DeepSeek v3.2, tools, thinking, and messages

Been reading through the DeepSeek 3.2 paper, and this section stuck out, and reminded me that I have questions about why we use "model"/"user" messages for tool events, generally, and specifically to ADK

Mostly want to start a thread to talk about this. It seems more message types would be useful, but perhaps the models are not good with them because they are not post-trained on the variety (yet)

---

Start with the DeepSeek v3.2 paper section referenced in the issue, then inspect how ADK represents model and user messages for tool events. Determine which additional message types would be needed and document the agreed direction; the issue currently describes an open discussion rather than a defined change.

Written by the indexing model from the issue text.