feat(question_gen): AnchorContext + 12 题型-层级映射常量

- AnchorContext frozen dataclass: 锚节点生成上下文（node_id, card_text, frame_paths, subtitle, distractor_texts） - TaskTypeSpec frozen dataclass: 题型生成规格（level, needs_frames, frame_count, context_fields） - TASK_TYPE_LEVEL_MAP: 12 种 Video-MME 题型 → 树层级 + 生成规格映射 - 11 项单元测试覆盖：映射完整性、值类型、层级合法性、frozen 不变性 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-07-09 05:10:58 -04:00
parent eb15ab315e
commit 9eb9b86954
2 changed files with 202 additions and 0 deletions
@@ -0,0 +1,68 @@
+"""赛题合成核心逻辑 — 节点采样、prompt 构造、去重。
+
+纯函数为主，异步编排仅 generate_one。
+通过 DI 接收 VLMProvider / EmbeddingProvider，不 import adapters/。
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class AnchorContext:
+    """锚节点上下文——生成单道题所需的全部素材。
+
+    属性:
+        node_id: 锚节点 ID。
+        card_text: 锚节点 card 序列化文本。
+        frame_paths: 帧图片路径列表。
+        subtitle: 对应字幕（可空）。
+        distractor_texts: 同视频其他节点摘要（供 VLM 生成干扰项）。
+    """
+
+    node_id: str
+    card_text: str
+    frame_paths: list[str]
+    subtitle: str
+    distractor_texts: list[str]
+
+
+@dataclass(frozen=True)
+class TaskTypeSpec:
+    """题型的生成规格。
+
+    属性:
+        level: 锚定层级（"L3" / "L2" / "L1" / "L1-L2"）。
+        needs_frames: 是否必须提供帧图。
+        frame_count: 帧数范围描述（如 "1", "2-3", "0-1"）。
+        context_fields: 需要提取的 card 字段元组。
+    """
+
+    level: str
+    needs_frames: bool
+    frame_count: str
+    context_fields: tuple[str, ...]
+
+
+# ---------------------------------------------------------------------------
+# 12 种 Video-MME 题型 → 树层级 + 生成规格映射
+# ---------------------------------------------------------------------------
+
+TASK_TYPE_LEVEL_MAP: dict[str, TaskTypeSpec] = {
+    # --- L3 单帧题型 ---
+    "Object Recognition": TaskTypeSpec("L3", True, "1", ("frame_summary",)),
+    "Attribute Perception": TaskTypeSpec("L3", True, "1", ("frame_summary",)),
+    "OCR Problems": TaskTypeSpec("L3", True, "1", ("frame_summary",)),
+    "Spatial Reasoning": TaskTypeSpec("L3", True, "1", ("frame_summary", "spatial_layout")),
+    "Spatial Perception": TaskTypeSpec("L3", True, "1", ("frame_summary",)),
+    # --- L2 多帧 / 事件级题型 ---
+    "Action Recognition": TaskTypeSpec("L2", True, "2-3", ("event_description",)),
+    "Action Reasoning": TaskTypeSpec("L2", True, "2-3", ("event_description",)),
+    "Counting Problem": TaskTypeSpec("L2", True, "2-3", ("event_description",)),
+    "Temporal Perception": TaskTypeSpec("L2", False, "0-1", ("event_description", "time_range")),
+    # --- L1 / 跨层级题型 ---
+    "Temporal Reasoning": TaskTypeSpec("L1", True, "per-L2", ("scene_summary",)),
+    "Information Synopsis": TaskTypeSpec("L1", True, "per-L2", ("scene_summary",)),
+    "Object Reasoning": TaskTypeSpec("L1-L2", True, "per-L2", ("event_description",)),
+}