[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>

klausur-service/backend/dsfa_rag_models.py

@@ -0,0 +1,137 @@
+"""
+DSFA RAG Pydantic Models.
+
+Request/Response models for the DSFA RAG API.
+"""
+
+from typing import List, Optional
+from pydantic import BaseModel, Field
+
+
+# =============================================================================
+# Response Models
+# =============================================================================
+
+class DSFASourceResponse(BaseModel):
+    """Response model for DSFA source."""
+    id: str
+    source_code: str
+    name: str
+    full_name: Optional[str] = None
+    organization: Optional[str] = None
+    source_url: Optional[str] = None
+    license_code: str
+    license_name: str
+    license_url: Optional[str] = None
+    attribution_required: bool
+    attribution_text: str
+    document_type: Optional[str] = None
+    language: str = "de"
+
+
+class DSFAChunkResponse(BaseModel):
+    """Response model for a single chunk with attribution."""
+    chunk_id: str
+    content: str
+    section_title: Optional[str] = None
+    page_number: Optional[int] = None
+    category: Optional[str] = None
+
+    # Document info
+    document_id: str
+    document_title: Optional[str] = None
+
+    # Attribution (always included)
+    source_id: str
+    source_code: str
+    source_name: str
+    attribution_text: str
+    license_code: str
+    license_name: str
+    license_url: Optional[str] = None
+    attribution_required: bool
+    source_url: Optional[str] = None
+    document_type: Optional[str] = None
+
+
+class DSFASearchResultResponse(BaseModel):
+    """Response model for search result."""
+    chunk_id: str
+    content: str
+    score: float
+
+    # Attribution
+    source_code: str
+    source_name: str
+    attribution_text: str
+    license_code: str
+    license_name: str
+    license_url: Optional[str] = None
+    attribution_required: bool
+    source_url: Optional[str] = None
+
+    # Metadata
+    document_type: Optional[str] = None
+    category: Optional[str] = None
+    section_title: Optional[str] = None
+    page_number: Optional[int] = None
+
+
+class DSFASearchResponse(BaseModel):
+    """Response model for search endpoint."""
+    query: str
+    results: List[DSFASearchResultResponse]
+    total_results: int
+
+    # Aggregated licenses for footer
+    licenses_used: List[str]
+    attribution_notice: str
+
+
+class DSFASourceStatsResponse(BaseModel):
+    """Response model for source statistics."""
+    source_id: str
+    source_code: str
+    name: str
+    organization: Optional[str] = None
+    license_code: str
+    document_type: Optional[str] = None
+    document_count: int
+    chunk_count: int
+    last_indexed_at: Optional[str] = None
+
+
+class DSFACorpusStatsResponse(BaseModel):
+    """Response model for corpus statistics."""
+    sources: List[DSFASourceStatsResponse]
+    total_sources: int
+    total_documents: int
+    total_chunks: int
+    qdrant_collection: str
+    qdrant_points_count: int
+    qdrant_status: str
+
+
+class IngestRequest(BaseModel):
+    """Request model for ingestion."""
+    document_url: Optional[str] = None
+    document_text: Optional[str] = None
+    title: Optional[str] = None
+
+
+class IngestResponse(BaseModel):
+    """Response model for ingestion."""
+    source_code: str
+    document_id: Optional[str] = None
+    chunks_created: int
+    message: str
+
+
+class LicenseInfo(BaseModel):
+    """License information."""
+    code: str
+    name: str
+    url: Optional[str] = None
+    attribution_required: bool
+    modification_allowed: bool
+    commercial_use: bool