From 1f95c4d1eaf0e59292c1c038f62ceb6c30f95775 Mon Sep 17 00:00:00 2001
From: Daniel <daniel@danvics.com>
Date: Wed, 1 Apr 2026 13:16:43 +0200
Subject: [PATCH] Explanation: capture ALL content verbatim until next question

Updated extraction prompt to be explicit that explanation must include
every section between the correct answer line and the next question:
- Explanation paragraph
- Critique section (if present)
- Learning Points (if present)
- Content Specifications / American Board of Pediatrics specs
- Suggested Reading references
- Any other content

No summarizing, skipping, or shortening of any text.
Keep all section headers verbatim.

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
---
 backend/app/services/ai_service.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/backend/app/services/ai_service.py b/backend/app/services/ai_service.py
index 44a1d2d..9747598 100644
--- a/backend/app/services/ai_service.py
+++ b/backend/app/services/ai_service.py
@@ -33,7 +33,7 @@ Your task: extract every question and return ONLY a JSON object in this exact fo
     "question_type": "mcq",
     "options": ["<option A text>", "<option B text>", "<option C text>", "<option D text>", "<option E text>"],
     "correct_answer": "<full text of the correct option, NOT the letter>",
-    "explanation": "<explanation paragraph>\\n\\nCritique: <critique section verbatim>\\n\\nContent Specifications: <content spec section verbatim>",
+    "explanation": "<ALL text verbatim from after the correct answer line to before the next question — explanation, Critique, Learning Points, Content Specifications, Suggested Reading, everything>",
     "page_reference": {page_ref}
   }}
 ]}}
@@ -44,9 +44,12 @@ CRITICAL RULES — follow exactly:
    NEVER store just the letter. NEVER guess. If not found, set correct_answer to null.
    Example: options=["alpha","beta","gamma","delta","epsilon"] and "Correct Answer: C" → correct_answer="gamma"
 
-2. EXPLANATION: Copy the explanation paragraph, then the Critique section, then Content Specifications
-   ALL VERBATIM — do NOT summarize, shorten, or paraphrase anything.
-   Format: "<explanation>\\n\\nCritique: <critique verbatim>\\n\\nContent Specifications: <specs verbatim>"
+2. EXPLANATION: Copy EVERYTHING that appears after the correct answer line and before the next question,
+   verbatim and in full — including the explanation paragraph, any Critique section, Learning Points,
+   Content Specifications, American Board of Pediatrics specifications, Suggested Readings, and any
+   other content. Do NOT summarize, shorten, skip, or paraphrase a single word.
+   Keep all section headers (e.g. "Critique:", "Content Specifications:", "Suggested Reading:").
+   The explanation field should be the complete, unaltered text block.
 
 3. QUESTIONS: Extract ALL questions, even if partially cut off.
    A new question starts with "Item NNN" or "ltem NNN" (OCR artifact — lowercase l instead of I).