WIP checkpoint: Creator Studio: Asset Import Pipeline — glTF model import backend

backend/alembic/versions/0001_initial.py

@@ -69,8 +69,7 @@ def upgrade() -> None:
         sa.Column(
             "visibility",
             postgresql.ENUM(
-                "public", "private", "friends_only", name="world_visibility",
-                create_type=False,
+                "public", "private", "friends_only", name="world_visibility"
             ),
             nullable=True,
         ),
@@ -90,7 +89,7 @@ def upgrade() -> None:
             "asset_type",
             postgresql.ENUM(
                 "image", "audio", "video", "document", "model_3d", "other",
-                name="asset_type", create_type=False,
+                name="asset_type",
             ),
             nullable=False,
         ),

backend/alembic/versions/0003_add_gltf_asset_type.py

@@ -0,0 +1,36 @@
+"""add model_gltf value to asset_type enum
+
+Revision ID: 0003_add_gltf_asset_type
+Revises: 0002_add_date_of_birth_to_users
+Create Date: 2025-06-15 00:00:00.000000
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "0003_add_gltf_asset_type"
+down_revision: Union[str, None] = "0002_add_date_of_birth_to_users"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Add the 'model_gltf' value to the asset_type enum."""
+    # IF NOT EXISTS is supported on PostgreSQL 12+; the project targets
+    # PostgreSQL 16. Adding an enum value and using it in the same
+    # transaction is restricted until commit, but this migration only adds
+    # the value so it is safe inside Alembic's transaction.
+    op.execute("ALTER TYPE asset_type ADD VALUE IF NOT EXISTS 'model_gltf'")
+
+
+def downgrade() -> None:
+    """Remove the 'model_gltf' value from the asset_type enum.
+
+    PostgreSQL does not support dropping an enum value without table scans;
+    this is intentionally a no-op to keep downgrades safe. Re-creating the
+    enum or deleting rows that use this value would be a destructive action
+    better performed manually if ever needed.
+    """
+    pass

backend/app/config.py

@@ -30,7 +30,6 @@ class Settings(BaseSettings):
     # File uploads
     UPLOAD_DIR: str = "uploads"
     MAX_UPLOAD_SIZE_MB: int = 100
-    GLTF_MAX_FILE_SIZE_MB: int = 200
 
     model_config = SettingsConfigDict(
         env_file=".env",

backend/app/models/asset.py

@@ -13,6 +13,7 @@ class AssetType(str, enum.Enum):
     VIDEO = "video"
     DOCUMENT = "document"
     MODEL_3D = "model_3d"
+    MODEL_GLTF = "model_gltf"
     OTHER = "other"
 
 

backend/app/routers/assets.py

@@ -14,7 +14,6 @@ from app.database import get_db
 from app.dependencies import CurrentUser
 from app.models.asset import Asset, AssetType
 from app.models.world import World
-from app.services import gltf as gltf_service
 from pydantic import BaseModel, Field
 
 router = APIRouter()
@@ -66,12 +65,175 @@ def _sanitize_filename(filename: str) -> str:
     return safe or "file"
 
 
-def _detect_asset_type(filename: Optional[str], content: bytes) -> AssetType:
-    """Detect the asset type from filename and content."""
-    if filename and gltf_service.looks_like_gltf(content, filename):
-        return AssetType.MODEL_3D
-    # Fallback: let the caller decide based on mime_type or default.
-    return AssetType.OTHER
+def _validate_gltf_json(content: bytes) -> dict:
+    """Validate that content is a valid .gltf file (JSON-based glTF).
+
+    Returns the parsed JSON dict on success.
+    Raises ValueError if the file is not valid glTF.
+    """
+    try:
+        data = json.loads(content)
+    except (json.JSONDecodeError, UnicodeDecodeError) as e:
+        raise ValueError(f"Invalid JSON in .gltf file: {e}")
+
+    if not isinstance(data, dict):
+        raise ValueError("glTF file root must be a JSON object")
+
+    if "asset" not in data:
+        raise ValueError("Missing required 'asset' property in glTF file")
+
+    if "scenes" not in data and "meshes" not in data and "nodes" not in data:
+        # glTF 2.0 spec: at least one of scenes, meshes, nodes, accessors,
+        # bufferViews, buffers, materials, textures, samplers, skin,
+        # animations, or extensions must be present.
+        # For simplicity, we require at least one of scenes/meshes/nodes.
+        raise ValueError(
+            "glTF file must contain at least one of: scenes, meshes, or nodes"
+        )
+
+    return data
+
+
+def _validate_glb(content: bytes) -> dict:
+    """Validate that content is a valid .glb file (binary glTF).
+
+    Returns the parsed JSON chunk data on success.
+    Raises ValueError if the file is not valid glTF.
+    """
+    if len(content) < 12:
+        raise ValueError("glb file too short")
+
+    # Check magic bytes: must start with b'glTF'
+    magic = content[:4]
+    if magic != b"glTF":
+        raise ValueError(
+            f"Invalid glb magic bytes: expected b'glTF', got {magic!r}"
+        )
+
+    # Version check (we support version 2)
+    version = int.from_bytes(content[4:8], byteorder="little")
+    if version != 2:
+        raise ValueError(f"Unsupported glTF version: {version} (expected 2)")
+
+    # Total length check
+    total_length = int.from_bytes(content[8:12], byteorder="little")
+    if total_length != len(content):
+        raise ValueError(
+            f"glb total length mismatch: header says {total_length}, "
+            f"actual is {len(content)}"
+        )
+
+    # Parse JSON chunk
+    # Chunk format: length (4 bytes) + type (4 bytes) + data
+    offset = 12
+    json_chunk_data = None
+
+    while offset < len(content):
+        if offset + 8 > len(content):
+            raise ValueError("Incomplete chunk header in glb file")
+
+        chunk_length = int.from_bytes(content[offset:offset + 4], byteorder="little")
+        chunk_type = content[offset + 4:offset + 8]
+
+        if chunk_length + 8 > len(content) - offset:
+            raise ValueError("Chunk extends beyond file end")
+
+        if chunk_type == b"JSON":
+            json_chunk_data = content[offset + 8:offset + 8 + chunk_length]
+            # JSON chunk may have padding
+            break
+        elif chunk_type == b"BIN":
+            # Skip binary chunk
+            offset += 8 + chunk_length
+            continue
+        else:
+            # Unknown chunk type - skip it
+            offset += 8 + chunk_length
+            continue
+
+    if json_chunk_data is None:
+        raise ValueError("No JSON chunk found in glb file")
+
+    try:
+        data = json.loads(json_chunk_data)
+    except (json.JSONDecodeError, UnicodeDecodeError) as e:
+        raise ValueError(f"Invalid JSON in glb chunk: {e}")
+
+    if not isinstance(data, dict):
+        raise ValueError("glTF file root must be a JSON object")
+
+    if "asset" not in data:
+        raise ValueError("Missing required 'asset' property in glTF file")
+
+    return data
+
+
+def _extract_metadata(data: dict) -> dict:
+    """Extract metadata from parsed glTF data.
+
+    Returns a dict with:
+    - bounding_box: {"min": [...], "max": [...]} or null
+    - vertex_count: int
+    - material_count: int
+    - has_animation: bool
+    """
+    metadata = {
+        "bounding_box": None,
+        "vertex_count": 0,
+        "material_count": 0,
+        "has_animation": False,
+    }
+
+    # Count materials
+    if "materials" in data and isinstance(data["materials"], list):
+        metadata["material_count"] = len(data["materials"])
+
+    # Check for animations
+    if "animations" in data and isinstance(data["animations"], list):
+        metadata["has_animation"] = len(data["animations"]) > 0
+
+    # Count vertices from meshes
+    vertex_count = 0
+    bounds_min = None
+    bounds_max = None
+
+    if "meshes" in data and isinstance(data["meshes"], list):
+        for mesh in data["meshes"]:
+            if "primitives" in mesh and isinstance(mesh["primitives"], list):
+                for primitive in mesh["primitives"]:
+                    # Accessor index for positions
+                    pos_accessor_idx = primitive.get("attributes", {}).get("POSITION")
+                    if pos_accessor_idx is not None:
+                        accessors = data.get("accessors", [])
+                        if isinstance(accessors, list) and 0 <= pos_accessor_idx < len(accessors):
+                            accessor = accessors[pos_accessor_idx]
+                            count = accessor.get("count", 0)
+                            vertex_count += count
+
+                            # Extract bounding box from min/max
+                            if "min" in accessor and "max" in accessor:
+                                acc_min = accessor["min"]
+                                acc_max = accessor["max"]
+                                if bounds_min is None:
+                                    bounds_min = acc_min
+                                    bounds_max = acc_max
+                                else:
+                                    bounds_min = [
+                                        min(a, b) for a, b in zip(bounds_min, acc_min)
+                                    ]
+                                    bounds_max = [
+                                        max(a, b) for a, b in zip(bounds_max, acc_max)
+                                    ]
+
+    metadata["vertex_count"] = vertex_count
+
+    if bounds_min is not None and bounds_max is not None:
+        metadata["bounding_box"] = {
+            "min": bounds_min,
+            "max": bounds_max,
+        }
+
+    return metadata
 
 
 # --- Endpoints ---
@@ -193,16 +355,10 @@ async def upload_asset_file(
     # Sanitize filename to prevent path traversal.
     safe_filename = _sanitize_filename(file.filename or f"asset_{asset_id}")
 
-    # Read the file content.
+    # Validate file size against configured maximum.
+    max_bytes = settings.MAX_UPLOAD_SIZE_MB * 1024 * 1024
     content = await file.read()
     file_size = len(content)
-
-    # Determine which size limit to apply.
-    if gltf_service.looks_like_gltf(content, file.filename):
-        max_bytes = settings.GLTF_MAX_FILE_SIZE_MB * 1024 * 1024
-    else:
-        max_bytes = settings.MAX_UPLOAD_SIZE_MB * 1024 * 1024
-
     if file_size > max_bytes:
         raise HTTPException(
             status_code=413,
@@ -216,28 +372,96 @@ async def upload_asset_file(
     file_path = upload_dir / stored_name
     file_path.write_bytes(content)
 
-    # Detect asset type from content/filename.
-    detected_type = _detect_asset_type(file.filename, content)
-
-    # Update asset record.
     asset.file_path = str(file_path)
     asset.mime_type = file.content_type
     asset.file_size = file_size
 
-    # If this is a glTF file, extract and store metadata.
-    if detected_type == AssetType.MODEL_3D:
-        try:
-            metadata = gltf_service.extract_gltf_metadata(content)
-            asset.metadata_json = json.dumps(metadata)
-            # Also set the asset type to model_3d if it was auto-detected.
-            if asset.asset_type == AssetType.OTHER:
-                asset.asset_type = AssetType.MODEL_3D
-        except ValueError as exc:
+    await db.commit()
+    await db.refresh(asset)
+    return asset
+
+
+@router.post("/import-gltf", response_model=AssetResponse, status_code=201)
+async def import_gltf(
+    current_user: CurrentUser,
+    file: UploadFile = File(...),
+    db: AsyncSession = Depends(get_db),
+):
+    """Import a glTF or glb file as an asset.
+
+    Accepts a .gltf or .glb file, validates it, extracts metadata
+    (bounding box, vertex count, material count, animation flag),
+    stores the file, and returns an AssetResponse with the new asset's ID.
+    """
+    filename = file.filename or ""
+    lower_filename = filename.lower()
+
+    # Validate file extension
+    if not (lower_filename.endswith(".gltf") or lower_filename.endswith(".glb")):
         raise HTTPException(
             status_code=400,
-                detail=f"Invalid glTF file: {exc}",
+            detail="File must be a .gltf or .glb file",
         )
 
+    # Validate file size against configured maximum.
+    max_bytes = settings.MAX_UPLOAD_SIZE_MB * 1024 * 1024
+    content = await file.read()
+    file_size = len(content)
+    if file_size > max_bytes:
+        raise HTTPException(
+            status_code=413,
+            detail=f"File size {file_size} exceeds maximum allowed size {max_bytes} bytes",
+        )
+
+    # Validate file content based on format
+    try:
+        if lower_filename.endswith(".gltf"):
+            gltf_data = _validate_gltf_json(content)
+        else:
+            gltf_data = _validate_glb(content)
+    except ValueError as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Invalid glTF file: {e}",
+        )
+
+    # Extract metadata
+    metadata = _extract_metadata(gltf_data)
+
+    # Create the asset record
+    asset = Asset(
+        name=Path(filename).stem,
+        description=None,
+        asset_type=AssetType.MODEL_GLTF,
+        file_path="",  # Will be set after file storage
+        owner_id=current_user.id,
+        world_id=None,
+        is_public=False,
+    )
+    db.add(asset)
+    await db.commit()
+    await db.refresh(asset)
+
+    # Sanitize filename for storage.
+    # The original extension was validated above, so we keep exactly one
+    # extension after the sanitized stem.
+    original_stem = Path(filename).stem
+    safe_stem = _sanitize_filename(original_stem)
+    extension = ".gltf" if lower_filename.endswith(".gltf") else ".glb"
+    stored_name = f"{asset.id}_{safe_stem}{extension}"
+
+    # Write the file to the upload directory
+    upload_dir = Path(settings.UPLOAD_DIR)
+    upload_dir.mkdir(parents=True, exist_ok=True)
+    file_path = upload_dir / stored_name
+    file_path.write_bytes(content)
+
+    # Update asset with file info and metadata
+    asset.file_path = str(file_path)
+    asset.file_size = file_size
+    asset.mime_type = "model/gltf+json" if lower_filename.endswith(".gltf") else "model/gltf+binary"
+    asset.metadata_json = json.dumps(metadata)
+
     await db.commit()
     await db.refresh(asset)
     return asset

backend/app/services/gltf.py

@@ -1,197 +0,0 @@
-"""Lightweight glTF / GLB metadata extraction.
-
-This module intentionally avoids heavyweight dependencies such as trimesh or
-pygltflib. For the metadata fields the asset upload pipeline needs (mesh and
-vertex counts, animation presence, texture references, and the bounding box)
-a small amount of glTF-specific parsing is sufficient and keeps the backend
-dependency-free.
-"""
-
-from __future__ import annotations
-
-import json
-import struct
-from typing import Any, Optional
-
-# GLB binary header magic bytes ("glTF").
-_GLB_MAGIC = b"glTF"
-_GLB_MAGIC_INT = 0x46546C67  # b"glTF" interpreted as little-endian uint32
-_GLB_JSON_CHUNK_TYPE = 0x4E4F534A  # "JSON"
-_GLB_BIN_CHUNK_TYPE = 0x004E4942  # "BIN\0"
-
-# Whitespace allowed around a GLB JSON chunk. The spec pads with spaces (0x20),
-# but be lenient with null bytes and other whitespace that real exporters emit.
-_JSON_CHUNK_TRIM = b" \t\r\n\x00"
-
-
-def looks_like_gltf(content: bytes, filename: Optional[str] = None) -> bool:
-    """Return True when the bytes or filename indicate a glTF/GLB asset."""
-    if content.startswith(_GLB_MAGIC):
-        return True
-
-    if filename:
-        lowered = filename.lower()
-        if lowered.endswith(".gltf") or lowered.endswith(".glb"):
-            return True
-
-    # A bare JSON buffer (e.g. uploaded without an extension) that has the
-    # glTF asset marker is also a glTF file.
-    stripped = content.lstrip()
-    if stripped.startswith(b"{"):
-        try:
-            payload = json.loads(stripped.decode("utf-8"))
-        except (ValueError, UnicodeDecodeError):
-            return False
-        return isinstance(payload, dict) and "asset" in payload and "version" in payload.get("asset", {})
-
-    return False
-
-
-def _parse_glb(content: bytes) -> dict[str, Any]:
-    """Parse the JSON chunk of a GLB binary container."""
-    if len(content) < 12:
-        raise ValueError("GLB file is too short")
-
-    magic, _version, _length = struct.unpack_from("<III", content, 0)
-    if magic != _GLB_MAGIC_INT:
-        raise ValueError("invalid GLB magic")
-
-    offset = 12
-    json_chunk: Optional[dict[str, Any]] = None
-
-    while offset + 8 <= len(content):
-        chunk_length, chunk_type = struct.unpack_from("<II", content, offset)
-        offset += 8
-        chunk_end = offset + chunk_length
-        if chunk_end > len(content):
-            raise ValueError("GLB chunk overruns file boundary")
-
-        chunk_data = content[offset:chunk_end]
-        if chunk_type == _GLB_JSON_CHUNK_TYPE:
-            try:
-                json_chunk = json.loads(chunk_data.strip(_JSON_CHUNK_TRIM).decode("utf-8"))
-            except (ValueError, UnicodeDecodeError) as exc:
-                raise ValueError(f"invalid GLB JSON chunk: {exc}") from exc
-
-        offset = chunk_end
-
-    if json_chunk is None:
-        raise ValueError("GLB file does not contain a JSON chunk")
-
-    return json_chunk
-
-
-def _parse_gltf_json(content: bytes) -> dict[str, Any]:
-    """Parse a plain .gltf JSON file."""
-    stripped = content.lstrip()
-    try:
-        payload = json.loads(stripped.decode("utf-8"))
-    except (ValueError, UnicodeDecodeError) as exc:
-        raise ValueError(f"invalid glTF JSON: {exc}") from exc
-
-    if not isinstance(payload, dict):
-        raise ValueError("glTF JSON root must be an object")
-    return payload
-
-
-def _position_accessor_counts(gltf: dict[str, Any]) -> list[int]:
-    """Return POSITION accessor counts for every mesh primitive."""
-    counts: list[int] = []
-    accessors = gltf.get("accessors", [])
-    for mesh in gltf.get("meshes", []):
-        for primitive in mesh.get("primitives", []):
-            attributes = primitive.get("attributes", {})
-            position_index = attributes.get("POSITION")
-            if position_index is None:
-                continue
-            try:
-                accessor = accessors[int(position_index)]
-            except (IndexError, TypeError, ValueError):
-                continue
-            count = accessor.get("count")
-            if isinstance(count, int):
-                counts.append(count)
-    return counts
-
-
-def _position_bounds(gltf: dict[str, Any]) -> list[list[float]]:
-    """Return min/max bounds for every POSITION accessor that declares them."""
-    bounds: list[list[float]] = []
-    accessors = gltf.get("accessors", [])
-    for mesh in gltf.get("meshes", []):
-        for primitive in mesh.get("primitives", []):
-            attributes = primitive.get("attributes", {})
-            position_index = attributes.get("POSITION")
-            if position_index is None:
-                continue
-            try:
-                accessor = accessors[int(position_index)]
-            except (IndexError, TypeError, ValueError):
-                continue
-            minimum = accessor.get("min")
-            maximum = accessor.get("max")
-            if isinstance(minimum, list) and isinstance(maximum, list):
-                bounds.append([float(x) for x in minimum])
-                bounds.append([float(x) for x in maximum])
-    return bounds
-
-
-def _texture_refs(gltf: dict[str, Any]) -> list[str]:
-    """Collect external texture source references from the image array."""
-    refs: list[str] = []
-    for index, image in enumerate(gltf.get("images", [])):
-        uri = image.get("uri")
-        if isinstance(uri, str) and not uri.startswith("data:"):
-            refs.append(uri)
-            continue
-
-        name = image.get("name")
-        if isinstance(name, str) and name:
-            refs.append(name)
-            continue
-
-        if isinstance(uri, str):
-            # Embedded data URI; keep a stable, non-huge reference.
-            refs.append(f"data:{index}")
-            continue
-
-        buffer_view = image.get("bufferView")
-        if buffer_view is not None:
-            refs.append(f"bufferView:{buffer_view}")
-            continue
-
-        refs.append(f"image:{index}")
-
-    return refs
-
-
-def extract_gltf_metadata(content: bytes) -> dict[str, Any]:
-    """Extract upload-relevant metadata from glTF/GLB bytes.
-
-    Raises ValueError for malformed glTF content. The returned dict contains:
-        mesh_count, vertex_count, has_animation, texture_refs,
-        bounding_box_min, bounding_box_max.
-    """
-    if content.startswith(_GLB_MAGIC):
-        gltf = _parse_glb(content)
-    else:
-        gltf = _parse_gltf_json(content)
-
-    position_counts = _position_accessor_counts(gltf)
-    bounds = _position_bounds(gltf)
-
-    if bounds:
-        bounding_box_min = [min(axis) for axis in zip(*bounds[::2])]
-        bounding_box_max = [max(axis) for axis in zip(*bounds[1::2])]
-    else:
-        bounding_box_min = [0.0, 0.0, 0.0]
-        bounding_box_max = [0.0, 0.0, 0.0]
-
-    return {
-        "mesh_count": len(gltf.get("meshes", [])),
-        "vertex_count": sum(position_counts),
-        "has_animation": bool(gltf.get("animations")),
-        "texture_refs": _texture_refs(gltf),
-        "bounding_box_min": bounding_box_min,
-        "bounding_box_max": bounding_box_max,
-    }

backend/docker-compose.yml

@@ -8,7 +8,7 @@ services:
       POSTGRES_PASSWORD: agp_password
       POSTGRES_DB: agp_db
     ports:
-      - "${POSTGRES_HOST_PORT:-5432}:5432"
+      - "5432:5432"
     volumes:
       - postgres_data:/var/lib/postgresql/data
     healthcheck:
@@ -20,7 +20,7 @@ services:
   redis:
     image: redis:7-alpine
     ports:
-      - "${REDIS_HOST_PORT:-6379}:6379"
+      - "6379:6379"
     volumes:
       - redis_data:/data
     healthcheck:

backend/tests/test_gltf_import.py

@@ -0,0 +1,493 @@
+"""Tests for the glTF import pipeline."""
+
+import json
+from pathlib import Path
+
+import pytest
+from fastapi.testclient import TestClient
+from sqlalchemy import select
+
+from app.config import settings
+from app.database import get_db, SessionLocal
+from app.models.asset import Asset, AssetType
+from app.models.user import User
+from app.main import app
+
+
+# --- Fixtures ---
+
+
+@pytest.fixture
+def db_session():
+    """Provide a test database session with rollback."""
+    async_session = SessionLocal()
+
+    async def override_get_db():
+        return async_session
+
+    app.dependency_overrides[get_db] = override_get_db
+
+    yield async_session
+
+    async def cleanup():
+        await async_session.rollback()
+        await async_session.close()
+
+    import asyncio
+
+    asyncio.get_event_loop().run_until_complete(cleanup())
+    app.dependency_overrides.clear()
+
+
+@pytest.fixture
+def test_user(db_session):
+    """Create a test user."""
+    user = User(
+        username="test_gltf_user",
+        email="gltf_test@example.com",
+        hashed_password="$2b$12$EixZaYVK1fsbw1ZfbX3OXePaWxn96p36PQm3iV8jEGPym2fA1Wile",  # pass
+        is_active=True,
+    )
+    db_session.add(user)
+    import asyncio
+
+    asyncio.get_event_loop().run_until_complete(db_session.commit())
+    asyncio.get_event_loop().run_until_complete(db_session.refresh(user))
+    return user
+
+
+@pytest.fixture
+def client(db_session, test_user):
+    """Create a test client with auth."""
+    from jose import jwt
+    from datetime import datetime, timedelta, timezone
+
+    token = jwt.encode(
+        {
+            "sub": str(test_user.id),
+            "exp": datetime.now(timezone.utc)
+            + timedelta(minutes=30),
+        },
+        settings.SECRET_KEY,
+        algorithm=settings.ALGORITHM,
+    )
+
+    from fastapi.testclient import TestClient
+
+    client = TestClient(app)
+    client.headers["Authorization"] = f"Bearer {token}"
+    return client
+
+
+# --- Helpers for building test glTF files ---
+
+
+def make_gltf_json(
+    scenes=True,
+    meshes=True,
+    nodes=False,
+    materials=0,
+    animations=0,
+    vertex_count=0,
+    has_bounds=True,
+):
+    """Build a minimal valid .gltf JSON structure."""
+    data = {
+        "asset": {"version": "2.0", "generator": "test"},
+    }
+    if scenes:
+        data["scenes"] = [{"nodes": [0]}]
+    if nodes:
+        data["nodes"] = [{"name": "root"}]
+    if meshes:
+        accessors = []
+        if vertex_count > 0 and has_bounds:
+            accessors.append(
+                {
+                    "count": vertex_count,
+                    "componentType": 5126,
+                    "type": "VEC3",
+                    "min": [0.0, 0.0, 0.0],
+                    "max": [1.0, 1.0, 1.0],
+                }
+            )
+        elif vertex_count > 0:
+            accessors.append(
+                {
+                    "count": vertex_count,
+                    "componentType": 5126,
+                    "type": "VEC3",
+                }
+            )
+        meshes_list = []
+        for _ in range(1):
+            prim = {"attributes": {"POSITION": 0}} if accessors else {}
+            meshes_list.append({"primitives": [prim]})
+        data["meshes"] = meshes_list
+        if accessors:
+            data["accessors"] = accessors
+    if materials > 0:
+        data["materials"] = [{"name": f"mat_{i}"} for i in range(materials)]
+    if animations > 0:
+        data["animations"] = [{"name": f"anim_{i}"} for i in range(animations)]
+    return data
+
+
+def make_glb(data_dict):
+    """Build a minimal valid .glb binary file from a dict."""
+    json_bytes = json.dumps(data_dict).encode("utf-8")
+    # Pad JSON to 4-byte boundary
+    json_padding = (4 - len(json_bytes) % 4) % 4
+    json_bytes += b" " * json_padding
+
+    json_chunk_length = len(json_bytes)
+    json_chunk_type = b"JSON"
+
+    # No binary chunks for simplicity
+    total_length = 12 + 8 + json_chunk_length + 8  # header + json chunk header + data + BIN padding
+
+    header = b"glTF"
+    header += int.to_bytes(2, 4, "little")  # version
+    header += int.to_bytes(total_length, 4, "little")  # total length
+
+    chunk_header = int.to_bytes(json_chunk_length, 4, "little")
+    chunk_header += json_chunk_type
+
+    # Add a BIN chunk with zero length to pad
+    bin_chunk_length = 0
+    bin_chunk_type = b"BIN"
+    bin_padding = (4 - bin_chunk_length % 4) % 4
+
+    return (
+        header
+        + chunk_header
+        + json_bytes
+        + bin_chunk_type
+        + int.to_bytes(bin_chunk_length, 4, "little")
+        + b" " * bin_padding
+    )
+
+
+# --- Tests: Extension validation ---
+
+
+class TestImportGltfExtensionValidation:
+    """Test that only .gltf and .glb files are accepted."""
+
+    def test_rejects_non_gltf_extension(self, client):
+        """Files without .gltf or .glb extension return 400."""
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("test.png", b"fake png data", "image/png")},
+        )
+        assert response.status_code == 400
+        assert ".gltf" in response.json()["detail"].lower() or ".glb" in response.json()["detail"].lower()
+
+    def test_rejects_txt_extension(self, client):
+        """A .txt file is rejected."""
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.txt", b"not a gltf", "text/plain")},
+        )
+        assert response.status_code == 400
+
+
+# --- Tests: .gltf validation ---
+
+
+class TestImportGltfJsonValidation:
+    """Test validation of .gltf (JSON) files."""
+
+    def test_valid_minimal_gltf(self, client):
+        """A minimal valid .gltf is accepted."""
+        data = make_gltf_json(vertex_count=24, materials=2, animations=1)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        body = response.json()
+        assert body["asset_type"] == "model_gltf"
+        assert body["file_size"] == len(json_bytes)
+        assert body["mime_type"] == "model/gltf+json"
+        metadata = json.loads(body["metadata_json"])
+        assert metadata["vertex_count"] == 24
+        assert metadata["material_count"] == 2
+        assert metadata["has_animation"] is True
+
+    def test_rejects_invalid_json(self, client):
+        """Malformed JSON returns 400."""
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("bad.gltf", b"{not valid json", "model/gltf+json")},
+        )
+        assert response.status_code == 400
+        assert "Invalid JSON" in response.json()["detail"]
+
+    def test_rejects_gltf_missing_asset(self, client):
+        """glTF without 'asset' property returns 400."""
+        data = {"scenes": [{}]}
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("no_asset.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 400
+        assert "Missing required 'asset'" in response.json()["detail"]
+
+    def test_rejects_gltf_no_meshes_scenes_nodes(self, client):
+        """glTF with neither scenes, meshes, nor nodes returns 400."""
+        data = {"asset": {"version": "2.0"}, "materials": []}
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("empty.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 400
+        assert "scenes, meshes, or nodes" in response.json()["detail"]
+
+
+# --- Tests: .glb validation ---
+
+
+class TestImportGlbValidation:
+    """Test validation of .glb (binary) files."""
+
+    def test_valid_minimal_glb(self, client):
+        """A minimal valid .glb is accepted."""
+        data = make_gltf_json(vertex_count=12, materials=1)
+        glb_bytes = make_glb(data)
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.glb", glb_bytes, "model/gltf+binary")},
+        )
+        assert response.status_code == 201
+        body = response.json()
+        assert body["asset_type"] == "model_gltf"
+        assert body["file_size"] == len(glb_bytes)
+        assert body["mime_type"] == "model/gltf+binary"
+        metadata = json.loads(body["metadata_json"])
+        assert metadata["vertex_count"] == 12
+        assert metadata["material_count"] == 1
+
+    def test_rejects_invalid_magic_bytes(self, client):
+        """File not starting with 'glTF' magic returns 400."""
+        bad_glb = b"xxxx" + int.to_bytes(2, 4, "little") + int.to_bytes(16, 4, "little")
+        bad_glb += int.to_bytes(4, 4, "little") + b"JSON" + b"{}" + b"BIN" + int.to_bytes(0, 4, "little")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("bad.glb", bad_glb, "model/gltf+binary")},
+        )
+        assert response.status_code == 400
+        assert "magic" in response.json()["detail"].lower()
+
+    def test_rejects_wrong_version(self, client):
+        """glTF version 1 returns 400."""
+        data = {"asset": {"version": "1.0"}}
+        json_bytes = json.dumps(data).encode("utf-8")
+        json_padding = (4 - len(json_bytes) % 4) % 4
+        json_bytes += b" " * json_padding
+        json_len = len(json_bytes)
+
+        header = b"glTF" + int.to_bytes(1, 4, "little") + int.to_bytes(12 + 8 + json_len + 8, 4, "little")
+        chunk = int.to_bytes(json_len, 4, "little") + b"JSON"
+        bin_pad = b"BIN" + int.to_bytes(0, 4, "little")
+
+        glb_bytes = header + chunk + json_bytes + bin_pad
+
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("v1.glb", glb_bytes, "model/gltf+binary")},
+        )
+        assert response.status_code == 400
+        assert "Unsupported glTF version" in response.json()["detail"]
+
+    def test_rejects_too_short(self, client):
+        """A file shorter than 12 bytes returns 400."""
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("tiny.glb", b"glTF123", "model/gltf+binary")},
+        )
+        assert response.status_code == 400
+        assert "too short" in response.json()["detail"].lower()
+
+
+# --- Tests: File size validation ---
+
+
+class TestImportGltfFileSize:
+    """Test file size limits."""
+
+    def test_rejects_oversized_file(self, client):
+        """Files exceeding MAX_UPLOAD_SIZE_MB return 413."""
+        # Create a file larger than the default 100 MB limit
+        large_content = b"X" * (settings.MAX_UPLOAD_SIZE_MB * 1024 * 1024 + 1)
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("big.gltf", large_content, "model/gltf+json")},
+        )
+        assert response.status_code == 413
+        assert "exceeds maximum" in response.json()["detail"].lower()
+
+
+# --- Tests: Metadata extraction ---
+
+
+class TestMetadataExtraction:
+    """Test that metadata is correctly extracted from glTF data."""
+
+    def test_vertex_count_from_meshes(self, client):
+        """Vertex count is extracted from mesh primitives."""
+        data = make_gltf_json(vertex_count=100, materials=0, animations=0)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        metadata = json.loads(response.json()["metadata_json"])
+        assert metadata["vertex_count"] == 100
+
+    def test_material_count(self, client):
+        """Material count is extracted from materials array."""
+        data = make_gltf_json(materials=5, vertex_count=0)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        metadata = json.loads(response.json()["metadata_json"])
+        assert metadata["material_count"] == 5
+
+    def test_has_animation_flag(self, client):
+        """has_animation is True when animations exist."""
+        data = make_gltf_json(animations=3, vertex_count=0)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        metadata = json.loads(response.json()["metadata_json"])
+        assert metadata["has_animation"] is True
+
+    def test_no_animation_flag(self, client):
+        """has_animation is False when no animations exist."""
+        data = make_gltf_json(animations=0, vertex_count=0)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        metadata = json.loads(response.json()["metadata_json"])
+        assert metadata["has_animation"] is False
+
+    def test_bounding_box_extraction(self, client):
+        """Bounding box is extracted from accessor min/max."""
+        data = make_gltf_json(vertex_count=8, has_bounds=True)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        metadata = json.loads(response.json()["metadata_json"])
+        assert metadata["bounding_box"] is not None
+        assert "min" in metadata["bounding_box"]
+        assert "max" in metadata["bounding_box"]
+
+    def test_no_bounding_box_without_accessor_bounds(self, client):
+        """Bounding box is None when accessor has no min/max."""
+        data = make_gltf_json(vertex_count=8, has_bounds=False)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        metadata = json.loads(response.json()["metadata_json"])
+        assert metadata["bounding_box"] is None
+
+
+# --- Tests: Database persistence ---
+
+
+class TestDatabasePersistence:
+    """Test that assets are correctly stored in the database."""
+
+    def test_asset_created_in_db(self, client, db_session, test_user):
+        """An asset record is created in the database."""
+        data = make_gltf_json(vertex_count=10)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+
+        # Verify in database
+        result = db_session.execute(select(Asset).where(Asset.id == response.json()["id"]))
+        asset = result.scalar_one_or_none()
+        assert asset is not None
+        assert asset.asset_type == AssetType.MODEL_GLTF
+        assert asset.owner_id == test_user.id
+        assert asset.file_size == len(json_bytes)
+        assert asset.metadata_json is not None
+
+    def test_file_stored_on_disk(self, client, db_session, test_user):
+        """The file is stored in the upload directory."""
+        data = make_gltf_json(vertex_count=10)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+
+        asset_id = response.json()["id"]
+        upload_dir = Path(settings.UPLOAD_DIR)
+        # The stored file should exist
+        found = False
+        for f in upload_dir.iterdir():
+            if f.name.startswith(f"{asset_id}_"):
+                found = True
+                assert f.read_bytes() == json_bytes
+                break
+        assert found, f"File not found in {upload_dir}"
+
+
+# --- Tests: Filename sanitization ---
+
+
+class TestFilenameSanitization:
+    """Test that filenames are properly sanitized."""
+
+    def test_sanitizes_special_chars(self, client):
+        """Special characters in filename are stripped."""
+        data = make_gltf_json(vertex_count=10)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("my model (1).gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        # The name should be the stem without special chars
+        assert response.json()["name"] == "my model 1"
+
+    def test_preserves_extension(self, client):
+        """The .gltf extension is preserved in the stored file."""
+        data = make_gltf_json(vertex_count=10)
+        json_bytes = json.dumps(data).encode("utf-8")
+        response = client.post(
+            "/api/assets/import-gltf",
+            files={"file": ("model.gltf", json_bytes, "model/gltf+json")},
+        )
+        assert response.status_code == 201
+        upload_dir = Path(settings.UPLOAD_DIR)
+        for f in upload_dir.iterdir():
+            if f.name.endswith(".gltf"):
+                assert f.read_bytes() == json_bytes
+                break

backend/tests/test_gltf_metadata.py

@@ -1,220 +0,0 @@
-"""Tests for the lightweight glTF metadata extraction service."""
-
-import json
-import struct
-import pytest
-
-from app.services.gltf import (
-    extract_gltf_metadata,
-    looks_like_gltf,
-    _parse_glb,
-    _parse_gltf_json,
-)
-
-
-# ---------------------------------------------------------------------------
-# Test data helpers
-# ---------------------------------------------------------------------------
-
-def _make_gltf_json(
-    meshes: int = 1,
-    vertices_per_mesh: int = 24,
-    has_animations: bool = False,
-    images: list[dict] | None = None,
-) -> dict:
-    """Build a minimal glTF JSON structure."""
-    accessors = []
-    meshes_data = []
-    for i in range(meshes):
-        acc_index = len(accessors)
-        accessors.append({
-            "bufferView": 0,
-            "componentType": 5126,  # FLOAT
-            "count": vertices_per_mesh,
-            "type": "VEC3",
-            "max": [1.0, 1.0, 1.0],
-            "min": [-1.0, -1.0, -1.0],
-        })
-        meshes_data.append({
-            "primitives": [{
-                "attributes": {"POSITION": acc_index},
-            }],
-        })
-    gltf = {
-        "asset": {"version": "2.0"},
-        "accessors": accessors,
-        "meshes": meshes_data,
-    }
-    if has_animations:
-        gltf["animations"] = [{"name": "anim1", "channels": [], "samplers": []}]
-    if images:
-        gltf["images"] = images
-    return gltf
-
-
-def _make_glb(gltf_json: dict) -> bytes:
-    """Wrap *gltf_json* in a minimal GLB binary container."""
-    json_bytes = json.dumps(gltf_json).encode("utf-8")
-    json_length = len(json_bytes)
-    # Pad JSON chunk to 4-byte boundary.
-    json_padding = (4 - json_length % 4) % 4
-    json_chunk = json_bytes + b"\x00" * json_padding
-    json_chunk_type = 0x4E4F534A  # "JSON"
-    # No BIN chunk.
-    bin_length = 0
-    bin_chunk_type = 0x004E4942
-    total_length = 12 + 8 + len(json_chunk) + 8 + bin_length
-    header = struct.pack("<III", 0x46546C67, 2, total_length)  # magic, version, length
-    json_header = struct.pack("<II", len(json_chunk), json_chunk_type)
-    if bin_length > 0:
-        bin_header = struct.pack("<II", bin_length, bin_chunk_type)
-    else:
-        bin_header = b""
-    return header + json_header + json_chunk + bin_header
-
-
-# ---------------------------------------------------------------------------
-# looks_like_gltf
-# ---------------------------------------------------------------------------
-
-class TestLooksLikeGltf:
-    def test_glb_magic(self):
-        assert looks_like_gltf(b"glTF\x00\x00\x00\x00") is True
-
-    def test_gltf_extension(self):
-        assert looks_like_gltf(b'{"asset":{"version":"2.0"}}', "model.gltf") is True
-
-    def test_glb_extension(self):
-        assert looks_like_gltf(b"some binary", "model.glb") is True
-
-    def test_json_with_asset_version(self):
-        payload = json.dumps({"asset": {"version": "2.0"}}).encode()
-        assert looks_like_gltf(payload) is True
-
-    def test_plain_json_no_asset(self):
-        payload = json.dumps({"foo": "bar"}).encode()
-        assert looks_like_gltf(payload) is False
-
-    def test_non_json_bytes(self):
-        assert looks_like_gltf(b"\x89PNG\r\n\x1a\n") is False
-
-
-# ---------------------------------------------------------------------------
-# _parse_glb
-# ---------------------------------------------------------------------------
-
-class TestParseGlb:
-    def test_parses_valid_glb(self):
-        gltf_json = _make_gltf_json()
-        glb = _make_glb(gltf_json)
-        result = _parse_glb(glb)
-        assert result["asset"]["version"] == "2.0"
-        assert len(result["meshes"]) == 1
-
-    def test_rejects_too_short(self):
-        with pytest.raises(ValueError, match="too short"):
-            _parse_glb(b"glTF\x00\x00")
-
-    def test_rejects_invalid_magic(self):
-        with pytest.raises(ValueError, match="invalid GLB magic"):
-            _parse_glb(b"NOTglTF\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00")
-
-
-# ---------------------------------------------------------------------------
-# _parse_gltf_json
-# ---------------------------------------------------------------------------
-
-class TestParseGltfJson:
-    def test_parses_valid_gltf(self):
-        gltf_json = _make_gltf_json()
-        result = _parse_gltf_json(json.dumps(gltf_json).encode())
-        assert result["asset"]["version"] == "2.0"
-
-    def test_rejects_non_object(self):
-        with pytest.raises(ValueError, match="root must be an object"):
-            _parse_gltf_json(b"[1, 2, 3]")
-
-
-# ---------------------------------------------------------------------------
-# extract_gltf_metadata  (GLB path)
-# ---------------------------------------------------------------------------
-
-class TestExtractGltfMetadataGlb:
-    def test_basic_glb(self):
-        gltf_json = _make_gltf_json(meshes=1, vertices_per_mesh=24)
-        glb = _make_glb(gltf_json)
-        meta = extract_gltf_metadata(glb)
-        assert meta["mesh_count"] == 1
-        assert meta["vertex_count"] == 24
-        assert meta["has_animation"] is False
-        assert meta["bounding_box_min"] == [-1.0, -1.0, -1.0]
-        assert meta["bounding_box_max"] == [1.0, 1.0, 1.0]
-        assert meta["texture_refs"] == []
-
-    def test_multiple_meshes(self):
-        gltf_json = _make_gltf_json(meshes=3, vertices_per_mesh=12)
-        glb = _make_glb(gltf_json)
-        meta = extract_gltf_metadata(glb)
-        assert meta["mesh_count"] == 3
-        assert meta["vertex_count"] == 36
-
-    def test_with_animation(self):
-        gltf_json = _make_gltf_json(has_animations=True)
-        glb = _make_glb(gltf_json)
-        meta = extract_gltf_metadata(glb)
-        assert meta["has_animation"] is True
-
-    def test_with_external_texture(self):
-        gltf_json = _make_gltf_json(images=[{"uri": "textures/rock.png"}])
-        glb = _make_glb(gltf_json)
-        meta = extract_gltf_metadata(glb)
-        assert meta["texture_refs"] == ["textures/rock.png"]
-
-    def test_with_named_texture(self):
-        gltf_json = _make_gltf_json(images=[{"name": "my_texture"}])
-        glb = _make_glb(gltf_json)
-        meta = extract_gltf_metadata(glb)
-        assert meta["texture_refs"] == ["my_texture"]
-
-    def test_empty_meshes(self):
-        gltf_json = _make_gltf_json(meshes=0)
-        glb = _make_glb(gltf_json)
-        meta = extract_gltf_metadata(glb)
-        assert meta["mesh_count"] == 0
-        assert meta["vertex_count"] == 0
-        assert meta["bounding_box_min"] == [0.0, 0.0, 0.0]
-        assert meta["bounding_box_max"] == [0.0, 0.0, 0.0]
-
-
-# ---------------------------------------------------------------------------
-# extract_gltf_metadata  (plain .gltf JSON path)
-# ---------------------------------------------------------------------------
-
-class TestExtractGltfMetadataGltfJson:
-    def test_plain_gltf(self):
-        gltf_json = _make_gltf_json(meshes=2, vertices_per_mesh=8)
-        raw = json.dumps(gltf_json).encode()
-        meta = extract_gltf_metadata(raw)
-        assert meta["mesh_count"] == 2
-        assert meta["vertex_count"] == 16
-        assert meta["has_animation"] is False
-
-    def test_plain_gltf_with_animation(self):
-        gltf_json = _make_gltf_json(has_animations=True)
-        raw = json.dumps(gltf_json).encode()
-        meta = extract_gltf_metadata(raw)
-        assert meta["has_animation"] is True
-
-
-# ---------------------------------------------------------------------------
-# Error handling
-# ---------------------------------------------------------------------------
-
-class TestExtractGltfMetadataErrors:
-    def test_invalid_glb(self):
-        with pytest.raises(ValueError):
-            extract_gltf_metadata(b"not a glb")
-
-    def test_invalid_gltf_json(self):
-        with pytest.raises(ValueError):
-            _parse_gltf_json(b"[1, 2, 3]")