From 0d0f275134148f3d1628aa777bd5932f3a559d90 Mon Sep 17 00:00:00 2001
From: iomgaa <iomgaaycz@gmail.com>
Date: Sun, 12 Jul 2026 22:33:49 -0400
Subject: [PATCH] feat(core): add PoolConfig dataclass for pool strategy
 configuration

---
 core/types.py                 | 34 +++++++++++++++++++++++++
 tests/unit/test_core_types.py | 47 ++++++++++++++++++++++++++++++++++-
 2 files changed, 80 insertions(+), 1 deletion(-)

diff --git a/core/types.py b/core/types.py
index 54908b3..5bed83e 100644
--- a/core/types.py
+++ b/core/types.py
@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
+from pathlib import Path as _Path
 
 
 @dataclass(frozen=True)
@@ -55,3 +56,36 @@ class GeneratedQuestion:
     difficulty: str
     skill_target: str | None = field(default=None)
     difficulty_steps: int | None = field(default=None)
+
+
+@dataclass(frozen=True)
+class PoolConfig:
+    """池构建策略的统一配置。
+
+    两组字段由两个具体策略各取所需，未使用的字段被忽略。
+
+    属性:
+        task_types: 限定题型元组；None 表示全部类别。
+        seed: 随机种子，保证可复现。
+        baseline_run_id: 基线 run 标识。
+        diag_size: 诊断池大小（GlobalStrategy 用）。
+        diag_correct_ratio: 诊断池中对题占比（GlobalStrategy 用）。
+        val_size: 验证池大小（GlobalStrategy 用）。
+        val_correct_ratio: 验证池中对题占比（GlobalStrategy 用）。
+        test_size: held-out 测试池大小（GlobalStrategy 用）。
+        eval_min_per_class: 验证池中每类保底样本数（GlobalStrategy 用）。
+        train_ratio: train/(train+val) 比例（PerCategoryStrategy 用）。
+        test_questions_dir: 外部 test 题源路径（PerCategoryStrategy 用）。
+    """
+
+    task_types: tuple[str, ...] | None
+    seed: int
+    baseline_run_id: str
+    diag_size: int
+    diag_correct_ratio: float
+    val_size: int
+    val_correct_ratio: float
+    test_size: int
+    eval_min_per_class: int
+    train_ratio: float
+    test_questions_dir: _Path | None
diff --git a/tests/unit/test_core_types.py b/tests/unit/test_core_types.py
index 0439f02..ee2aa3f 100644
--- a/tests/unit/test_core_types.py
+++ b/tests/unit/test_core_types.py
@@ -2,9 +2,11 @@
 
 from __future__ import annotations
 
+from pathlib import Path
+
 import pytest
 
-from core.types import GeneratedQuestion, LLMResponse
+from core.types import GeneratedQuestion, LLMResponse, PoolConfig
 
 
 class TestLLMResponse:
@@ -98,3 +100,46 @@ class TestGeneratedQuestion:
 
     def test_source_nodes_is_tuple(self, sample_question: GeneratedQuestion) -> None:
         assert isinstance(sample_question.source_nodes, tuple)
+
+
+class TestPoolConfig:
+    """PoolConfig frozen dataclass 基本行为。"""
+
+    def test_pool_config_frozen(self) -> None:
+        """PoolConfig 创建后不可变。"""
+        cfg = PoolConfig(
+            task_types=("Action Reasoning",),
+            seed=42,
+            baseline_run_id="baseline_v2",
+            diag_size=200,
+            diag_correct_ratio=0.5,
+            val_size=30,
+            val_correct_ratio=0.5,
+            test_size=60,
+            eval_min_per_class=2,
+            train_ratio=0.667,
+            test_questions_dir=Path("store/questions/benchmarks/Video-MME"),
+        )
+        assert cfg.task_types == ("Action Reasoning",)
+        assert cfg.baseline_run_id == "baseline_v2"
+        assert cfg.train_ratio == 0.667
+        with pytest.raises(AttributeError):
+            cfg.seed = 1
+
+    def test_pool_config_task_types_none(self) -> None:
+        """task_types=None 表示全部类别。"""
+        cfg = PoolConfig(
+            task_types=None,
+            seed=0,
+            baseline_run_id="run_1",
+            diag_size=200,
+            diag_correct_ratio=0.5,
+            val_size=30,
+            val_correct_ratio=0.5,
+            test_size=60,
+            eval_min_per_class=2,
+            train_ratio=0.667,
+            test_questions_dir=None,
+        )
+        assert cfg.task_types is None
+        assert cfg.test_questions_dir is None