Sentry LLM Monitoring does not capture tool use or thinking for Anthropic

When capturing LLM outputs sentry should capture tool use blocks and thinking blocks as part of the response object, this is vital information for developers working on LLM products. Currently only text responses are captured.

https://github.com/getsentry/sentry-python/blob/adcfa0f6abf8850f3b007bde609d0f943f621786/sentry_sdk/integrations/anthropic.py#L78-L85

https://docs.anthropic.com/en/api/messages#response-content

Comece em sentry_sdk/integrations/anthropic.py, por volta das linhas 78-85, e compare a resposta capturada com a response-content documentation da Anthropic. Garanta que tool use e thinking blocks sejam representados junto com text no response object e, em seguida, verifique se a integração captura todos os tipos de conteúdo solicitados.

Escrita pelo modelo de indexação a partir do texto da issue.