feat: wire grounded selector into AR slot processing

将 Task 5 的 grounded selector 织入 AR 出题路径（Phase 3.5，位于
record_item 与 postprocess 之间），仅在 strategy.uses_grounded_selector
为真时进入。observation 始终落库（含 hard-fail），硬失败走重出。
PipelineConfig 新增 candidate_pool_size/selector_delta_low/
selector_delta_high 三参，YAML 与 CLI seed override 同步。

tests/integration/test_pipeline_v2.py

@@ -194,8 +194,15 @@ class MockVLM:
         parent_call_id: str | None = None,
     ) -> LLMResponse:
         prompt_text = str(messages)
+        system_text = messages[0].get("content", "") if messages else ""
         if "verdict" in prompt_text.lower():
             return _make_llm_response(self._gate_response)
+        if "distractor" in system_text.lower() and "grader" not in system_text.lower():
+            # 候选池请求：返回 4 个 grounded 干扰项
+            return _make_llm_response('{"distractors": ["蒸", "煮", "炸", "烤"]}')
+        if "grader" in system_text.lower():
+            # 打分请求：正解高分、3 个落区间、1 个负空间
+            return _make_llm_response('{"scores": [0.90, 0.80, 0.70, 0.60, 0.20]}')
         idx = min(self._gen_count, len(self._responses) - 1)
         self._gen_count += 1
         return _make_llm_response(self._responses[idx])

tests/unit/test_pipeline_selector_wiring.py

@@ -0,0 +1,42 @@
+"""selector 织入辅助：正解文本提取 + 分流。"""
+
+import pytest
+
+from app.question_gen.pipeline_v2 import _extract_correct_text
+
+
+def test_extract_correct_text_strips_prefix():
+    options = ("A. 蒸", "B. 炒", "C. 煮", "D. 炸")
+    assert _extract_correct_text(options, "C") == "煮"
+
+
+def test_extract_correct_text_handles_lowercase_answer():
+    options = ("A. run", "B. walk", "C. jump", "D. sit")
+    assert _extract_correct_text(options, "b") == "walk"
+
+
+def test_extract_correct_text_out_of_range_raises():
+    options = ("A. a", "B. b", "C. c", "D. d")
+    with pytest.raises(ValueError):
+        _extract_correct_text(options, "E")
+
+
+def test_replace_candidate_options():
+    from app.question_gen.generator_v2 import CandidateQuestion
+    from app.question_gen.pipeline_v2 import _replace_candidate_options
+
+    c = CandidateQuestion(
+        question_id="q",
+        video_id="v",
+        task_type="Action Recognition",
+        skill_target="M1_AR",
+        question="?",
+        options=("A. a", "B. b", "C. c", "D. d"),
+        answer="A",
+        source_nodes=("n1",),
+        difficulty="hard",
+    )
+    new = _replace_candidate_options(c, ("A. 蒸", "B. 炒", "C. 煮", "D. 炸"), "A")
+    assert new.options == ("A. 蒸", "B. 炒", "C. 煮", "D. 炸")
+    assert new.question == "?"  # 其余字段不变
+    assert new.source_nodes == ("n1",)