feat(question_gen): add generate-v2 CLI subcommand and experiment script

- Add generate-v2 subparser with --config, --store-dir, --db-path,
  --seed, and --dry-run arguments to tools/generate_questions.py
- Implement _run_generate_v2 async handler: config loading, video
  discovery, DI client construction, TreeIndex loading, pipeline
  invocation, and result persistence
- Add scripts/generate_questions_v2.sh following build_trees.sh
  conventions (source .env, conda run python path, MODE=mock support)
- Update app/question_gen/__init__.py to export full v2 public API:
  run_pipeline_v2, PipelineConfig, PipelineResult, QuestionFamilySpec,
  ALL_FAMILIES, CandidateQuestion, generate_one_v2, GateReport, run_gates
- Add QuestionGenStore.load_progress() for pipeline resumption
- Add integration tests for CLI help and dry-run behavior
- Update test_question_gen_api to match expanded __all__

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/question_gen/__init__.py

@@ -1,6 +1,10 @@
-"""出题模块 — benchmark 加载、分层采样与赛题合成。"""
+"""出题模块 — benchmark 加载、分层采样、赛题合成与 v2 出题管线。"""
 
+from app.question_gen.families import ALL_FAMILIES, QuestionFamilySpec
+from app.question_gen.gates import GateReport, run_gates
+from app.question_gen.generator_v2 import CandidateQuestion, generate_one_v2
 from app.question_gen.loader import load_benchmark, stratified_sample
+from app.question_gen.pipeline_v2 import PipelineConfig, PipelineResult, run_pipeline_v2
 from app.question_gen.synthesizer import (
     TASK_TYPE_LEVEL_MAP,
     AnchorContext,
@@ -9,10 +13,21 @@ from app.question_gen.synthesizer import (
 )
 
 __all__ = [
+    # v1 接口
     "load_benchmark",
     "stratified_sample",
     "TASK_TYPE_LEVEL_MAP",
     "AnchorContext",
     "generate_one",
     "sample_anchor",
+    # v2 接口
+    "run_pipeline_v2",
+    "PipelineConfig",
+    "PipelineResult",
+    "QuestionFamilySpec",
+    "ALL_FAMILIES",
+    "CandidateQuestion",
+    "generate_one_v2",
+    "GateReport",
+    "run_gates",
 ]

app/question_gen/run_store.py

@@ -380,6 +380,46 @@ class QuestionGenStore:
             heavy_sampled=row[3] or 0,
         )
 
+    def load_progress(self) -> dict[str, str]:
+        """加载已完成 slot 的进度映射（用于断点续跑）。
+
+        从最近一次 running 状态的批次中，读取所有 final_status 非 pending 的 item，
+        聚合为 slot_id → "accepted"|"rejected" 映射。
+
+        若存在同一 slot_id 的多条记录（多次重出），取最终状态:
+        - 任一条 accepted → accepted
+        - 全部 rejected → rejected
+
+        Returns
+        -------
+        dict[str, str]
+            {slot_id: "accepted"|"rejected"} 映射。无进度时返回空 dict。
+        """
+        # 取最近一次未结束的 run_id
+        row = self._conn.execute(
+            "SELECT run_id FROM question_gen_runs WHERE status='running' "
+            "ORDER BY started_at DESC LIMIT 1",
+        ).fetchone()
+
+        if row is None:
+            return {}
+
+        run_id = row[0]
+        rows = self._conn.execute(
+            "SELECT slot_id, final_status FROM question_gen_items "
+            "WHERE run_id=? AND final_status != 'pending'",
+            (run_id,),
+        ).fetchall()
+
+        progress: dict[str, str] = {}
+        for slot_id, status in rows:
+            if status == "accepted":
+                progress[slot_id] = "accepted"
+            elif slot_id not in progress:
+                progress[slot_id] = "rejected"
+
+        return progress
+
     def close(self) -> None:
         """关闭数据库连接。"""
         self._conn.close()