[split-required] Split 700-870 LOC files across all services

backend-lehrer (11 files):
- llm_gateway/routes/schools.py (867 → 5), recording_api.py (848 → 6)
- messenger_api.py (840 → 5), print_generator.py (824 → 5)
- unit_analytics_api.py (751 → 5), classroom/routes/context.py (726 → 4)
- llm_gateway/routes/edu_search_seeds.py (710 → 4)

klausur-service (12 files):
- ocr_labeling_api.py (845 → 4), metrics_db.py (833 → 4)
- legal_corpus_api.py (790 → 4), page_crop.py (758 → 3)
- mail/ai_service.py (747 → 4), github_crawler.py (767 → 3)
- trocr_service.py (730 → 4), full_compliance_pipeline.py (723 → 4)
- dsfa_rag_api.py (715 → 4), ocr_pipeline_auto.py (705 → 4)

website (6 pages):
- audit-checklist (867 → 8), content (806 → 6)
- screen-flow (790 → 4), scraper (789 → 5)
- zeugnisse (776 → 5), modules (745 → 4)

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

backend-lehrer/unit_analytics_helpers.py

@@ -0,0 +1,97 @@
+"""
+Unit Analytics API - Helpers.
+
+Database access, statistical computation, and utility functions.
+"""
+
+import os
+import logging
+from typing import List, Dict, Optional
+
+logger = logging.getLogger(__name__)
+
+# Feature flags
+USE_DATABASE = os.getenv("GAME_USE_DATABASE", "true").lower() == "true"
+
+# Database singleton
+_analytics_db = None
+
+
+async def get_analytics_database():
+    """Get analytics database instance."""
+    global _analytics_db
+    if not USE_DATABASE:
+        return None
+    if _analytics_db is None:
+        try:
+            from unit.database import get_analytics_db
+            _analytics_db = await get_analytics_db()
+            logger.info("Analytics database initialized")
+        except ImportError:
+            logger.warning("Analytics database module not available")
+        except Exception as e:
+            logger.warning(f"Analytics database not available: {e}")
+    return _analytics_db
+
+
+def calculate_gain_distribution(gains: List[float]) -> Dict[str, int]:
+    """Calculate distribution of learning gains into buckets."""
+    distribution = {
+        "< -20%": 0,
+        "-20% to -10%": 0,
+        "-10% to 0%": 0,
+        "0% to 10%": 0,
+        "10% to 20%": 0,
+        "> 20%": 0,
+    }
+
+    for gain in gains:
+        gain_percent = gain * 100
+        if gain_percent < -20:
+            distribution["< -20%"] += 1
+        elif gain_percent < -10:
+            distribution["-20% to -10%"] += 1
+        elif gain_percent < 0:
+            distribution["-10% to 0%"] += 1
+        elif gain_percent < 10:
+            distribution["0% to 10%"] += 1
+        elif gain_percent < 20:
+            distribution["10% to 20%"] += 1
+        else:
+            distribution["> 20%"] += 1
+
+    return distribution
+
+
+def calculate_trend(scores: List[float]) -> str:
+    """Calculate trend from a series of scores."""
+    if len(scores) < 3:
+        return "insufficient_data"
+
+    # Simple linear regression
+    n = len(scores)
+    x_mean = (n - 1) / 2
+    y_mean = sum(scores) / n
+
+    numerator = sum((i - x_mean) * (scores[i] - y_mean) for i in range(n))
+    denominator = sum((i - x_mean) ** 2 for i in range(n))
+
+    if denominator == 0:
+        return "stable"
+
+    slope = numerator / denominator
+
+    if slope > 0.05:
+        return "improving"
+    elif slope < -0.05:
+        return "declining"
+    else:
+        return "stable"
+
+
+def calculate_difficulty_rating(success_rate: float, avg_attempts: float) -> float:
+    """Calculate difficulty rating 1-5 based on success metrics."""
+    # Lower success rate and higher attempts = higher difficulty
+    base_difficulty = (1 - success_rate) * 3 + 1  # 1-4 range
+    attempt_modifier = min(avg_attempts - 1, 1)  # 0-1 range
+    return min(5.0, base_difficulty + attempt_modifier)