smart_image_gen v0.7.11: docstrings steer follow-up edits to edit_image

When the user generated an image and then asked to modify it ("make
her hair red", "now at sunset"), the OWUI default-mode tool decider
was picking generate_image and producing a fresh, unrelated image —
or, if the base model output the call as text instead, narrating
generate_image(...) in the chat instead of dispatching anything.

Root cause was in the tool docstrings, which the decider weights
heavily. Both were asymmetric in the same direction:

- edit_image led with "an image the user has ATTACHED to the chat"
  and "the user uploads an image" — both phrasings exclude assistant-
  emitted images, so the decider read follow-up turns as "no source,
  edit_image invalid."
- generate_image's exclusion clause ("they have NOT attached an
  existing image") matched: assistant-emitted images aren't
  "attached," so generate_image stayed valid for follow-ups too.

Result: on iteration turns, the decider saw generate_image as the
only valid choice and dispatched it (or the base model emitted a
pseudo-call when the decider declined).

Rewrite both leads symmetrically:
- edit_image now covers "any image already in this chat" with
  explicit mention of assistant-emitted sources.
- generate_image now defers to edit_image whenever ANY image is
  visible above, even when the user's phrasing sounds like a fresh
  request — that last clause is what catches "make her hair red."

The extraction code itself already handled assistant-emitted images
correctly (path #2 + #4 in _extract_attached_image, including the
chat-DB fallback from f26dfbe) — only the docstrings were lying to
the decider.

smart_image_gen.py 0.7.10 -> 0.7.11

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

deployments/ai-stack/openwebui-tools/smart_image_gen.py

@@ -1,7 +1,7 @@
 """
 title: Smart Image Generator & Editor (ComfyUI)
 author: ai-stack
-version: 0.7.10
+version: 0.7.11
 description: Generate or edit images via ComfyUI with automatic SDXL
     checkpoint routing. Two methods — generate_image (txt2img) and
     edit_image (img2img on the user's most recently attached image). The
@@ -754,11 +754,17 @@ class Tools:
     ) -> str:
         """
         Create a NEW image from scratch and show it to the user. Use this
-        whenever the user asks you to draw, generate, create, make, paint,
-        render, or imagine any visual content — photographs, portraits,
-        characters, scenes, illustrations, anime, drawings — and they have
-        NOT attached an existing image. If they did attach an image and
-        want it modified, use edit_image instead.
+        ONLY when there is no existing image in the chat at all and the
+        user is asking for a fresh image (draw, generate, create, make,
+        paint, render, imagine) — photographs, portraits, characters,
+        scenes, illustrations, anime, drawings. If ANY image is already
+        visible in the chat (either user-attached OR one you generated
+        earlier in this conversation) and the user is asking to change,
+        modify, restyle, recolor, add to, remove from, or iterate on it,
+        use edit_image instead — even if the user's word choice sounds
+        like a fresh request ("make her hair red", "now show her at
+        sunset"). Follow-up requests on an existing image are ALMOST
+        ALWAYS edits, not new generations.
 
         Pick `style` to match what the user wants:
         - "photo" — photorealistic photographs, portraits, cinematic shots.
@@ -854,9 +860,13 @@ class Tools:
         __event_emitter__: Optional[Callable[[dict], Awaitable[None]]] = None,
     ) -> str:
         """
-        Edit, modify, transform, or restyle an image the user has ATTACHED
-        to the chat. Use whenever the user uploads an image and asks to
-        change it. If no image is attached, use generate_image instead.
+        Edit, modify, transform, or restyle an image already in this
+        chat — either one the user attached, OR one you (the assistant)
+        generated earlier in this same conversation via generate_image
+        or edit_image. Use whenever the user asks to change, modify,
+        restyle, recolor, add to, remove from, or iterate on an image
+        that is already visible above in the chat. If no image exists
+        in the chat at all, use generate_image instead.
 
         TWO MODES — choose based on whether the change is local or global:
 
@@ -905,7 +915,8 @@ class Tools:
             1.0 with mask_text, 0.7 without.
         :param negative_prompt: Extra terms to exclude. Usually unneeded.
         :param seed: 0 to randomize, otherwise specific.
-        :return: Markdown image of the result, or an error if no image is attached.
+        :return: Markdown image of the result, or an error if no image
+            exists anywhere in this chat (user-uploaded or assistant-generated).
         """
         # Resolve style — inheritance DOMINATES for edits. Vision LLMs
         # misclassify subject types (observed in the wild: juggernaut