Update app.py

app.py

@@ -51,7 +51,7 @@ Generate a single Markdown document. For each (sub-)question, output a structure
 """
     },
 
-    "GRADING_PROMPT": {
+  "GRADING_PROMPT": {
     "role": "system",
     "content": """Developer: You are an official examiner. Apply the following grading rules precisely.
 
@@ -60,17 +60,19 @@ Generate a single Markdown document. For each (sub-)question, output a structure
 - Award marks for correct methods (M), accurate answers (A), and clear reasoning (R) as specified.
 - Use Follow Through (FT) for correctly applied subsequent working that uses a previously incorrect answer.
 - Clearly indicate any lost marks and provide a concise reason for the deduction.
-- Always also explain the **correct answer or correct method** when a mistake is made, so the student learns what should have been done.
+- Always state both:
+  1. **What was wrong** (explain the error).
+  2. **What is right** (give the correct value, method, or reasoning from the markscheme).
 - Check for alternative valid methods and award marks accordingly.
 - Summarize the total marks and classify the types of errors made by the student.
 - Ensure the final output adheres to the specified Markdown table format.
 
 ### Abbreviations:
-- **M**: Method mark
-- **A**: Accuracy mark
-- **R**: Reasoning mark
-- **AG**: Answer given in question—no marks awarded
-- **FT**: Follow Through (carry forward a previous mistake if method is correct)
+- **M**: Marks for demonstrating a correct Method.
+- **A**: Marks for providing an accurate Answer.
+- **R**: Marks for clear Reasoning.
+- **AG**: Answer is given in the question—no marks awarded.
+- **FT**: Follow Through; award marks when candidates continue with their own previous (possibly incorrect) answers.
 
 ---
 ## Grading Instructions
@@ -93,17 +95,12 @@ Produce a GitHub-flavored Markdown table:
 Rules:
 - Each row matches a markable step.
 - For blanks, write “(no answer)” and indicate the lost mark(s).
-- Lost marks: wrap in red with `<span style="color:red">A0</span>` (or M0, R0) and make Reason column red.  
-  The reason must say BOTH what went wrong **and** what the correct answer/method is.  
-  Example: `<span style="color:red">Incorrectly calculated (3×10⁴)³ as 3×10¹². Correct answer is 27×10¹².</span>`
+- Lost marks: wrap in red with `<span style="color:red">A0</span>` (or M0, R0) and make Reason column red.
 - Awarded marks remain plain text.
 - For partial awards (e.g., M1A0A1), only highlight lost marks.
+- **When a mark is lost, the Reason column must explain both the error AND the correct answer or method from the markscheme.**
 
-**Formatting Rule (Question Headers):**  
-- At the start of each question or sub-question section, output a dark black bold header using:  
-  `<span style="font-weight:900; color:black">## Question 1(b)(ii)</span>`
-
-**New Rule (Per-Question Total):**  
+**New Rule (Per-Question Total):**
 - After each question (including all subparts), show marks obtained vs total in square brackets, e.g.:  
   `[2/4]`
 
@@ -137,8 +134,6 @@ Optionally, if reasons are available, extend with:
 """
 }
 
-}
-
 # -------------------- CONFIG --------------------
 genai.configure(api_key=os.getenv("GEMINI_API_KEY"))