v1.2.1

liriliri/ayav1.2.1Jul 14, 2026by cdoern

AI Summary

A bug fix release improving CI/CD processes and correcting inference URL handling for Anthropic messages.

Key Highlights

  • Container entrypoint boot restored using --insecure flag
  • Fixed duplicate /v1 prefix in Anthropic message URLs
  • Generated TypeScript types in-repo instead of cloning

Full Release Notes

## What's Changed
* fix(ci): regenerate uv.lock for ogx-client 1.2.0 on release-1.2.x by @cdoern in https://github.com/ogx-ai/ogx/pull/6300
* fix(ci): generate ogx-client in-repo instead of cloning external repo (backport #6297) by @mergify[bot] in https://github.com/ogx-ai/ogx/pull/6299
* fix(containers): pass --insecure to entrypoint to restore starter image boot (backport #6288) by @mergify[bot] in https://github.com/ogx-ai/ogx/pull/6293
* fix(inference): strip duplicate /v1 prefix in vLLM Anthropic message URLs (backport #6294) by @mergify[bot] in https://github.com/ogx-ai/ogx/pull/6295
* fix(ci): publish ogx-client-typescript on release-1.2.x (backport #6301) by @cdoern in https://github.com/ogx-ai/ogx/pull/6302


**Full Changelog**: https://github.com/ogx-ai/ogx/compare/v1.2.0...v1.2.1