTO traces(trace_id,session_id,step_id,type,name,timestamp,status,payload) VALUES (?,?,?,?,?,?,?,?)",
+            ("capture", sid, "s", "tool", "android_file", 2, "success", raw_payload),
+        )
+    report = reports.session_report(sid)
+    source = report["evidence_sources"]["sources"][0]
+    assert source["kind"] == "android"
+    assert source["references"][0]["trace_id"] == "capture"
+    assert report["evidence_sources"]["unattributed_step_count"] == 0
+    with sqlite3.connect(isolated.path) as conn:
+        assert (
+            conn.execute("SELECT payload FROM traces WHERE trace_id='capture'").fetchone()[0]
+            == raw_payload
+        )
+
+
 def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolated):
     job = isolated.jobs(service.create_batch(payload())["id"])[0]
     isolated.save_job({**job, "status": "failed"})