feat(03-04): retire flat-file settings; wire per-user AI config via DB lookup

- config.py: Remove SETTINGS_FILE, DEFAULT_SYSTEM_PROMPT, DEFAULT_SETTINGS
  constants; add system_prompt, default_ai_provider, default_ai_model to Settings
- services/classifier.py: Add _DEFAULT_SYSTEM_PROMPT module constant; classify_document
  and suggest_topics_for_document accept ai_provider/ai_model kwargs; no longer calls
  storage.load_settings() — uses app_settings defaults with DB-supplied overrides (D-14, D-15)
- services/storage.py: Delete load_settings, save_settings, mask_api_key, settings_masked;
  remove from __all__; remove import copy, json, DEFAULT_SETTINGS, SETTINGS_FILE (D-12)
- tasks/document_tasks.py: _run resolves user.ai_provider/ai_model via session.get(User,
  doc.user_id) and passes through to classifier; task signature unchanged (T-03-19)
- api/settings.py: Deleted — /api/settings endpoint removed (D-12)
- main.py: Remove settings_router import and include_router call
- tests/test_settings.py: Replace all tests with test_settings_endpoint_removed (404, green)
- tests/test_classifier.py: Implement test_per_user_provider, test_celery_task_uses_user_provider,
  test_default_provider_fallback; remove xfail markers (DOC-03, DOC-05)

backend/tasks/document_tasks.py

@@ -52,6 +52,13 @@ async def _run(document_id: str) -> dict:
         if not doc.object_key:
             return {"document_id": document_id, "status": "missing_object"}
 
+        # ── Resolve per-user AI config (D-14, D-15) ────────────────────────────
+        from db.models import User
+        from config import settings as app_settings
+        user = await session.get(User, doc.user_id) if doc.user_id else None
+        ai_provider = (user.ai_provider if user else None) or app_settings.default_ai_provider
+        ai_model = (user.ai_model if user else None) or app_settings.default_ai_model
+
         # ── Step 2: retrieve bytes from MinIO ──────────────────────────────────
         try:
             backend = get_storage_backend()
@@ -77,7 +84,7 @@ async def _run(document_id: str) -> dict:
 
         # ── Step 4: classify document (non-fatal) ──────────────────────────────
         try:
-            topics = await classifier.classify_document(session, document_id)
+            topics = await classifier.classify_document(session, document_id, ai_provider=ai_provider, ai_model=ai_model)
             return {
                 "document_id": document_id,
                 "status": "classified",