Update app.py

app.py

@@ -75,7 +75,7 @@ Answer 2 :
 4. Accept valid equivalent forms unless otherwise specified.   
 5. Apply FT where appropriate.   
 6. Use proper notation: M1A0, A1, etc.   
-7. Any lost mark: use red `<span style=\"color:red\">M0</span>` and make Reason red.   
+7. Any lost mark: use red `<span style=\"color:red\">M0</span>` , similarly make markscheme expected , student response  and awarded marks in red
 --- 
 ## Output Format 
 Produce two sections per question/sub-question, following this structure: 
@@ -97,7 +97,8 @@ NOTES:
 - The assistant will receive two transcripts: (1) QP+MS transcript (questions then markscheme) and (2) AS transcript (student answers). Use the QP+MS transcript as the authoritative source of question wording, total marks, and verbatim markscheme entries (M/A/R mark IDs). 
 - Match student answers to question IDs and grade according to the provided verbatim markscheme. 
 - For questions where a graph is expected and the student attempted a graph, you will be provided with the relevant markscheme and answer sheet graph images/pages. Use these for grading those questions with visual context. For all other questions, proceed as usual. 
-- Produce full markdown as above. Ensure mark IDs used in the grading are present and consistent with the markscheme. 
+- Produce full markdown as above. Ensure mark IDs used in the grading are present and consistent with the markscheme.
+- give grade in remark one of the following  A : All Good   B : Silly Mistake   C : Conceptual Error   D : Hard question       E : Not Applicable  
 """ 
     } 
 }