v0.6.20
opencode-ai/opencodev0.6.20Sep 28, 2026by RasulOs
Upgrading?
AI Summary
This release refreshes provider model catalogs and improves UI stability by handling null children. It also adds streaming support for OpenAI OAuth responses and improves error handling by summarizing HTML pages.
Key Highlights
- Refreshed provider model catalogs.
- Streamed OpenAI OAuth responses through Codex.
- Fixed UI null children handling.
- Summarized provider HTML error pages in logs and results.
New Features
- Refreshed provider model catalogs.
- Streamed OpenAI OAuth responses through Codex.
Full Release Notes
## What's Changed * Rename favicon.svg to favicon.svg by @asifajrof in https://github.com/droidrun/mobilerun/pull/448 * fix(ui): treat null children by @lutz-grex in https://github.com/droidrun/mobilerun/pull/451 * feat: refresh provider model catalogs by @RasulOs in https://github.com/droidrun/mobilerun/pull/457 * fix: stream OpenAI OAuth responses through Codex by @RasulOs in https://github.com/droidrun/mobilerun/pull/458 * fix: summarize provider HTML error pages in logs and results by @RasulOs in https://github.com/droidrun/mobilerun/pull/460 * fix: merge Gemini OAuth generationConfig overrides by @RasulOs in https://github.com/droidrun/mobilerun/pull/461 * chore: release mobilerun 0.6.20 by @RasulOs in https://github.com/droidrun/mobilerun/pull/463 * chore: merge develop into main by @RasulOs in https://github.com/droidrun/mobilerun/pull/462 ## New Contributors * @asifajrof made their first contribution in https://github.com/droidrun/mobilerun/pull/448 **Full Changelog**: https://github.com/droidrun/mobilerun/compare/v0.6.19...v0.6.20
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.