feat: expandable previews, KaTeX rendering, variant speedup, batch import

- Analytics/Similar: expandable question preview with KaTeX rendering
- KaTeXRenderer: auto markdown-to-HTML (code blocks, tables, bold), auto Unicode→LaTeX
- ErrorBook: full question text rendering instead of truncated preview
- Variant: remove hint/solution from generation (faster), async, fix null crash
- Grading: add max_tokens limit
- JSON parser: robust multi-layer repair + JSONDecodeError retry
- Extraction prompt: enforce LaTeX notation for math
- Upload: redirect to home instead of blank paper page
- ProcessingBanner: add ETA time estimate + percentage
- Batch import script + handoff guide for team

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/app/routers/analytics.py

@@ -230,6 +230,7 @@ async def get_course_analytics(course_code: str):
             "source": source_label,
             "question_number": question["question_number"],
             "preview": question["question_text"][:220],
+            "full_text": question["question_text"],
             "difficulty": question.get("difficulty"),
             "question_type": question_type,
             "year": paper.get("year"),

backend/app/routers/questions.py

@@ -133,7 +133,7 @@ async def create_variant(question_id: str, user_id: str = Depends(get_current_us
         raise HTTPException(status_code=404, detail="Question not found")
 
     question = result.data[0]
-    variant_data = await asyncio.to_thread(generate_variant, question)
+    variant_data = await generate_variant(question)
     variant_data["knowledge_reminder"] = question.get("knowledge_reminder", "")
 
     saved = sb.table("question_variants").insert({

backend/app/services/grader.py

@@ -68,9 +68,7 @@ Return JSON:
   "question_text": "HTML formatted variant question",
   "question_type": "{question_type}",
   "options": [MC only, format {{"label":"A","text":"..."}}, ...] or null,
-  "correct_answer": "Correct answer (plain text)",
-  "ai_hint": "HTML formatted hint that guides thinking WITHOUT giving the answer",
-  "solution": "HTML formatted complete step-by-step solution"
+  "correct_answer": "Correct answer (plain text)"
 }}"""
 
 
@@ -90,7 +88,7 @@ def ocr_photo(photo_bytes: bytes) -> str:
             ]},
         ],
         temperature=0,
-        max_tokens=2000,
+        max_tokens=1500,
     )
     return resp.choices[0].message.content or ""
 
@@ -114,13 +112,15 @@ def grade_answer(question: dict, student_answer: str) -> dict:
             )},
         ],
         temperature=0.2,
+        max_tokens=2048,
         response_format={"type": "json_object"},
     )
     return json.loads(resp.choices[0].message.content)
 
 
-def generate_variant(question: dict) -> dict:
-    """Gemini generates a variant question"""
+async def generate_variant(question: dict) -> dict:
+    """DeepSeek generates a variant question (async)"""
+    import asyncio
     answer = (
         question.get("correct_option")
         or question.get("correct_answer")
@@ -129,18 +129,20 @@ def generate_variant(question: dict) -> dict:
     )
 
     ds = get_deepseek_client()
-    resp = ds.chat.completions.create(
+    prompt = VARIANT_PROMPT.format(
+        question_type=question["question_type"],
+        question_text=question["question_text"],
+        topics=", ".join(question.get("topics", [])),
+        difficulty=question.get("difficulty", "medium"),
+        answer=answer,
+    )
+
+    resp = await asyncio.to_thread(
+        ds.chat.completions.create,
         model="deepseek-chat",
-        messages=[
-            {"role": "system", "content": VARIANT_PROMPT.format(
-                question_type=question["question_type"],
-                question_text=question["question_text"],
-                topics=", ".join(question.get("topics", [])),
-                difficulty=question.get("difficulty", "medium"),
-                answer=answer,
-            )},
-        ],
+        messages=[{"role": "system", "content": prompt}],
         temperature=0.5,
+        max_tokens=2048,
         response_format={"type": "json_object"},
     )
     return json.loads(resp.choices[0].message.content)

backend/app/services/paper_processor.py

@@ -35,6 +35,8 @@ CRITICAL RULES for question_text:
 - For sub-questions (e.g. (a)(i)), copy the ENTIRE parent question setup (variable definitions, code blocks, problem description) into the question_text, then append the specific sub-question.
 - For Python/code questions: include ALL variable definitions and import statements verbatim, exactly as they appear in the exam, preserving multi-line arrays and data structures completely.
 - Never truncate code. If a variable is defined across multiple lines (e.g. a numpy array), include every line.
+- CRITICAL: ALL mathematical expressions, formulas, variables, and symbols MUST use LaTeX notation. Wrap inline math with $...$ and display math with $$...$$. NEVER use Unicode symbols like σ, μ, π, ², ≥, ≤, √, ∑, etc. Use $\sigma$, $\mu$, $\pi$, $^2$, $\geq$, $\leq$, $\sqrt{}$, $\sum$, etc. Every fraction should be $\frac{a}{b}$, every subscript $x_i$, every superscript $x^n$.
+- Code blocks must use markdown fenced code blocks (```python ... ```).
 
 Output JSON format (strictly follow):
 {
@@ -203,6 +205,8 @@ RETRYABLE_ERROR_MARKERS = (
 
 
 def is_retryable_error(exc: Exception) -> bool:
+    if isinstance(exc, json.JSONDecodeError):
+        return True  # LLM returned bad JSON, retry may fix it
     message = str(exc).lower()
     return any(marker in message for marker in RETRYABLE_ERROR_MARKERS)
 
@@ -221,17 +225,51 @@ def pdf_to_images(pdf_bytes: bytes, dpi: int = 96) -> list[str]:
 
 
 def parse_json_response(text: str) -> dict:
-    """解析模型返回的 JSON，兼容 markdown 代码块包装"""
+    """解析模型返回的 JSON，兼容各种格式问题"""
     text = text.strip()
-    # 去掉 ```json ... ``` 包装
+
+    # 1. 去掉 ```json ... ``` 包装
     if text.startswith("```"):
         lines = text.splitlines()
         text = "\n".join(lines[1:-1] if lines[-1].strip() == "```" else lines[1:])
-    # 移除 JSON 字符串中的非法控制字符（0x00-0x1F 除了 \t \n \r）
+
+    # 2. 如果不以 { 开头，尝试找到第一个 {
+    idx = text.find("{")
+    if idx > 0:
+        text = text[idx:]
+    # 找到最后一个 } 截断尾部垃圾
+    ridx = text.rfind("}")
+    if ridx > 0:
+        text = text[:ridx + 1]
+
+    # 3. 移除所有非法控制字符（0x00-0x1F 除了 \t \n \r）
     text = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', text)
-    # 修复模型返回的无效 JSON 转义序列：只修奇数个反斜杠后的非法字符
-    text = re.sub(r'(?<!\\)((?:\\\\)*)\\([^"\\/bfnrtu])', r'\1\\\\\2', text)
-    return json.loads(text)
+
+    # 4. 修复无效 JSON 转义：LaTeX 如 \sqrt, \sigma 等
+    text = re.sub(r'(?<!\\)((?:\\\\)*)\\([^"\\/bfnrtu\n])', r'\1\\\\\2', text)
+
+    # 5. 尝试解析
+    try:
+        return json.loads(text)
+    except json.JSONDecodeError:
+        pass
+
+    # 6. 更激进的修复：移除所有控制字符包括 \t
+    text = re.sub(r'[\x00-\x1f]', lambda m: ' ' if m.group() in '\t\n\r' else '', text)
+
+    # 7. 修复未终止的字符串：在行尾补引号
+    text = re.sub(r'(?<!\\)"([^"]*)\n', r'"\1\\n"\n', text)
+
+    try:
+        return json.loads(text)
+    except json.JSONDecodeError:
+        pass
+
+    # 8. 最后一搏：用 strict=False 解析
+    try:
+        return json.loads(text, strict=False)
+    except json.JSONDecodeError:
+        raise
 
 
 async def gemini_vision_json(