v0.5.20

Kieirra/murmurev0.5.20Jul 7, 2026by decolua

AI Summary

This release enhances model control and reasoning capabilities by introducing a per-model thinking level picker with suffix support across multiple providers. It also includes updates to the RTK, Caveman, and i18n modules, alongside various fixes for token counting and provider compatibility.

Key Highlights

Thinking level picker with suffix support for forced reasoning effort across providers
RTK: Added JS-native git-log filter
Caveman: Added targeted upstream-aligned style rules
i18n: Added Farsi language support
Fixes for Claude reasoning budget reconciliation and Anthropic token counting

New Features

Per-model thinking level picker
JS-native git-log filter for RTK
Targeted upstream-aligned style rules for Caveman
Farsi (fa) 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)