fix(editor): stabilize image workflows and editing controls

src/agent_tools/editor_tools.py

@@ -191,7 +191,7 @@ def _persist_png(image_bytes: bytes, owner: Optional[str], session_id: Optional[
         db.close()
 
 
-async def _place_layer(data_url: str, name: str, owner: Optional[str], session: str, *, masked: bool = False, blend: str = "normal", opacity: float = 100.0, mode: Optional[str] = None) -> bool:
+async def _place_layer(data_url: str, name: str, owner: Optional[str], session: str, *, masked: bool = False, blend: str = "normal", opacity: float = 100.0, mode: Optional[str] = None, native_size: bool = False) -> bool:
     params: Dict[str, Any] = {
         "dataUrl": data_url,
         "name": name,
@@ -199,6 +199,8 @@ async def _place_layer(data_url: str, name: str, owner: Optional[str], session:
         "blend": blend or "normal",
         "opacity": opacity,
     }
+    if native_size:
+        params["nativeSize"] = True
     # Forward the edit mode so the client can build a difference mask for
     # instruction-mode results: the whole image was regenerated under an
     # instruction prompt, so untouched pixels must stay pixel-identical (the
@@ -506,6 +508,8 @@ class AiEditImageTool:
             }
         _t["image"] = time.perf_counter()
         payload: Dict[str, Any] = {"image": image}
+        if args.get("_use_image_settings") is True:
+            payload["_use_image_settings"] = True
         model_choice = str(args.get("model") or "").strip()
         mask_used = False
         place_mode: Optional[str] = None
@@ -609,10 +613,11 @@ class AiEditImageTool:
                 f"AI {op}",
                 owner,
                 session,
-                masked=mask_used,
+                masked=mask_used and data.get("full_frame") is not True,
                 blend=str(args.get("blend") or "normal"),
                 opacity=float(args.get("opacity") or 100),
                 mode=place_mode,
+                native_size=data.get("full_frame") is True,
             )
             info["placed"] = placed
             if placed:
@@ -687,6 +692,7 @@ class GenerateImageLayerTool:
                 str(args.get("name") or "Generated image"),
                 owner,
                 session,
+                native_size=True,
                 masked=bool(args.get("mask")),
                 blend=str(args.get("blend") or "normal"),
                 opacity=float(args.get("opacity") or 100),

src/ai_interaction.py

@@ -179,8 +179,13 @@ def _resolve_model(spec: str, owner: Optional[str] = None, model_type: Optional[
                 # served internal id. Include pinned/cached ids in the match set
                 # so chat sessions using the HF repo id still resolve. Do not use
                 # stale cached aliases when the endpoint itself is unreachable.
-                if model_type == "image" and endpoint_reachable:
-                    for extra in _json_list(getattr(ep, "pinned_models", None)) + _json_list(getattr(ep, "cached_models", None)):
+                if endpoint_reachable:
+                    # Gateway image models may live in a dedicated catalogue,
+                    # so explicitly pinned IDs are valid on mixed endpoints too.
+                    extras = _json_list(getattr(ep, "pinned_models", None))
+                    if model_type == "image":
+                        extras += _json_list(getattr(ep, "cached_models", None))
+                    for extra in extras:
                         if extra not in model_ids:
                             model_ids.append(extra)
 
@@ -1200,6 +1205,39 @@ def image_editing_provider_available(owner: Optional[str] = None) -> bool:
         return False
 
 
+def _uses_openrouter_chat_images(model_id: str) -> bool:
+    # GPT-5 Image is an LLM wrapper, unlike native gpt-image-* image models.
+    leaf = model_id_leaf(model_id).lower()
+    return leaf.startswith("gpt-") and "-image" in leaf and not leaf.startswith("gpt-image-")
+
+
+def _chat_image_results(data: dict) -> list:
+    images = []
+    for choice in data.get("choices") or []:
+        message = choice.get("message") or {}
+        for item in message.get("images") or []:
+            url = (item.get("image_url") or {}).get("url")
+            if not isinstance(url, str):
+                continue
+            if url.startswith("data:image/") and ";base64," in url:
+                images.append({"b64_json": url.split(",", 1)[1]})
+            elif url.startswith(("https://", "http://")):
+                images.append({"url": url})
+    return images
+
+
+def _image_response_error(data: dict, model_id: str) -> Optional[str]:
+    errors = [data.get("error")]
+    errors.extend(choice.get("error") for choice in data.get("choices") or [])
+    for error in errors:
+        if not error:
+            continue
+        message = str(error.get("message") or "Image provider failed") if isinstance(error, dict) else str(error)
+        hint = " Choose a currently supported image model in AI settings." if "deprecated" in message.lower() else ""
+        return f"Image provider failed for '{model_id}': {message}{hint}"
+    return None
+
+
 async def do_generate_image(content: str, session_id: Optional[str] = None, owner: Optional[str] = None, *, incognito: bool = False) -> Dict:
     """Generate an image using an image-capable model (e.g. gpt-image-1).
 
@@ -1342,8 +1380,19 @@ async def do_generate_image(content: str, session_id: Optional[str] = None, owne
     base_url = url.replace("/chat/completions", "").replace("/v1/messages", "").rstrip("/")
     images_url = base_url + "/images/generations"
     from src.model_capability_readers.base import detect_vendor
+    chat_images = detect_vendor(url) == "openrouter" and _uses_openrouter_chat_images(model_id)
     if detect_vendor(url) == "openrouter":
         images_url = base_url + "/images"
+    if chat_images:
+        images_url = base_url + "/chat/completions"
+
+    # Capture the requested geometry before older OpenAI size restrictions.
+    from src.image_model_ids import image_aspect_ratio
+    try:
+        requested_width, requested_height = (int(value) for value in size.lower().split("x"))
+        requested_ratio = image_aspect_ratio(requested_width, requested_height)
+    except (TypeError, ValueError):
+        requested_ratio = "1:1"
 
     # Validate size for cloud image models (local diffusion accepts any WxH)
     valid_gpt_sizes = {"1024x1024", "1024x1536", "1536x1024", "auto"}
@@ -1359,6 +1408,9 @@ async def do_generate_image(content: str, session_id: Optional[str] = None, owne
         "n": 1,
         "size": size,
     }
+    if detect_vendor(url) == "openrouter":
+        payload.pop("size", None)
+        payload["aspect_ratio"] = requested_ratio
 
     # GPT image models and local diffusion support quality; DALL-E does not
     if is_gpt_image or is_local_diffusion:
@@ -1372,7 +1424,16 @@ async def do_generate_image(content: str, session_id: Optional[str] = None, owne
     try:
         # GPT image models can take 30-120s+ depending on quality
         async with httpx.AsyncClient(timeout=httpx.Timeout(connect=30.0, read=300.0, write=30.0, pool=30.0)) as client:
-            resp = await client.post(images_url, json=payload, headers=headers)
+            request_payload = payload
+            if chat_images:
+                request_payload = {
+                    "model": model_id,
+                    "messages": [{"role": "user", "content": prompt}],
+                    "modalities": ["image", "text"],
+                    "stream": False,
+                    "image_config": {"aspect_ratio": requested_ratio},
+                }
+            resp = await client.post(images_url, json=request_payload, headers=headers)
 
             if resp.status_code != 200:
                 error_text = resp.text[:500]
@@ -1387,9 +1448,15 @@ async def do_generate_image(content: str, session_id: Optional[str] = None, owne
                 }
 
             data = resp.json()
-            images = data.get("data", [])
+            provider_error = _image_response_error(data, model_id)
+            if provider_error:
+                return {"error": provider_error, "untrusted_content": True}
+            images = _chat_image_results(data) if chat_images else data.get("data", [])
             if not images:
-                return {"error": "No images returned from API"}
+                return {"error": (
+                    f"Image model '{model_id}' returned no image. "
+                    "Choose another image generation model in AI settings."
+                )}
 
             img = images[0]
             image_url = None
@@ -1508,7 +1575,7 @@ async def do_edit_image(
         _settings = {}
 
     if not model_spec:
-        model_spec = _settings.get("image_model", "")
+        model_spec = _settings.get("image_edit_model") or _settings.get("image_model", "")
     if quality == "medium" and _settings.get("image_quality"):
         quality = _settings["image_quality"]
     if not model_spec:
@@ -1517,6 +1584,10 @@ async def do_edit_image(
     try:
         try:
             def _call():
+                try:
+                    return _resolve_model(model_spec, owner=owner)
+                except ValueError:
+                    pass
                 try:
                     return _resolve_model(model_spec, owner=owner, model_type="image")
                 except TypeError as exc:
@@ -1529,6 +1600,7 @@ async def do_edit_image(
     except ValueError:
         return {"error": f"No endpoint found with image model '{model_spec}'."}
 
+    requested_edit_size = size
     if not size or size == "auto":
         from PIL import Image
         from src.image_model_ids import image_edit_size
@@ -1704,7 +1776,35 @@ async def do_edit_image(
                             "image_url": {"url": f"data:{mime};base64,{image_b64}"},
                         }],
                     }
-                    resp = await client.post(base_url + "/images", json=edit_payload, headers=headers)
+                    from src.image_model_ids import image_aspect_ratio
+                    from PIL import Image as ReferenceImage
+                    with ReferenceImage.open(path) as reference:
+                        reference_width, reference_height = reference.size
+                        if reference.getexif().get(274) in {5, 6, 7, 8}:
+                            reference_width, reference_height = reference_height, reference_width
+                    if requested_edit_size and requested_edit_size != "auto":
+                        try:
+                            reference_width, reference_height = (int(value) for value in requested_edit_size.lower().split("x"))
+                        except (TypeError, ValueError):
+                            pass
+                    edit_payload.pop("size", None)
+                    edit_payload["aspect_ratio"] = image_aspect_ratio(reference_width, reference_height)
+                    if _uses_openrouter_chat_images(model_id):
+                        edit_payload = {
+                            "model": model_id,
+                            "messages": [{"role": "user", "content": [
+                                {"type": "text", "text": prompt},
+                                {"type": "image_url", "image_url": {
+                                    "url": f"data:{mime};base64,{image_b64}",
+                                }},
+                            ]}],
+                            "modalities": ["image", "text"],
+                            "stream": False,
+                            "image_config": {"aspect_ratio": edit_payload["aspect_ratio"]},
+                        }
+                        resp = await client.post(base_url + "/chat/completions", json=edit_payload, headers=headers)
+                    else:
+                        resp = await client.post(base_url + "/images", json=edit_payload, headers=headers)
                 else:
                     with path.open("rb") as f:
                         files = {"image": (path.name, f, mime)}
@@ -1747,7 +1847,12 @@ async def do_edit_image(
                 }
 
             data = resp.json()
-            images = data.get("data", [])
+            provider_error = _image_response_error(data, model_id)
+            if provider_error:
+                return {"error": provider_error, "untrusted_content": True}
+            images = (_chat_image_results(data)
+                      if is_openrouter and _uses_openrouter_chat_images(model_id)
+                      else data.get("data", []))
             if not images:
                 return {"error": "No image returned from edit API"}
 

src/editor_image_settings.py

@@ -0,0 +1,11 @@
+"""The shared model defaults used by Quick Edit's image operations."""
+from src.settings import load_settings
+
+
+def editor_image_models():
+    settings = load_settings()
+    generation = str(settings.get("image_model") or "").strip()
+    return {
+        "generation": generation,
+        "edit": str(settings.get("image_edit_model") or generation).strip(),
+    }

src/image_model_ids.py

@@ -40,6 +40,15 @@ def image_edit_size(model_id: str, width: int, height: int) -> str:
     return f"{width}x{height}"
 
 
+def image_aspect_ratio(width: int, height: int) -> str:
+    """Choose the nearest common Image API ratio, without distorting pixels."""
+    if width <= 0 or height <= 0:
+        raise ValueError("Image dimensions must be positive")
+    ratios = ((1, 1), (16, 9), (9, 16), (3, 2), (2, 3), (4, 3), (3, 4), (21, 9))
+    w, h = min(ratios, key=lambda ratio: abs(math.log((ratio[0] / ratio[1]) / (width / height))))
+    return f"{w}:{h}"
+
+
 def looks_like_image_generation_model(model_id: str) -> bool:
     """Return True when a model id should use image generation routes.
 

src/settings.py

@@ -46,6 +46,7 @@ DEFAULT_SETTINGS = {
     "agent_email_confirm": True,
     "image_gen_enabled": False,
     "image_model": "",
+    "image_edit_model": "",
     "image_quality": "medium",
     # Optional editor planner/caption endpoints. Empty uses configured chat
     # fallback without probing a developer-specific host.
@@ -294,7 +295,7 @@ def is_setting_overridden(key: str) -> bool:
 # resolved by FastAPI deps; an empty/None owner falls through to the global.
 _PER_USER_KEYS = {
     "vision_model", "vision_enabled", "vision_model_fallbacks",
-    "image_model", "image_gen_enabled", "image_quality",
+    "image_model", "image_edit_model", "image_gen_enabled", "image_quality",
     # Default chat endpoint / model — without per-user resolution every new
     # account inherited whatever the most-recent admin picked, which then
     # got injected into the chat composer on first open.