feat: add cache control support for claude models

[Pratham-Mishra04]

Summary

Improved the test retry framework with better logging and added support for cache control in content blocks across multiple providers.

Changes

• Enhanced test retry framework with more detailed logging:
  • Added attempt count with max attempts (e.g., "attempt 2/10")
  • Added waiting time logs before retries
  • Improved error reporting during test retries
  • Fixed attempt number handling in OnRetry callbacks
• Added cache control support to content blocks for:
  • Anthropic provider
  • Bedrock provider
  • OpenAI provider (with special handling to exclude from JSON marshaling)
• Added CacheControl type to schemas with support for ephemeral content and TTL

Type of change

• Bug fix
• Feature
• Refactor

Affected areas

• Core (Go)
• Transports (HTTP)
• Providers/Integrations
• Plugins
• UI (Next.js)
• Docs

How to test

# Core/Transports
go version
go test ./...

Breaking changes

• Yes
• No

Security considerations

Cache control implementation allows providers to specify content that should be treated as ephemeral, improving security for sensitive content.

Checklist

• I added/updated tests where appropriate
• I verified builds succeed (Go and UI)
• I verified the CI pipeline passes locally if applicable

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch 11-25-feat_support_for_prompt_caching_parameter_for_claude_models

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[Pratham-Mishra04]

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

• feat: add cache control support for claude models #979 👈 (View in Graphite)
• feat: add reasoning support for chat completions #978 : 1 other dependent PR (#999 )
• refactor: extract error parsing into dedicated files for providers #977
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.