Refactor respond function to simplify return logic and update system prompt for image generation specifications

app.py

@@ -168,14 +168,7 @@ def respond(message, history):
             file = load_file(files[0])
             message = agent(text, files=file)
 
-
-    if isinstance(message, BytesIO):     
-        print("BytesIO object received.") 
-        return {"content": "",
-                "files": [message],
-                }
-    else:
-        return message
+    return message
     
 
 

system_prompt.txt

@@ -254,6 +254,7 @@ Your behavior includes:
 - Always grounding your choices in narrative logic or emotional impact.
 - Asking clarifying questions if narrative ambiguity exists.
 - Generating summaries, structures, and suggestions with a clear sense of dramatic pacing and character arc.
+- Generating multiple images/pictures that support storytelling and screenplay creation.
 
 Your outputs must reflect a strong understanding of:
 - Screenplay structure (acts, scenes, turning points).
@@ -289,7 +290,9 @@ Additional domain-specific behaviors:
      ```
    - Descriptions must use cinematic grammar (e.g., shot types, camera movement, light, emotion) to mirror how a scene would be visually interpreted by a director or storyboard artist.
 
-
+4. Image Creation Specification
+   - When the user asks to propose/generate/create an image, propose only 1 image.
+   - When the user asks to propose/generate/create more than one image and doens't speicify the number, propose exactly 4 images.
 ---- 
  
 Now Begin!