Harden auth and security controls with session auth and docs

backend/app/services/processing_logs.py

@@ -6,10 +6,13 @@ from uuid import UUID
 from sqlalchemy import delete, func, select
 from sqlalchemy.orm import Session
 
+from app.core.config import get_settings
 from app.models.document import Document
 from app.models.processing_log import ProcessingLogEntry
 
 
+settings = get_settings()
+
 MAX_STAGE_LENGTH = 64
 MAX_EVENT_LENGTH = 256
 MAX_LEVEL_LENGTH = 16
@@ -37,9 +40,49 @@ def _trim(value: str | None, max_length: int) -> str | None:
 
 
 def _safe_payload(payload_json: dict[str, Any] | None) -> dict[str, Any]:
-    """Ensures payload values are persisted as dictionaries."""
+    """Normalizes payload persistence mode using metadata-only defaults for sensitive content."""
 
-    return payload_json if isinstance(payload_json, dict) else {}
+    if not isinstance(payload_json, dict):
+        return {}
+    if settings.processing_log_store_payload_text:
+        return payload_json
+    return _metadata_only_payload(payload_json)
+
+
+def _metadata_only_payload(payload_json: dict[str, Any]) -> dict[str, Any]:
+    """Converts payload content into metadata descriptors without persisting raw text values."""
+
+    metadata: dict[str, Any] = {}
+    for index, (raw_key, raw_value) in enumerate(payload_json.items()):
+        if index >= 80:
+            break
+        key = str(raw_key)
+        metadata[key] = _metadata_only_payload_value(raw_value)
+    return metadata
+
+
+def _metadata_only_payload_value(value: Any) -> Any:
+    """Converts one payload value into non-sensitive metadata representation."""
+
+    if isinstance(value, dict):
+        return _metadata_only_payload(value)
+    if isinstance(value, (list, tuple)):
+        items = list(value)
+        return {
+            "item_count": len(items),
+            "items_preview": [_metadata_only_payload_value(item) for item in items[:20]],
+        }
+    if isinstance(value, str):
+        normalized = value.strip()
+        return {
+            "text_chars": len(normalized),
+            "text_omitted": bool(normalized),
+        }
+    if isinstance(value, bytes):
+        return {"binary_bytes": len(value)}
+    if isinstance(value, (int, float, bool)) or value is None:
+        return value
+    return {"value_type": type(value).__name__}
 
 
 def set_processing_log_autocommit(session: Session, enabled: bool) -> None:
@@ -82,8 +125,8 @@ def log_processing_event(
         document_filename=_trim(resolved_document_filename, MAX_DOCUMENT_FILENAME_LENGTH),
         provider_id=_trim(provider_id, MAX_PROVIDER_LENGTH),
         model_name=_trim(model_name, MAX_MODEL_LENGTH),
-        prompt_text=_trim(prompt_text, MAX_PROMPT_LENGTH),
-        response_text=_trim(response_text, MAX_RESPONSE_LENGTH),
+        prompt_text=_trim(prompt_text, MAX_PROMPT_LENGTH) if settings.processing_log_store_model_io_text else None,
+        response_text=_trim(response_text, MAX_RESPONSE_LENGTH) if settings.processing_log_store_model_io_text else None,
         payload_json=_safe_payload(payload_json),
     )
     session.add(entry)