feat(llm): Add prompt caching for Anthropic Claude models

[Seayon]

Add prompt caching parameters for all Claude-3 series models, supporting tagged text caching to improve response speed. Each model can cache up to 4 text blocks.

Summary

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Resolves #7382

Screenshots

Before

After

Checklist

Important

Please review the checklist below before submitting your pull request.

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[crazywoola]

Please fix the lint errors.

[Seayon]

Please fix the lint errors.
@crazywoola
Done