v0.5.18

Vanilagy/mediabunnyv0.5.18Jul 3, 2026by decolua

AI Summary

This release focuses on improving token tracking accuracy, adding support for new models across providers like NVIDIA and Kiro, and fixing various stability and authentication issues for providers such as Claude, Xiaomi, and Kimchi.

Key Highlights

Enhanced usage tracking to accurately calculate cached token costs.
Added support for new NVIDIA models and capabilities.
Improved Kiro provider with Claude Sonnet 5 support and IdC routing.
Added new provider support for ClinePass.
Fixed critical bugs including non-SSE stream crashes and cross-IdP account overwrites.

New Features

Track cached tokens and correct input/output/cache costs.
Show reset credit expiry details for Codex.
Add new models and capabilities for NVIDIA.
Add provider support for ClinePass.
Add Claude Sonnet 5 model support for Kiro.

Full Release Notes

Features:
- Usage: track cached tokens + correct input/output/cache cost (#2209)
- Codex: show reset credit expiry details (#2290)
- NVIDIA: add new models and capabilities
- ClinePass: add provider support

Fixes:
- Usage: dedupe streaming request-details log entries
- Claude: drop foreign thinking signatures in passthrough
- Prevent non-SSE stream pipe crash and cross-IdP account overwrites (#2244)
- Kiro: route IdC auth to regional CodeWhisperer surface (#2297)
- Kiro: add Claude Sonnet 5 model support (#2264)
- Xiaomi-tokenplan: region selector, key validation, multi-connection (#2251)
- Translator: strict Anthropic content block compliance (#2225)
- Kimchi: strip reasoning_content echo to bound multi-turn input tokens
- Kimchi: bump User-Agent to kimchi/0.1.40 (#2256)
- Codebuddy-cn: strip empty tool_calls arrays to preserve reasoning
- Antigravity: preserve Claude tool delta index (#2223)
- MITM: generate root CA on server startup (#2228)