[Bug] DeepSeek DSML tool-call markers leak into assistant content and streamlit UI

Summary

When using DeepSeek with tool calls, raw DSML markers such as <‖DSML‖tool_calls> and <‖DSML‖invoke ...> are leaking into the assistant content field. Downstream consumers (UI/TUI) then display or speak these internal markers.

Suggested fix

• Add DSML marker detection before emitting content.
• Strip / normalize Unicode variants (‖, ｜, etc.).
• Keep tool-call data only in structured tool_calls.
• Add regression tests with streaming chunks split across markers.

Reference

• https://jishuzhan.net/article/2065972403007746050