diff --git a/backend/app/engine/nodes/analysis.py b/backend/app/engine/nodes/analysis.py
index 80501458..3c622232 100644
--- a/backend/app/engine/nodes/analysis.py
+++ b/backend/app/engine/nodes/analysis.py
@@ -56,7 +56,12 @@ async def run_analysis(state: GraphState, ctx: NodeContext) -> dict[str, Any]:
     if errors := [i for i in analysis_issues(ctx.run.spec, ctx.node) if i.level == "error"]:
         raise NodeError(ctx.node.id, errors[0].message)
     items: list[dict[str, Any]] = ctx.config["items"]
-    settings = await settings_of(run_snapshot(ctx.run), ctx.config.get("overrides") or None)
+    overrides = ctx.config.get("overrides") or None
+    settings = await settings_of(run_snapshot(ctx.run), overrides)
+    # 画图时阈值覆盖只能对着缺省值校验；合并了这次运行的设置快照以后再核一遍（管理员把「超出常规波动」调到 3、卡上把「明显
+    # 超出」覆盖成 2.5，就永远判不出超出）。这是配置错误，不是数据问题：让卡失败、说清冲突在哪
+    if overrides and (problem := contract.settings_problem(settings)):
+        raise NodeError(ctx.node.id, f"阈值覆盖和这次运行的分析设置冲突：{problem}。请改分析卡上的阈值覆盖")
 
     queries = [e for e in state.get("evidence") or [] if isinstance(e, dict) and e.get("kind") == "query"]
     inputs: dict[str, InputSnapshot] = {}
diff --git a/backend/tests/test_analysis_card_data.py b/backend/tests/test_analysis_card_data.py
index 755df707..179ef740 100644
--- a/backend/tests/test_analysis_card_data.py
+++ b/backend/tests/test_analysis_card_data.py
@@ -68,3 +68,16 @@ async def test_a_structural_call_error_still_fails_the_card_and_names_the_item()
     assert row.status == "failed"
     assert "分析项「where」（变化拆解）" in row.error and "没有「channel」这一列" in row.error
     assert "请在分析卡中改正这一项" in row.error
+
+
+async def test_overrides_that_conflict_with_the_run_settings_fail_the_card():
+    # 画图时对着缺省值校验能过（缺省「超出常规波动」是 2）；这次运行的设置把它调到 3，卡上覆盖的「明显超出」2.5 就永远判不出
+    card = node("card", "analysis", items=[WHERE], overrides={"k_alert": 2.5})
+    graph = chain(node("start", "input"), node("by_region", "tool", tool=TOOL, args={"sql": BY_REGION}), card)
+    run = await run_manager.start(graph=graph, input_payload={}, options={"analysis": {"k_warn": 3.0}})
+    row = await wait(run.id)
+    assert row.status == "failed"
+    assert "阈值覆盖和这次运行的分析设置冲突：「明显超出」的倍数要大于「超出常规波动」的倍数" in row.error
+    assert await events(row.id, "analysis.end", "card") == []
+    ok = await run_manager.start(graph=graph, input_payload={}, options={"analysis": {"k_warn": 2.0}})
+    assert (await wait(ok.id)).status == "succeeded"