harden memory edits and uploads

core/config.py

@@ -6,6 +6,23 @@ from pathlib import Path
 
 
 _PROJECT_ROOT = Path(__file__).resolve().parents[1]
+_DEFAULT_ALLOWED_MIME_TYPES = (
+    "image/*",
+    "audio/*",
+    "application/pdf",
+    "text/html",
+    "application/xhtml+xml",
+    "text/plain",
+    "text/markdown",
+    "text/csv",
+    "application/json",
+    "application/msword",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "application/vnd.ms-excel",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    "application/vnd.ms-powerpoint",
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+)
 
 
 @dataclass(frozen=True)
@@ -14,9 +31,22 @@ class GatewayConfig:
     database_path: Path = _PROJECT_ROOT / "data" / "memory_gateway.sqlite3"
     storage_dir: Path = _PROJECT_ROOT / "data" / "storage"
     resource_search_batch_size: int = 50
+    max_upload_bytes: int = 25 * 1024 * 1024
+    allowed_mime_types: tuple[str, ...] = _DEFAULT_ALLOWED_MIME_TYPES
+    everos_ingest_attempts: int = 3
+    everos_retry_delay_seconds: float = 0.25
+    everos_timeout_seconds: float = 120.0
 
     @classmethod
     def from_env(cls) -> GatewayConfig:
+        allowed_mime_types = tuple(
+            item.strip()
+            for item in os.environ.get(
+                "MEMORY_GATEWAY_ALLOWED_MIME_TYPES",
+                ",".join(_DEFAULT_ALLOWED_MIME_TYPES),
+            ).split(",")
+            if item.strip()
+        )
         return cls(
             everos_base_url=os.environ.get(
                 "EVEROS_BASE_URL",
@@ -37,4 +67,17 @@ class GatewayConfig:
             resource_search_batch_size=int(
                 os.environ.get("MEMORY_GATEWAY_RESOURCE_SEARCH_BATCH_SIZE", "50")
             ),
+            max_upload_bytes=int(
+                os.environ.get("MEMORY_GATEWAY_MAX_UPLOAD_BYTES", str(25 * 1024 * 1024))
+            ),
+            allowed_mime_types=allowed_mime_types,
+            everos_ingest_attempts=int(
+                os.environ.get("MEMORY_GATEWAY_EVEROS_INGEST_ATTEMPTS", "3")
+            ),
+            everos_retry_delay_seconds=float(
+                os.environ.get("MEMORY_GATEWAY_EVEROS_RETRY_DELAY_SECONDS", "0.25")
+            ),
+            everos_timeout_seconds=float(
+                os.environ.get("MEMORY_GATEWAY_EVEROS_TIMEOUT_SECONDS", "120")
+            ),
         )