smart_image_gen v0.4: emit image to chat, return only confirmation

The data URI returned from the tool was being given to the LLM as the
tool result — the LLM then either echoed the base64 to the user as
plain text (screenshot 1) or hallucinated a description of what it
thought the image looked like (screenshot 2 — "an image of a cat
sitting on a windowsill" for a fox-warrior prompt).

Fix: push the markdown image into the chat directly via
__event_emitter__ as a "message" event, and return a short text
confirmation as the function value. The confirmation is worded to
prevent the LLM from describing the image or repeating the markdown
(both common failure modes for tool-using LLMs).

Both generate_image and edit_image fixed.

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

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

@@ -1,14 +1,17 @@
 """
 title: Smart Image Generator & Editor (ComfyUI)
 author: ai-stack
-version: 0.3.0
+version: 0.4.0
 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
     LLM picks (or auto-detects) the right model — photoreal, Pony
     score-tag, NoobAI/Illustrious furry, etc. — and each style ships
     with the creator-recommended sampler, scheduler, CFG, steps, CLIP
-    skip, prompt-prefix dialect, and negatives.
+    skip, prompt-prefix dialect, and negatives. The actual image is
+    pushed into the chat via the event emitter; the function return is
+    just a short confirmation so the LLM doesn't try to describe or
+    re-emit the data URI.
 required_open_webui_version: 0.5.0
 """
 
@@ -483,8 +486,23 @@ class Tools:
             return err
 
         b64 = base64.b64encode(raw).decode("ascii")
+        # Push the image straight into the chat. The function return is just
+        # a confirmation for the LLM — if we returned the markdown, the LLM
+        # would either echo the base64 to the user as text, or hallucinate
+        # a description of what it thinks the image looks like.
+        if __event_emitter__:
+            await __event_emitter__({
+                "type": "message",
+                "data": {"content": f"![{chosen}](data:image/png;base64,{b64})"},
+            })
         await emit(f"Done — {chosen}", done=True)
-        return f"![{chosen}](data:image/png;base64,{b64})"
+        return (
+            f"Image generated and shown to the user above (style: {chosen}, "
+            f"checkpoint: {settings['ckpt']}). Do NOT describe the image, "
+            f"do NOT repeat any base64 or markdown — the user can see it. "
+            f"You may briefly note your style choice and offer one or two "
+            f"iteration ideas (different style, tighter framing, etc)."
+        )
 
     async def edit_image(
         self,
@@ -582,5 +600,16 @@ class Tools:
             return err
 
         b64 = base64.b64encode(raw_out).decode("ascii")
+        if __event_emitter__:
+            await __event_emitter__({
+                "type": "message",
+                "data": {"content": f"![edit:{chosen}](data:image/png;base64,{b64})"},
+            })
         await emit(f"Done — {chosen} (denoise {denoise:.2f})", done=True)
-        return f"![edit:{chosen}](data:image/png;base64,{b64})"
+        return (
+            f"Edited image shown to the user above (style: {chosen}, "
+            f"checkpoint: {settings['ckpt']}, denoise: {denoise:.2f}). Do NOT "
+            f"describe the image, do NOT repeat any base64 or markdown — the "
+            f"user can see it. You may briefly note your choice and offer "
+            f"iterations (different denoise, alternate style, etc)."
+        )