feat(data_process): 问答对数据评测体系与质量分雷达图

- 三层评测：规则层沿用原五维规则分，语义层用本地 BGE 向量算问答/来源
  相关性，评审层复用生成模型按 rubric 打分（忠实度/正确性/清晰度等，
  区分 standard/reasoning/dpo 输出类型），任一层失败自动降级
- 组合分 = 规则 35% + 语义 20% + 评审 45%，缺层自动重归一
- 新增 results/evaluate-batch 批量评测接口，镜像批量重生成的并发、
  乐观锁与部分成功语义；生成阶段不再展示质量分
- 详情页与结果编辑页新增"数据评测"按钮和批量进度；质量分列悬停弹出
  雷达图浮窗（评审 5 维 + 语义 2 维、三层分项、评审理由）
- 手动编辑/恢复后重算规则与语义层并丢弃过期评审分，雷达图不再展示
  失效数据

backend/app/api/v1/endpoints/data_process.py

@@ -60,6 +60,10 @@ from app.modules.data_process.document_chunking import (
     chunk_semantic_text,
     merge_short_chunks,
 )
+from app.modules.data_process.evaluation import (
+    evaluate_result_record,
+    reevaluate_edited_record,
+)
 from app.modules.data_process.generation import generate_model_records
 from app.modules.data_process.office_preview import (
     MAX_XLSX_PREVIEW_ROWS,
@@ -96,6 +100,7 @@ from app.schemas.data_process import (
     PreviewItemUpdate,
     ProcessType,
     PublishRequest,
+    ResultBatchEvaluateRequest,
     ResultBatchRegenerateRequest,
     ResultRegenerateRequest,
     ResultUpdate,
@@ -2039,12 +2044,13 @@ def update_result(
                 or 20
             ),
         )
-        quality = score_quality(
+        # 编辑后内容已变化：重算规则与语义层，旧的评审分不再可信直接丢弃。
+        update["quality_score"] = reevaluate_edited_record(
             merged,
-            min_output_length=minimum,
             source_content=source_content,
+            previous_quality=current.get("quality_score"),
+            min_output_length=minimum,
         )
-        update["quality_score"] = asdict(quality)
         result = store.update_result(
             task_id,
             result_id,
@@ -2089,11 +2095,6 @@ def restore_result(
                 or 20
             ),
         )
-        quality = score_quality(
-            restored,
-            min_output_length=minimum,
-            source_content=source_content,
-        )
         restored = store.update_result(
             task_id,
             result_id,
@@ -2103,7 +2104,12 @@ def restore_result(
                 "output": restored["output"],
                 "chosen": restored["chosen"],
                 "rejected": restored["rejected"],
-                "quality_score": asdict(quality),
+                "quality_score": reevaluate_edited_record(
+                    restored,
+                    source_content=source_content,
+                    previous_quality=current.get("quality_score"),
+                    min_output_length=minimum,
+                ),
                 "expected_updated_at": current.get("updated_at"),
             },
         )
@@ -2266,6 +2272,46 @@ def _safe_regeneration_error(exc: Exception) -> str:
     return re.sub(r"\s+", " ", str(exc)).strip()[:500] or "result regeneration failed"
 
 
+def _evaluate_result_in_place(
+    task_id: str,
+    current: dict[str, Any],
+    source_content: str,
+    config: dict[str, Any],
+    evaluation_model: dict[str, Any] | None,
+    store: DataProcessStore,
+    *,
+    expected_updated_at: str,
+    model_client: httpx.Client | None = None,
+    minimum: int = 20,
+) -> dict[str, Any]:
+    """评测单条结果并落库；复用逐结果互斥锁避免与重生成并发写冲突。"""
+
+    result_id = str(current["id"])
+    with _claim_result_regeneration(task_id, result_id):
+        quality = evaluate_result_record(
+            {
+                "instruction": current.get("instruction"),
+                "input": current.get("input"),
+                "output": current.get("output"),
+                "chosen": current.get("chosen"),
+                "rejected": current.get("rejected"),
+            },
+            source_content=source_content,
+            model=evaluation_model,
+            config=config,
+            client=model_client,
+            min_output_length=minimum,
+        )
+        return store.update_result(
+            task_id,
+            result_id,
+            {
+                "quality_score": quality,
+                "expected_updated_at": expected_updated_at,
+            },
+        )
+
+
 @router.post("/{task_id}/results/regenerate-batch")
 def regenerate_results_batch(
     task_id: str,
@@ -2439,6 +2485,186 @@ def regenerate_results_batch(
         )
 
 
+@router.post("/{task_id}/results/evaluate-batch")
+def evaluate_results_batch(
+    task_id: str,
+    payload: ResultBatchEvaluateRequest,
+    store: DataProcessStore = Depends(get_data_process_store),
+) -> dict[str, Any]:
+    """对一批结果执行三层质量评测（规则+语义+评审），允许部分成功。"""
+
+    started_at = time.perf_counter()
+    batch_id = new_id("dpeb")
+    with api_errors():
+        task = store.get_task(task_id)
+        if task.get("status") == "running":
+            raise ConflictError("data process task is running")
+        if task.get("output_dataset_id"):
+            raise InvalidStateError("published results cannot be evaluated")
+        config = task.get("config") or {}
+        evaluation_model: dict[str, Any] | None = None
+        model_id = _value(config, "generation_model_id", "generationModelId", None)
+        if model_id:
+            try:
+                evaluation_model = store.get_generation_model(str(model_id))
+            except NotFoundError:
+                logger.warning(
+                    "data process evaluation model unavailable, judge layer "
+                    "skipped task_id=%s model_id=%s",
+                    task_id,
+                    model_id,
+                )
+        evaluation_config = {
+            **config,
+            "output_type": str(
+                _value(config, "output_type", "outputType", "standard")
+            ).strip().lower(),
+        }
+        minimum = max(
+            1,
+            int(_value(config, "min_output_length", "minOutputLength", 20) or 20),
+        )
+
+        prepared: list[tuple[int, dict[str, Any], str, str]] = []
+        failures: list[tuple[int, dict[str, str]]] = []
+        for index, requested in enumerate(payload.items):
+            try:
+                current = store.get_result(task_id, requested.result_id)
+                if requested.expected_updated_at != str(current.get("updated_at") or ""):
+                    raise ConflictError("data process result was modified by another request")
+                source_content = ""
+                preview_id = current.get("preview_item_id")
+                if preview_id:
+                    preview = store.get_preview_item(task_id, str(preview_id))
+                    source_content = str(
+                        preview.get("edited_content")
+                        or preview.get("original_content")
+                        or ""
+                    )
+                prepared.append(
+                    (index, current, source_content, requested.expected_updated_at)
+                )
+            except ConflictError as exc:
+                failures.append((index, {
+                    "result_id": requested.result_id,
+                    "code": "conflict",
+                    "message": _safe_regeneration_error(exc),
+                }))
+            except (NotFoundError, InvalidStateError) as exc:
+                failures.append((index, {
+                    "result_id": requested.result_id,
+                    "code": "skipped",
+                    "message": _safe_regeneration_error(exc),
+                }))
+
+        logger.info(
+            "data process result batch evaluation started batch_id=%s task_id=%s "
+            "requested=%s prepared=%s judge_enabled=%s",
+            batch_id,
+            task_id,
+            len(payload.items),
+            len(prepared),
+            evaluation_model is not None,
+        )
+        successes: list[tuple[int, dict[str, Any]]] = []
+        if prepared:
+            try:
+                from app.modules.data_process.algorithms.embedding import (
+                    semantic_embedding_model,
+                )
+
+                semantic_embedding_model()
+            except Exception:
+                logger.warning(
+                    "data process semantic embedding unavailable, semantic layer "
+                    "will be skipped batch_id=%s",
+                    batch_id,
+                )
+            request_timeout = _result_regeneration_timeout(config)
+            model_timeout = httpx.Timeout(
+                request_timeout,
+                connect=min(10.0, request_timeout),
+            )
+            model_limits = httpx.Limits(
+                max_connections=RESULT_REGENERATION_CONCURRENCY,
+                max_keepalive_connections=RESULT_REGENERATION_CONCURRENCY,
+            )
+            with httpx.Client(timeout=model_timeout, limits=model_limits) as model_client, \
+                    ThreadPoolExecutor(
+                        max_workers=min(RESULT_REGENERATION_CONCURRENCY, len(prepared)),
+                        thread_name_prefix="data-result-evaluation",
+                    ) as executor:
+                futures = {
+                    executor.submit(
+                        _evaluate_result_in_place,
+                        task_id,
+                        current,
+                        source_content,
+                        evaluation_config,
+                        evaluation_model,
+                        store,
+                        expected_updated_at=expected_updated_at,
+                        model_client=model_client if evaluation_model else None,
+                        minimum=minimum,
+                    ): (index, str(current["id"]), time.perf_counter())
+                    for index, current, source_content, expected_updated_at in prepared
+                }
+                for future in as_completed(futures):
+                    index, result_id, item_started_at = futures[future]
+                    try:
+                        evaluated = future.result()
+                        successes.append((index, evaluated))
+                        outcome = "succeeded"
+                    except ConflictError as exc:
+                        outcome = "conflict"
+                        failures.append((index, {
+                            "result_id": result_id,
+                            "code": outcome,
+                            "message": _safe_regeneration_error(exc),
+                        }))
+                    except Exception as exc:
+                        outcome = "evaluation_failed"
+                        failures.append((index, {
+                            "result_id": result_id,
+                            "code": outcome,
+                            "message": _safe_regeneration_error(exc),
+                        }))
+                    logger.info(
+                        "data process result batch evaluation item finished "
+                        "batch_id=%s task_id=%s result_id=%s outcome=%s duration_ms=%.2f",
+                        batch_id,
+                        task_id,
+                        result_id,
+                        outcome,
+                        (time.perf_counter() - item_started_at) * 1000,
+                    )
+
+        success_items = [item for _, item in sorted(successes, key=lambda pair: pair[0])]
+        failure_items = [item for _, item in sorted(failures, key=lambda pair: pair[0])]
+        duration_ms = (time.perf_counter() - started_at) * 1000
+        logger.info(
+            "data process result batch evaluation completed batch_id=%s task_id=%s "
+            "succeeded=%s failed=%s duration_ms=%.2f",
+            batch_id,
+            task_id,
+            len(success_items),
+            len(failure_items),
+            duration_ms,
+        )
+        return ok(
+            {
+                "batch_id": batch_id,
+                "total": len(payload.items),
+                "succeeded": len(success_items),
+                "failed": len(failure_items),
+                "duration_ms": round(duration_ms, 2),
+                "items": success_items,
+                "failures": failure_items,
+            },
+            "data process results evaluated",
+        )
+
+
 @router.post("/{task_id}/results/{result_id}/regenerate")
 def regenerate_result(
     task_id: str,