Update OS evals

desktop_env/evaluators/metrics/general.py

@@ -16,6 +16,11 @@ from .utils import _match_record, _match_value_to_rule
 
 import sqlite3
 
+def check_include_exclude(result: str, rules: Dict[str, List[str]]) -> float:
+    include = rules.get("include", [])
+    exclude = rules.get("exclude", [])
+    return all(r in result for r in include) and all(r not in result for r in exclude)
+
 def exact_match(result, rules) -> float:
     expect = rules["expected"]
     print(result, expect)
@@ -195,3 +200,4 @@ def check_json(result: str, rules: Dict[str, List[Dict[str, Union[List[str], str
             value = value[k]
         metric = metric and not _match_value_to_rule(value, r)
     return metric
+