Update app.py

app.py

@@ -16,14 +16,21 @@ PROMPTS = {
 ## Instructions
 Output must be a valid JSON array, with one object per (sub-)question, in order. 
 Each object must have exactly these keys:
-- "question_number": string (e.g., "1", "1(a)", "2(b)(ii)")
-- "qp": string (exact question text or "[Not found]")
-- "ms": string (relevant markscheme text or "[Not found]")
-- "as": string (final cleaned student answer; "[No response]" or "[illegible]" if needed)
-Rules:
-- Preserve math inside fenced code ```...```.
-- If diagram/graph missing, write "[Graph omitted]".
-- Do not add extra commentary outside JSON.
+- "question_number": string (e.g., "1", "1(a)", "2(b)(ii)")  
+- "qp": string (exact question text or "[Not found]")  
+- "ms": string (relevant markscheme text or "[Not found]")  
+- "as": string (final cleaned student answer; "[No response]" or "[illegible]" if needed)  
+
+### Numbering Rules
+- Always use **logical order of questions** (1, 2, 3, …) regardless of how they are labeled in the PDF.  
+- If the QP shows a mismatch (e.g., under "Question 1" the serial number says "12"), **still treat it as Q1**.  
+- Subparts must be written in standard form (e.g., "1(a)", "1(b)(ii)").  
+
+### Formatting Rules
+- Preserve math inside fenced code ```...```.  
+- If diagram/graph missing, write "[Graph omitted]".  
+- Do not add extra commentary outside JSON.  
+
 ## Example
 [
   {
@@ -39,51 +46,34 @@ Rules:
         "role": "system",
         "content": """Developer: You are an official examiner. Apply the following grading rules precisely.
 ### Abbreviations:
-- **M**: Marks for demonstrating a correct Method.
-- **A**: Marks for providing an accurate Answer; often requires a valid M mark first.
-- **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, provided their later method is correct.
+- **M**: Marks for Method
+- **A**: Marks for Accuracy/Answer
+- **R**: Marks for Reasoning
+- **AG**: Answer given in question—no marks
+- **FT**: Follow Through marks (if error carried forward correctly)
+- **MR**: Deduct for misread (once only)
+
 ---
 ## Grading Instructions
-1. **General Marking**
-   - Award marks using official annotations (e.g., M1, A2).
-   - Do not award full marks for answers alone; check for method marks.
-2. **Method and Answer/Accuracy Marks**
-   - A marks usually require a valid M mark first.
-   - Multiple A marks may be independent unless specified.
-3. **Implied Marks**
-   - Implied M marks can only be given when the method is clearly demonstrated or properly inferred.
-4. **Follow Through (FT) Marks**
-   - Award FT if an earlier mistake is carried forward correctly (unless nonsensical).
-5. **Misread (MR)**
-   - Deduct MR once for consistent misreading.
-6. **Alternative Methods**
-   - Allow valid alternative approaches unless 'Hence' precludes them.
-7. **Alternative Forms**
-   - Accept equivalent algebraic/numeric forms unless otherwise specified.
-8. **Format and Accuracy**
-   - Default accuracy: 3 s.f. unless stated.
-   - Simplify arithmetic/algebra as appropriate.
-9. **Presentation of Work**
-   - Ignore crossed-out work unless stated.
-   - Mark only the first full solution unless otherwise indicated.
-10. **Graphs/Diagrams**
-    - Award marks for correctly executed graphs/diagrams as specified.
+1. Award marks using official annotations (e.g., M1, A2).  
+2. Do not award full marks for answers alone; check for method marks.  
+3. A marks usually require a valid M mark first.  
+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.  
+
 ---
 ## Output Format
-Produce a GitHub-flavored Markdown table with these columns:
-| Student wrote | Marks Awarded | Reason |
-- Each row = one markable step/point in order, following the markscheme.
-- For blanks, write “(no answer)” and mark lost.
-- Use proper notation (M1A0, A1, etc.).
-- Any lost mark (M0, A0, R0, etc.): wrap in red `<span style="color:red">M0</span>` and make the Reason column red.
-- Awarded marks appear plain.
-After the table, provide:
-### Summary & Final Mark
-- Show total marks vs available.
-- Note any FT used.
-- Classify errors (Conceptual, Silly mistake, Misread, etc.).
+1. Produce a GitHub-flavored Markdown table with columns:  
+   | Student wrote | Marks Awarded | Reason |  
+   - Each row = one markable step/point, in order.  
+   - For blanks: “(no answer)” with marks lost.  
+
+2. After the table, write ONLY one line for total marks in the form:  Final Marks: X / Y
+
+⚠️ Do NOT include summaries, error classifications, or extra commentary.  
+Only table + final marks line.  
 """
     }
 }
@@ -222,8 +212,8 @@ def align_and_grade(qp_file, ms_file, ans_file):
             section = f"## Question {qnum}\n\n{grading_piece}"
             grading_sections.append(section)
 
-            # Extract marks from "Summary & Final Mark"
-            match = re.search(r"(\d+)\s*/\s*(\d+)", grading_piece)
+            # Extract marks from "Final Marks: X / Y"
+            match = re.search(r"Final Marks:\s*(\d+)\s*/\s*(\d+)", grading_piece)
             if match:
                 awarded, possible = int(match.group(1)), int(match.group(2))
                 marks_summary.append((qnum, awarded, possible))
@@ -282,3 +272,5 @@ with gr.Blocks(title="LeadIB AI Grading (JSON Alignment + Auto-Grading)") as dem
 
 if __name__ == "__main__":
     demo.launch()
+
+