Skip to content

Open Dungeon 0.3.3: Mac setup and image worker controls

Choose a tag to compare

View all tags
@newideas99 newideas99 released this 15 Jun 12:41
v0.3.3
8159e91

Mac setup parity and easier image-worker startup.

  • Mac DMG and Launch.command now let you choose a narrator backend. First run offers either Ollama on this Mac or an OpenAI-compatible server URL for LM Studio, llama.cpp, OpenRouter, remote Ollama, etc.
  • Custom backend defaults are saved to .env.server. New chats pick up DEFAULT_TEXT_PROVIDER=custom, OPENAI_COMPAT_BASE_URL, and OPENAI_COMPAT_MODEL; API keys can stay server-side through OPENAI_COMPAT_API_KEY / OPENROUTER_API_KEY.
  • Images panel can start the local image worker. Click Start in Images instead of opening a second terminal in the exact repo folder.
  • Images panel can open the model/cache folder. Click Models to open the local MFLUX/ultra-fast-image-gen cache folder in Finder.
  • Better image-worker errors. If image generation fails because the worker is down, the app now points users to the Images panel Start button and the correct terminal command.

Install:

  • macOS Apple Silicon: open the DMG, drag Open Dungeon to Applications, and open it (right-click then Open the first time, since it is unsigned). Choose Ollama or paste a compatible server URL during setup.
  • Windows: download Open-Dungeon-0.3.3-Windows.zip, unzip it, then run Launch-Windows.bat.

Validation: Windows smoke passed on the release commit, local lint/build passed, image routing checks passed, and the DMG verified with hdiutil verify.

Full changelog: v0.3.2...v0.3.3

Assets 4
Loading