v1.4.455

deepseek-ai/DeepSeek-OCRv1.4.455Jun 9, 2026by github-actions[bot]

AI Summary

This release focuses on improving AI provider integrations by adding a persistent cache for model discovery and handling rate limits. It also introduces support for the Claude Fable 5 model.

Key Highlights

Persistent cache for provider model discovery results
Serve stale model caches during discovery failures
Add Claude Fable 5 Anthropic model support
Concise localized errors for rate-limited model fetches

New Features

Persistent caching mechanism for provider integrations
Claude Fable 5 model support with automatic sampling parameter omission
Localized error handling for rate limits

Full Release Notes

## Changes

### PR [#2138](https://github.com/danielmiessler/Fabric/pull/2138) by [ksylvan](https://github.com/ksylvan): New Claude Fable model + cache OpenAI model discovery and handle provider rate limits

- Add persistent cache for provider model discovery results, improving performance and reliability of provider integrations.
- Serve stale model caches during discovery failures, ensuring continued operation when upstream providers are unavailable.
- Add Claude Fable 5 Anthropic model support, with sampling parameters automatically omitted for compatibility.
- Return concise localized errors for rate-limited model fetches, with updated translations across all supported locales.
- Update Go dependencies for AI provider integrations to keep upstream libraries current.