Skip to content

Nenya

v0.5.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai ai-gateway ai-governance ai-proxy ai-safety ai-security
+14 more
ai-tools anthropic deepseek litellm-alternative llm llm-gateway observability ollama openai openai-compatible-api openai-proxy opencode-zen proxy zhipu-ai

Summary

AI summary

Complete account attribution for billing tracking fixes a critical data‑race bug in MarkExhausted.

Full changelog

Changelog

  • 243f1624566e65287ac029a4bc4946e658151f9e feat: billing-aware routing with free model scoring, exhaustion filtering, and spend resets
  • ba33512ae226ce8a8d0b7a0bc4ba4083c8735b8a feat: make quota fetch timeout configurable per provider
  • 83bf44d01261b7819a956bc67ea44be946cfa23f feat: per-provider backoff for quota fetch operations
  • 9269edc244817f0017ae692c867fc0fa8bd780db fix: complete account attribution for billing tracking
  • 90ef1eb1c751826651ff567ceae63f4d06e21917 fix: data race in MarkExhausted — use Lock instead of RLock for non-atomic write
  • 1593ae6fed0eb240c93d7d2c27477d3e5c36f8a2 fix: reduce nesting depth in InjectAPIKeyWithGatewayCtx
  • b2841e1e5842cd978682c6b2b26dc14befd20ce8 fix: strip orphaned tool_use blocks when converting to Anthropic format
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Nenya

Get notified when new releases ship.

Sign up free

About Nenya

All releases →

Related context

Beta — feedback welcome: [email protected]