fix: correct conflicting output format instruction in follow-up generation prompt (open-webui#22212)

The Guidelines section instructed LLMs to return "a JSON array of strings"
while the Output section showed a JSON object with a "follow_ups" key.
This mismatch caused some models to return a top-level array, which the
frontend parser cannot handle (it looks for `{ }` delimiters and the
`follow_ups` key). Updated the guideline to consistently request a JSON
object matching the expected format.

Fixes open-webui#22187

Author: MJ16MJ

backend/open_webui/config.py

@@ -1960,7 +1960,7 @@ class BannerModel(BaseModel):
 - Only suggest follow-ups that make sense given the chat content and do not repeat what was already covered.
 - If the conversation is very short or not specific, suggest more general (but relevant) follow-ups the user might ask.
 - Use the conversation's primary language; default to English if multilingual.
-- Response must be a JSON array of strings, no extra text or formatting.
+- Response must be a JSON object with a "follow_ups" key containing an array of strings, no extra text or formatting.
 ### Output:
 JSON format: { "follow_ups": ["Question 1?", "Question 2?", "Question 3?"] }
 ### Chat History: