[WIP] Showing the Think process for Deep Seek R1 in Cody UI

[arafatkatze]

Originally a PR from @abeatrix on having a thinktag UX.

Loom Video

This PR adds a simple hack to support rendering tags in the ChatMessageContent component. The content is displayed in a collapsible details element, allowing users to view the AI's internal thought process.
The MarkdownFromCody component is also updated to allow the element.

Test plan

• Run SG instance locally and switch to branch fake-think-tag
• Run cody with this branch in the debugger and choose sonnet model with the local SG instance
• Ask Cody "Tell me a long story"
• Verify that tags are properly extracted and displayed in the ChatMessageContent component
• Ensure that the collapsible details element functions as expected, allowing users to view the think content
• Confirm that the MarkdownFromCody component correctly renders the element

[arafatkatze]

Will fix all the CSS in proper files separately AFTER the design has been approved.

[PriNova]

@arafatkatze If you need some inspirations how I implemented it, have a look at https://github.com/PriNova/cody/blob/dev/vscode/webviews/chat/ChatMessageContent/ChatMessageContent.tsx
But to be honest, it is not somehow optimized.

I used special thinking tags to separate them from the model response for future changes.
The thinking tags I handled in the model response stream handler.
I don't know if this is the right choice, but it somehow works.