v0.5.20

alibaba/MNNv0.5.20Jul 7, 2026by decolua

AI Summary

Adds a per-model thinking level picker with suffix support for reasoning effort, includes a JS-native git-log filter, targeted style rules, and Farsi language support.

Key Highlights

Thinking level picker with suffix support
RTK git-log filter
Caveman targeted style rules
Farsi language support

Breaking Changes

Model name handling changed to strip (level) suffix from upstream body.model

New Features

Thinking level picker
Suffix support for reasoning effort
RTK git-log filter
Caveman style rules
Farsi language support

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)