feat: is_dev flag for some debugging

Author: HongleiGu

evaluation_function/evaluation.py

@@ -43,5 +43,5 @@ def evaluation_function(
     except Exception as e:
         return LFResult(
             is_correct=False,
-            feedback_items=[("error", f"Invalid FSA format: {str(e)}")]
+            feedback_items=[("error", f"Invalid FSA format: {str(e)}, received: {response}")]
         )

evaluation_function/schemas/params.py

@@ -47,3 +47,8 @@ class Params(BaseModel):
 
     # Test generation
     max_test_length: int = Field(default=10, ge=1, le=50, description="Max length for generated test strings")
+
+    is_dev: bool = Field(
+        default=False,
+        description="Flag indicating if running in development mode"
+    )

evaluation_function/schemas/result.py

@@ -8,6 +8,8 @@
 from enum import Enum
 from pydantic import BaseModel, Field
 
+from evaluation_function.schemas.fsa import FSA
+
 
 class ErrorCode(str, Enum):
     """
@@ -314,3 +316,9 @@ class Result(BaseModel):
         default=None,
         description="Detailed structured feedback with element highlighting for UI"
     )
+
+    # this is dev only
+    input_data: Optional[FSA] = Field(
+        default=None,
+        description="The parsed FSA input data (for development/debugging purposes only)"
+    )