fix(cntfilter): allow legacy sensitive-word lists over 64 patterns (#2467)

* fix(cntfilter): allow legacy sensitive-word lists over 64 patterns

Legacy sensitive-words.json files shipped ~70 rules. After v4.10.7,
BanWordFilter treated the 64-pattern safe_regex cap as a hard failure
and blocked every message. Raise the cap only on the sensitive-word
path, keep the 50ms CPU budget, and truncate oversized lists with a
one-time warning.

Fixes #2443

* fix(cntfilter): reject oversized sensitive-word lists

---------

Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>

tests/unit_tests/utils/test_safe_regex.py

@@ -53,6 +53,45 @@ async def test_matches_any_rejects_pattern_and_input_amplification():
         )
 
 
+@pytest.mark.asyncio
+async def test_mask_patterns_honors_explicit_pattern_count_cap():
+    patterns = ['a'] * (safe_regex.MAX_PATTERN_COUNT + 6)
+    found, masked = await safe_regex.mask_patterns(
+        patterns,
+        'hello',
+        mask='*',
+        mask_word='',
+        max_pattern_count=len(patterns),
+    )
+    assert found is False
+    assert masked == 'hello'
+
+    with pytest.raises(safe_regex.SafeRegexLimitError):
+        await safe_regex.mask_patterns(
+            patterns,
+            'hello',
+            mask='*',
+            mask_word='',
+        )
+
+
+@pytest.mark.asyncio
+async def test_mask_patterns_rejects_oversized_sequence_before_copying_it():
+    class OversizedPatterns(list):
+        def __iter__(self):
+            raise AssertionError('oversized patterns must not be materialized')
+
+    patterns = OversizedPatterns(['a'] * (safe_regex.MAX_PATTERN_COUNT + 1))
+
+    with pytest.raises(safe_regex.SafeRegexLimitError):
+        await safe_regex.mask_patterns(
+            patterns,
+            'hello',
+            mask='*',
+            mask_word='',
+        )
+
+
 @pytest.mark.asyncio
 async def test_mask_patterns_bounds_replacement_growth_and_masks_matches():
     found, masked = await safe_regex.mask_patterns(