Skip to content

v0.3.3 - Cached vision model discovery

Latest

Choose a tag to compare

@libinyam libinyam released this 14 Aug 07:27
· 1 commit to main since this release

Improves provider discovery performance with a 30-second cache shared across model listing and routing, including in-flight request deduplication. Documents the direct fallback's retry, middleware, and token-accounting limitations. Also synchronizes the runtime User-Agent version with package.json and strengthens release validation. All 17 tests pass on GitHub Actions.