v0.5.20

met4citizen/TalkingHeadv0.5.20Jul 7, 2026by decolua

AI Summary

This release introduces a thinking level picker for models and adds suffix support across various providers. It also includes enhancements to the RTK, Caveman, and i18n modules, along with several fixes for token counting, provider compatibility, and documentation.

Key Highlights

Thinking level picker with suffix support for forced reasoning effort across multiple providers
RTK update with JS-native git-log filter
Farsi (fa) language support added
Fixes for Claude max_tokens reconciliation and Volcengine-ark GLM-5 ceiling

New Features

Per-model thinking level picker
JS-native git-log filter in RTK
Targeted upstream-aligned style rules in 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)