v0.5.20

QwenAudio/SenseVoicev0.5.20Jul 7, 2026by decolua

AI Summary

An update adding a 'thinking level' picker for AI models and internationalization support, alongside fixes for token counting and specific provider behaviors.

Key Highlights

Added thinking level picker with suffix support for forced reasoning effort across providers.
Added Farsi (fa) language support.
Fixed token counting for structured Anthropic blocks.
Fixed Volcengine-ark GLM-5 max_tokens clamping.
Fixed Kiro system prompt delivery and Opus versions.

New Features

Thinking level picker with suffix support
Farsi language support (i18n)
Improved structured Anthropic block token counting
Volcengine-ark max_tokens fix
Kiro system prompt fix

Full Release Notes

Features:
- Thinking: per-model thinking level picker on provider page, appends (level) suffix to copied model names for forced reasoning effort across all formats (openai, claude, gemini, deepseek, kimi, qwen, zai, minimax, hunyuan, step)
- RTK: add JS-native git-log filter (#2423)
- Caveman: add targeted upstream-aligned style rules (#2424)
- i18n: add Farsi (fa) language support (#2385)

Fixes:
- Thinking: strip (level) suffix from upstream body.model so providers no longer reject requests
- Translator: preserve developer instructions in openai-responses conversion (#2434)
- count_tokens: count structured Anthropic blocks (#2419)
- Volcengine-ark: clamp GLM-5 max_tokens to model output ceiling (#2428)
- Kimi: normalize reasoning_effort to backend enum (#2427)
- Claude: reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381)
- Kiro: deliver system prompt natively, add Opus 4.5/4.7/4.8, tolerate dash version ids (#2366)
- Headroom: proxy dashboard through app (#2372)
- MITM: recover from stale lock file on server start

Docs:
- README: swap in Vietnamese tutorial video; add English and Urdu/Hindi tutorials (#2305)
- Add CLAUDE.md guidance for Claude Code (#2354)