v1.4.420

danielmiessler/Fabricv1.4.420Feb 24, 2026by github-actions[bot]

AI Summary

Enhanced Azure AI Gateway with i18n support, documentation, configurable API version, URL validation with HTTPS enforcement, and response body size limits.

Key Highlights

Added configurable API version support (default: 2025-04-01-preview)
Implemented URL validation with HTTPS enforcement and 300-second timeout
Added 10MB response body size limit using io.LimitReader
Expanded error body truncation from 200 to 500 characters
Fixed Bedrock max_tokens to respect opts.MaxTokens with fallback

New Features

Azure AI Gateway i18n support
File-level documentation across all backend files
Error checks for empty message lists across all backends

Full Release Notes

## Changes

### PR [#2021](https://github.com/danielmiessler/Fabric/pull/2021) by [jlec](https://github.com/jlec) and [ksylvan](https://github.com/ksylvan): Enhanced Azure AI Gateway with i18n Support and documentation

- Added configurable API version support for the Azure OpenAI backend, defaulting to `2025-04-01-preview` while maintaining backward compatibility.
- Implemented URL validation with HTTPS enforcement and a cancellable context in `SendStream` with a 300-second timeout.
- Added a 10MB response body size limit using `io.LimitReader` and improved error body truncation from 200 to 500 characters.
- Added file-level documentation across all backend files and enforced lowercase error messages per Go convention.
- Fixed Bedrock `max_tokens` to correctly respect `opts.MaxTokens` with a fallback, and added error checks for empty message lists across all backends.