llms/bedrock: add cache support for anthropic

[lucaronca]

PR Checklist

Plumbs llms.CachedContent / llms.CacheControl through the Bedrock provider for Anthropic
models, so callers can mark content blocks as prompt-cache breakpoints with the same API used
by llms/anthropic:

llm.GenerateContent(ctx, []llms.MessageContent{
    {Role: llms.ChatMessageTypeSystem, Parts: []llms.ContentPart{
        llms.WithCacheControl(llms.TextPart(largeContext), bedrock.EphemeralCache()),
    }},
})

Note: this PR includes the changes from #1489. Please merge that one first so this diff can be rebased to show only the prompt-caching work.

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.