feat(data-process): 支持思维链输出类型

backend/tests/test_data_process_generation.py

@@ -86,6 +86,119 @@ def test_generate_model_records_uses_prompt_auth_and_stable_split() -> None:
     assert progress_updates == [(1, 1)]
 
 
+def test_generate_model_records_builds_reasoning_output_with_think_tags() -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        payload = json.loads(request.content)
+        system_prompt = payload["messages"][0]["content"]
+        assert '"reasoning":"...","answer":"..."' 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(
+            {
+                "items": [
+                    {
+                        "instruction": "计算两项费用合计",
+                        "input": "交通费 30 元，餐费 20 元",
+                        "reasoning": "先识别两项费用，再计算 30 + 20。",
+                        "answer": "合计 50 元。",
+                    }
+                ]
+            },
+            ensure_ascii=False,
+        )
+        return httpx.Response(
+            200,
+            json={"choices": [{"message": {"content": content}}]},
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-reasoning", "edited_content": "交通费 30 元，餐费 20 元"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"output_type": "reasoning"},
+        task_id="task-reasoning",
+        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 records[0]["output"] == (
+        "<think>\n先识别两项费用,再计算 30 + 20。\n</think>\n合计 50 元。"
+    )
+
+
+def test_generate_model_records_marks_reasoning_without_reasoning_field_invalid() -> None:
+    response = {
+        "choices": [
+            {
+                "message": {
+                    "content": json.dumps(
+                        {
+                            "items": [
+                                {
+                                    "instruction": "问题",
+                                    "answer": "只有最终答案",
+                                }
+                            ]
+                        },
+                        ensure_ascii=False,
+                    )
+                }
+            }
+        ]
+    }
+    client = httpx.Client(
+        transport=httpx.MockTransport(lambda _: httpx.Response(200, json=response))
+    )
+
+    records = generate_model_records(
+        [{"id": "preview-missing-reasoning", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"output_type": "reasoning"},
+        task_id="task-missing-reasoning",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=client,
+    )
+
+    assert records[0]["status"] == "invalid"
+    assert records[0]["output"] == "只有最终答案"
+    assert "reasoning" in records[0]["error"]
+
+
+def test_standard_output_removes_model_think_block() -> None:
+    content = json.dumps(
+        {
+            "items": [
+                {
+                    "instruction": "问题",
+                    "output": "<think>不应保存的分析</think>最终答案",
+                }
+            ]
+        },
+        ensure_ascii=False,
+    )
+    client = httpx.Client(
+        transport=httpx.MockTransport(
+            lambda _: httpx.Response(
+                200,
+                json={"choices": [{"message": {"content": content}}]},
+            )
+        )
+    )
+
+    records = generate_model_records(
+        [{"id": "preview-standard", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"output_type": "standard"},
+        task_id="task-standard",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=client,
+    )
+
+    assert records[0]["output"] == "最终答案"
+
+
 def test_generate_model_records_keeps_partial_failure_for_manual_repair() -> None:
     client = httpx.Client(
         transport=httpx.MockTransport(
@@ -267,3 +380,15 @@ def test_generate_model_records_rejects_out_of_range_count(
             split={"train": 100, "validation": 0, "test": 0},
             qa_pairs_per_item=qa_pairs_per_item,
         )
+
+
+def test_generate_model_records_rejects_unknown_output_type() -> None:
+    with pytest.raises(ModelGenerationError, match="output_type"):
+        generate_model_records(
+            [],
+            model={"name": "model", "api_url": "https://model.example/v1"},
+            config={"output_type": "unknown"},
+            task_id="task-invalid-output",
+            split={"train": 100, "validation": 0, "test": 0},
+            qa_pairs_per_item=1,
+        )