owen dcf10d85b3 assistant: reply 'images not supported' and skip images ...

The cog's vision_model defaulted to the text-only llama3.2:3b, so any image in
the message/reply was sent to a non-vision model, causing Ollama 400 'invalid
image input'. Now the bot tells the user images aren't supported and continues
with text-only, preserving normal chat.

2026-09-22 23:02:09 -05:00

..

__init__.py

Rename greeptchat cog to assistant - generic AI chatbot branding

2026-07-31 20:41:40 -05:00

assistant.py

assistant: reply 'images not supported' and skip images

2026-09-22 23:02:09 -05:00

info.json

Rename greeptchat cog to assistant - generic AI chatbot branding

2026-07-31 20:41:40 -05:00