Starstruk Logo MarkStarstruk

v0.3.46

RightNow-AI/openfangv0.3.46Mar 11, 2026by jaberjaber23

AI Summary

A community-driven release featuring 11 PRs that fix critical bugs related to IME input, token quotas, and embedding drivers. It also introduces new AI models and fixes XML-attribute tool call recovery.

Key Highlights

  • Default User-Agent added to all LLM drivers to fix 403 errors from Moonshot/Qwen.
  • Token quota changed to unlimited to prevent immediate quota errors on fresh installs.
  • Embedding driver now respects `provider_urls` config and auto-selects models.
  • New Z.AI Coding models (glm-5-coding, glm-4.7-coding) and Kimi for Code added.
  • Wizard now generates proper multi-line TOML strings for system prompts.

New Features

  • New Z.AI Coding models (glm-5-coding, glm-4.7-coding) added.
  • Kimi for Code (Anthropic-compatible) models added.
  • Kimi-k2.5-0711 alias added.
  • XML-attribute tool call recovery (Pattern 9) for Groq/Llama models.

Full Release Notes

## Community Contributions

11 PRs reviewed, labeled, commented, and implemented from scratch following our architecture. All PR authors credited.

### Bug Fixes
- **#438** — IME composition guard prevents Enter from sending during CJK input (@pandego)
- **#433** — Default `User-Agent: openfang/0.3.46` on all LLM drivers — fixes 403s from Moonshot/Qwen (@ozekimasaki)
- **#417 / #392** — Default token quota changed to unlimited (was 1M/hour, caused immediate quota errors on fresh installs) (@f-liva, @cryptonahue)
- **#410** — Safe string slicing in channel bridge (9 instances) + desktop server shutdown race condition (@hobostay)
- **#413 / #275** — Embedding driver respects `provider_urls` config + auto-selects correct model per provider (@castorinop, @woodcoal)
- **#464** — Wizard generates proper multi-line TOML strings for system_prompt with escaping (@citadelgrad)

### New Models & Providers
- **#419 / #480 / #439** — Added Z.AI Coding models (glm-5-coding, glm-4.7-coding), Kimi for Code (Anthropic-compatible), fixed Moonshot base URL, added kimi-k2.5-0711 alias (@shipdocs, @skeltavik, @modship)

### Internal
- XML-attribute tool call recovery (Pattern 9) for Groq/Llama models that emit `<function name="..." parameters="..." />`
- 187 models, 40+ providers, 2040+ tests, 0 clippy warnings

**Full Changelog**: https://github.com/RightNow-AI/openfang/compare/v0.3.45...v0.3.46