added winning changes

__init__.py

@@ -1,7 +1,7 @@
 """Public package exports for python_code_review_env."""
 
 from .client import PythonCodeReviewEnv, PythonEnv
-from .models import (
+from .openenv_models import (
     PythonAction,
     PythonCodeReviewAction,
     PythonCodeReviewObservation,

client.py

@@ -7,7 +7,7 @@ from typing import Dict
 from openenv.core import EnvClient
 from openenv.core.client_types import StepResult
 
-from .models import (
+from .openenv_models import (
     PythonCodeReviewAction,
     PythonCodeReviewObservation,
     PythonCodeReviewState,

graders/bug_fix.py

@@ -3,10 +3,10 @@
 from __future__ import annotations
 
 try:
-    from ..models import TaskGrade
+    from ..openenv_models import TaskGrade
     from ..tasks.catalog import ReviewTask
 except ImportError:
-    from models import TaskGrade
+    from openenv_models import TaskGrade
     from tasks.catalog import ReviewTask
 
 from .shared import (

graders/dispatch.py

@@ -3,10 +3,10 @@
 from __future__ import annotations
 
 try:
-    from ..models import TaskGrade
+    from ..openenv_models import TaskGrade
     from ..tasks.catalog import ReviewTask
 except ImportError:
-    from models import TaskGrade
+    from openenv_models import TaskGrade
     from tasks.catalog import ReviewTask
 
 from .bug_fix import grade_bug_fix_task

graders/optimization.py

@@ -3,10 +3,10 @@
 from __future__ import annotations
 
 try:
-    from ..models import TaskGrade
+    from ..openenv_models import TaskGrade
     from ..tasks.catalog import ReviewTask
 except ImportError:
-    from models import TaskGrade
+    from openenv_models import TaskGrade
     from tasks.catalog import ReviewTask
 
 from .shared import (

graders/shared.py

@@ -11,10 +11,10 @@ import traceback
 from typing import Any, Callable, Dict, List
 
 try:
-    from ..models import TaskGrade
+    from ..openenv_models import TaskGrade
     from ..tasks.catalog import CallCase, ReviewTask
 except ImportError:
-    from models import TaskGrade
+    from openenv_models import TaskGrade
     from tasks.catalog import CallCase, ReviewTask
 
 

graders/syntax.py

@@ -3,10 +3,10 @@
 from __future__ import annotations
 
 try:
-    from ..models import TaskGrade
+    from ..openenv_models import TaskGrade
     from ..tasks.catalog import ReviewTask
 except ImportError:
-    from models import TaskGrade
+    from openenv_models import TaskGrade
     from tasks.catalog import ReviewTask
 
 from .shared import (

inference.py

@@ -28,7 +28,7 @@ except Exception:
     PythonCodeReviewEnvironment = None  # type: ignore[assignment]
 
 try:
-    from models import PythonCodeReviewAction
+    from openenv_models import PythonCodeReviewAction
 except Exception:
     PythonCodeReviewAction = None  # type: ignore[assignment]
 

server/app.py

@@ -15,11 +15,11 @@ except Exception:
     gr = None  # type: ignore[assignment]
 
 try:
-    from ..models import PythonCodeReviewAction, PythonCodeReviewObservation
+    from ..openenv_models import PythonCodeReviewAction, PythonCodeReviewObservation
     from .env import PythonCodeReviewEnvironment
     from .demo import build_demo
 except ImportError:
-    from models import PythonCodeReviewAction, PythonCodeReviewObservation
+    from openenv_models import PythonCodeReviewAction, PythonCodeReviewObservation
     from server.env import PythonCodeReviewEnvironment
     from server.demo import build_demo
 

server/env.py

@@ -11,7 +11,7 @@ from openenv.core.env_server.types import EnvironmentMetadata
 try:
     from ..graders import grade_task
     from ..graders.shared import component_score, safe_ratio, strict_score
-    from ..models import (
+    from ..openenv_models import (
         HistoryEntry,
         PythonCodeReviewAction,
         PythonCodeReviewObservation,
@@ -23,7 +23,7 @@ try:
 except ImportError:
     from graders import grade_task
     from graders.shared import component_score, safe_ratio, strict_score
-    from models import (
+    from openenv_models import (
         HistoryEntry,
         PythonCodeReviewAction,
         PythonCodeReviewObservation,

tests/test_scoring.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from graders import grade_task
-from models import PythonCodeReviewAction
+from openenv_models import PythonCodeReviewAction
 from server.env import PythonCodeReviewEnvironment
 from tasks import list_tasks