updated

backend/services/report_generator.py

@@ -1,24 +1,3 @@
-"""Utilities for assembling and exporting interview reports.
-
-This module provides two primary helpers used by the recruiter dashboard:
-
-``generate_llm_interview_report(application)``
-    Given a candidate's ``Application`` record, assemble a plain‑text report
-    summarising the interview.  Because the interview process currently
-    executes entirely client‑side and does not persist questions or answers
-    to the database, this report focuses on the information available on
-    the server: the candidate's profile, the job requirements and a skills
-    match score.  Should future iterations store richer interview data
-    server‑side, this function can be extended to include question/answer
-    transcripts, per‑question scores and LLM‑generated feedback.
-
-``create_pdf_report(report_text)``
-    Convert a multi‑line string into a simple PDF.  The implementation
-    leverages Matplotlib's PDF backend (available by default) to avoid
-    heavyweight dependencies such as ReportLab or WeasyPrint, which are
-    absent from the runtime environment.  Text is wrapped and split
-    across multiple pages as necessary.
-"""
 
 from __future__ import annotations
 import json
@@ -341,33 +320,38 @@ def create_pdf_report(report_text: str) -> BytesIO:
             
             y_pos -= 0.5
             
-            # Show first 2-3 Q&As on first page
+            # Show up to 3 Q&As on the first page.  The number actually
+            # displayed depends on available space.  We track how many
+            # questions we render so the remainder can be displayed on
+            # subsequent pages without skipping any entries.
             max_qa_on_page1 = min(3, len(report_data['qa_log']))
-            
+            qa_count_on_page1 = 0
             for i in range(max_qa_on_page1):
                 qa = report_data['qa_log'][i]
                 
-                # Check if we have space
+                # Check if we have space for the next Q&A.  If not, break
+                # early.  The 2.2 constant accounts for the approximate
+                # vertical space needed for a question, answer, evaluation
+                # and some spacing.  If insufficient space remains, we
+                # stop adding to this page.
                 if y_pos < BOTTOM_MARGIN + 2.2:
                     break
                 
-                # Question
-                question_text = f"Q{i+1}: {qa['question']}"
+                # Question number starts at 1 on the first page
+                question_text = f"Q{qa_count_on_page1 + 1}: {qa['question']}"
                 for line in textwrap.wrap(question_text, width=85):
                     ax.text(LEFT_MARGIN, y_pos, line,
                             fontsize=11, fontweight='bold', color=ACCENT_COLOR, fontfamily='sans-serif')
                     y_pos -= 0.25
                 y_pos -= 0.15  # extra spacing after question block
 
-                
-                # Answer
+                # Answer.  Mask salary disclosure if applicable.
                 answer_text = qa['answer']
                 if "salary" in qa['question'].lower() and (answer_text == "0$" or answer_text == "0" or answer_text == "$0"):
                     answer_text = "Prefer not to disclose"
                 
                 wrapped_answer = textwrap.fill(answer_text, width=85)
                 answer_lines = wrapped_answer.split('\n')[:2]  # Max 2 lines
-                
                 for line in answer_lines:
                     ax.text(LEFT_MARGIN + 0.3, y_pos, line,
                             fontsize=10, color=TEXT_COLOR, fontfamily='sans-serif')
@@ -377,22 +361,27 @@ def create_pdf_report(report_text: str) -> BytesIO:
                 eval_color = _get_score_color(qa['score'])
                 ax.text(LEFT_MARGIN + 0.3, y_pos, f"Evaluation: {qa['score']}",
                         fontsize=10, fontweight='bold', color=eval_color, fontfamily='sans-serif')
-                
                 y_pos -= 0.6
+
+                qa_count_on_page1 += 1
         
         # Save first page
         pdf.savefig(fig, bbox_inches='tight', pad_inches=0)
         plt.close(fig)
         
         # === PAGE 2: REMAINING TRANSCRIPT ===
-        if report_data['qa_log'] and len(report_data['qa_log']) > max_qa_on_page1:
+        # Render the remainder of the Q&A log on additional pages.  Use
+        # qa_count_on_page1 (actual number shown on the first page) rather
+        # than the theoretical max_qa_on_page1 so that no entries are
+        # inadvertently skipped when the first page runs out of space.
+        if report_data['qa_log'] and len(report_data['qa_log']) > qa_count_on_page1:
             _create_transcript_page(
                 pdf,
-                report_data['qa_log'][max_qa_on_page1:],  # Continue from the next unanswered question
+                report_data['qa_log'][qa_count_on_page1:],  # Continue from the next unanswered question
                 A4_WIDTH, A4_HEIGHT,
                 LEFT_MARGIN, RIGHT_MARGIN, TOP_MARGIN, BOTTOM_MARGIN,
                 ACCENT_COLOR, TEXT_COLOR,
-                start_index=max_qa_on_page1 + 1  # Correct numbering
+                start_index=qa_count_on_page1 + 1  # Correct numbering
             )
 
     
@@ -444,8 +433,17 @@ def _parse_report_text(report_text: str) -> Dict[str, Any]:
                 data['skills_match']['ratio'] = float(line.split(':')[1].strip().rstrip('%'))
             except:
                 data['skills_match']['ratio'] = 0
-        elif line.startswith('Score:') and 'skills_match' in str(data):
-            data['skills_match']['score'] = line.split(':', 1)[1].strip()
+        elif line.startswith('Score:'):
+            # Distinguish between the overall skills match score and per‑question scores.
+            # If no question has been started yet (i.e. current_question is None),
+            # interpret this Score line as the skills match score.  Otherwise it
+            # belongs to the most recent question.
+            score_value = line.split(':', 1)[1].strip()
+            if current_question is None:
+                data['skills_match']['score'] = score_value
+            else:
+                current_question['score'] = score_value
+            continue
         elif line.startswith('Question'):
             if current_question:
                 data['qa_log'].append(current_question)
@@ -457,8 +455,6 @@ def _parse_report_text(report_text: str) -> Dict[str, Any]:
             }
         elif line.startswith('Answer:') and current_question:
             current_question['answer'] = line.split(':', 1)[1].strip()
-        elif line.startswith('Score:') and current_question:
-            current_question['score'] = line.split(':', 1)[1].strip()
         elif line.startswith('Feedback:') and current_question:
             current_question['feedback'] = line.split(':', 1)[1].strip()