support Claude 4 Interleaved thinking (beta)

[heisenbergye]

support Claude 4 Interleaved thinking (beta)

Issue #, if available:

Description of changes:

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

as OpenAI API format, add extra_body , anthropic_beta and thinking are required to enable interleaved thinking. when interleaved thinking enabled with reasoning_effort, reasoning_effort will be ignored.

curl http://127.0.0.1:8000/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer bedrock" \
-d '{
"model": "us.anthropic.claude-sonnet-4-20250514-v1:0",
"max_tokens": 2048,
"messages": [{
"role": "user",
"content": "xxxxxxxxxxxx"
}],
"stream": true,
"extra_body": {
"anthropic_beta": ["interleaved-thinking-2025-05-14"],
"thinking": {"type": "enabled", "budget_tokens": 4096}
}
}'