feat(data-process): 增加可配置思维链生成

backend/app/modules/data_process/generation.py

@@ -25,6 +25,12 @@ class ModelGenerationError(ValueError):
 OUTPUT_TYPE_STANDARD = "standard"
 OUTPUT_TYPE_REASONING = "reasoning"
 SUPPORTED_OUTPUT_TYPES = {OUTPUT_TYPE_STANDARD, OUTPUT_TYPE_REASONING}
+REASONING_DETAIL_NORMAL = "normal"
+REASONING_DETAIL_DETAILED = "detailed"
+SUPPORTED_REASONING_DETAILS = {
+    REASONING_DETAIL_NORMAL,
+    REASONING_DETAIL_DETAILED,
+}
 
 
 def chat_completions_url(value: str) -> str:
@@ -122,19 +128,32 @@ def _prompt_messages(
     start_index: int,
     total_count: int,
     output_type: str,
+    reasoning_detail: str,
 ) -> list[dict[str, str]]:
     end_index = start_index + count - 1
     if output_type == OUTPUT_TYPE_REASONING:
         schema = '{"items":[{"instruction":"...","input":"...","reasoning":"...","answer":"..."}]}'
+        detail_rule = (
+            "推理详细程度为“详细”：完整展开问题条件、来源依据、中间计算或推导，"
+            "并在得出答案前核对结论；每一步都必须能从来源内容中验证。"
+            if reasoning_detail == REASONING_DETAIL_DETAILED
+            else
+            "推理详细程度为“普通”：只保留得出答案所需的关键依据和必要步骤，"
+            "避免冗长复述、套话和无依据扩展。"
+        )
         output_rule = (
+            "你正在生成用于训练推理模型的思维链数据，而不是普通问答数据。"
             "instruction、reasoning 和 answer 均不得为空；reasoning 必须是基于来源内容、"
-            "可核对且简洁的推理步骤，answer 只写最终答案。"
+            f"可核对的推理过程，answer 只写最终答案。{detail_rule}"
             "这是思维链输出模式，即使其他提示语要求省略分析，也不得省略 reasoning。"
             "不要自行添加 <think> 标签，系统会在保存时统一组装。"
         )
     else:
         schema = '{"items":[{"instruction":"...","input":"...","output":"..."}]}'
-        output_rule = "instruction 和 output 不得为空，不要输出分析过程。"
+        output_rule = (
+            "你正在生成标准监督微调问答数据。instruction 和 output 不得为空；"
+            "output 只写最终答案，禁止输出分析、推理过程或 <think> 标签。"
+        )
     schema_instruction = (
         f"必须只返回 JSON 对象，格式为 {schema}；items 必须包含 {count} 条。"
         f"这是总计 {total_count} 条中的第 {start_index}-{end_index} 条，"
@@ -176,6 +195,13 @@ def generate_model_records(
     output_type = str(config.get("output_type") or OUTPUT_TYPE_STANDARD).strip().lower()
     if output_type not in SUPPORTED_OUTPUT_TYPES:
         raise ModelGenerationError(f"output_type must be one of {sorted(SUPPORTED_OUTPUT_TYPES)}")
+    reasoning_detail = str(
+        config.get("reasoning_detail") or REASONING_DETAIL_NORMAL
+    ).strip().lower()
+    if reasoning_detail not in SUPPORTED_REASONING_DETAILS:
+        raise ModelGenerationError(
+            f"reasoning_detail must be one of {sorted(SUPPORTED_REASONING_DETAILS)}"
+        )
     endpoint = chat_completions_url(str(model.get("api_url") or ""))
     model_name = str(model.get("online_model_name") or model.get("name") or "").strip()
     if not model_name:
@@ -217,6 +243,7 @@ def generate_model_records(
                         start_index=batch_start,
                         total_count=qa_pairs_per_item,
                         output_type=output_type,
+                        reasoning_detail=reasoning_detail,
                     ),
                     "temperature": temperature,
                     "max_tokens": max_tokens,

backend/app/modules/data_process/store.py

@@ -95,6 +95,17 @@ def _task_output_type(task: dict[str, Any]) -> str:
     return str(config.get("output_type") or config.get("outputType") or "standard")
 
 
+def _task_reasoning_detail(task: dict[str, Any]) -> str:
+    config = _json_value(task.get("config"), {})
+    if not isinstance(config, dict):
+        return "normal"
+    return str(
+        config.get("reasoning_detail")
+        or config.get("reasoningDetail")
+        or "normal"
+    )
+
+
 def _reasoning_output_is_valid(value: Any) -> bool:
     match = re.fullmatch(
         r"\s*<think>\s*(?P<reasoning>[\s\S]*?)\s*</think>\s*(?P<answer>[\s\S]+?)\s*",
@@ -1773,6 +1784,7 @@ class DataProcessStore:
                 "storage_backend": "database",
                 "source_task_id": task_id,
                 "output_type": _task_output_type(task),
+                "reasoning_detail": _task_reasoning_detail(task),
                 "source_file_ids": [item["id"] for item in self._source_ids(conn, task_id)],
                 "source_result_ids": source_result_ids,
                 "format": payload.get("format") or "alpaca_jsonl",