feat(data-process): 增加可配置思维链生成

backend/tests/test_data_process_generation.py

@@ -33,6 +33,8 @@ def test_generate_model_records_uses_prompt_auth_and_stable_split() -> None:
         assert payload["model"] == "qwen-plus"
         assert payload["response_format"] == {"type": "json_object"}
         assert "客户反馈页面加载慢" in payload["messages"][1]["content"]
+        assert "你正在生成标准监督微调问答数据" in payload["messages"][0]["content"]
+        assert "禁止输出分析、推理过程" in payload["messages"][0]["content"]
         return httpx.Response(
             200,
             json={
@@ -91,6 +93,8 @@ def test_generate_model_records_builds_reasoning_output_with_think_tags() -> Non
         payload = json.loads(request.content)
         system_prompt = payload["messages"][0]["content"]
         assert '"reasoning":"...","answer":"..."' in system_prompt
+        assert "你正在生成用于训练推理模型的思维链数据" in system_prompt
+        assert "推理详细程度为“普通”" in system_prompt
         assert "系统会在保存时统一组装" in system_prompt
         content = "<think>模型接口自己的分析</think>" + json.dumps(
             {
@@ -126,6 +130,49 @@ def test_generate_model_records_builds_reasoning_output_with_think_tags() -> Non
     )
 
 
+def test_generate_model_records_uses_detailed_reasoning_instruction() -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        system_prompt = json.loads(request.content)["messages"][0]["content"]
+        assert "推理详细程度为“详细”" in system_prompt
+        assert "完整展开问题条件、来源依据、中间计算或推导" in system_prompt
+        return httpx.Response(
+            200,
+            json={
+                "choices": [
+                    {
+                        "message": {
+                            "content": json.dumps(
+                                {
+                                    "items": [
+                                        {
+                                            "instruction": "计算报销总额",
+                                            "reasoning": "条件为交通费 30 元和餐费 20 元。分别核对后相加，30 + 20 = 50。",
+                                            "answer": "报销总额为 50 元。",
+                                        }
+                                    ]
+                                },
+                                ensure_ascii=False,
+                            )
+                        }
+                    }
+                ]
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-detailed", "edited_content": "交通费 30 元，餐费 20 元"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"output_type": "reasoning", "reasoning_detail": "detailed"},
+        task_id="task-detailed",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert records[0]["status"] == "valid"
+    assert "分别核对后相加" in records[0]["output"]
+
+
 def test_generate_model_records_marks_reasoning_without_reasoning_field_invalid() -> None:
     response = {
         "choices": [
@@ -392,3 +439,15 @@ def test_generate_model_records_rejects_unknown_output_type() -> None:
             split={"train": 100, "validation": 0, "test": 0},
             qa_pairs_per_item=1,
         )
+
+
+def test_generate_model_records_rejects_unknown_reasoning_detail() -> None:
+    with pytest.raises(ModelGenerationError, match="reasoning_detail"):
+        generate_model_records(
+            [],
+            model={"name": "model", "api_url": "https://model.example/v1"},
+            config={"output_type": "reasoning", "reasoning_detail": "verbose"},
+            task_id="task-invalid-reasoning-detail",
+            split={"train": 100, "validation": 0, "test": 0},
+            qa_pairs_per_item=1,
+        )