fix(question_gen): check_verbatim covers question_text + add missing blacklist patterns

- check_verbatim now computes n-gram overlap for BOTH question_text and
  correct_option vs source texts, returning max(question_ratio, option_ratio).
  Extracted _ngram_overlap_ratio helper for reuse.

- Added 4 missing blacklist patterns: 'this segment', 'this frame',
  'the current frame', 'frame summary'.

- Added 5 new test cases covering the above changes.

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

tests/unit/test_postprocess.py

@@ -122,6 +122,31 @@ class TestReferentBlacklist:
         violations = check_referent_blacklist(q)
         assert len(violations) >= 1
 
+    def test_this_segment_caught(self) -> None:
+        """'this segment' 被检测为违规。"""
+        q = "What action is performed in this segment?"
+        violations = check_referent_blacklist(q)
+        assert len(violations) >= 1
+        assert any("this segment" in v.lower() for v in violations)
+
+    def test_this_frame_caught(self) -> None:
+        """'this frame' 被检测为违规。"""
+        q = "What object is visible in this frame?"
+        violations = check_referent_blacklist(q)
+        assert len(violations) >= 1
+
+    def test_current_frame_caught(self) -> None:
+        """'the current frame' 被检测为违规。"""
+        q = "Based on the current frame, what is happening?"
+        violations = check_referent_blacklist(q)
+        assert len(violations) >= 1
+
+    def test_frame_summary_caught(self) -> None:
+        """'frame summary' 被检测为违规。"""
+        q = "According to the frame summary, what is the main event?"
+        violations = check_referent_blacklist(q)
+        assert len(violations) >= 1
+
 
 # ---------------------------------------------------------------------------
 # TestVerbatim
@@ -186,6 +211,21 @@ class TestVerbatim:
         )
         assert ratio == 0.0
 
+    def test_question_text_overlap_detected(self) -> None:
+        """题目文本从来源复制但选项原创时，仍检测到高重叠率。"""
+        source = "The man walked slowly through the crowded market buying fresh vegetables"
+        # 题目直接复制来源的大部分内容
+        question = "The man walked slowly through the crowded market buying what?"
+        # 选项完全原创
+        option = "A. Fresh organic produce from the local farm stand"
+        ratio = check_verbatim(
+            question_text=question,
+            correct_option=option,
+            source_texts=[source],
+            window=6,
+        )
+        assert ratio > 0.0, "题目文本的逐字重叠应被检测到"
+
 
 # ---------------------------------------------------------------------------
 # TestTimeAnchor