v0.5.18
antgroup/echomimicv0.5.18Jul 3, 2026by decolua
AI Summary
This release focuses on improved usage tracking including cached tokens, fixes for provider-specific issues such as Kiro and Kimchi, and adds support for new NVIDIA models and the ClinePass provider.
Key Highlights
- Enhanced usage tracking with cached tokens and corrected cost calculations
- Added support for new NVIDIA models and ClinePass provider
- Fixed Kiro authentication routing and Kimchi reasoning content handling
New Features
- Usage: track cached tokens + correct input/output/cache cost
- Codex: show reset credit expiry details
- NVIDIA: add new models and capabilities
- ClinePass: add provider support
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)