Skip to main content

​
What config.json Stores

Located at brain/config.json, this file stores application-level settings. It’s read on startup and can be modified via the Settings UI or by editing the file directly.

​
Configuration Fields

​
Field Reference

​
Model Selection

Wolffish runs on an explicitly selected model — there is no automatic fallback. You choose your Brain model (provider + model) from the model switch beside the chat input, and that’s the model that runs. The model you pick is the one that answers; if it fails, the turn fails rather than silently routing to another provider. Optionally, switch the chat into workflow mode (llm.mode: "workflow", toggled from the composer’s mode pill) — each turn can then plan phases and spawn parallel agents, with the master picking every agent’s model from your connected providers. See Workflow Mode for how that works. Even then there’s no cascade — every model that runs was explicitly chosen, by you or by the master. All providers are optional — you only need the ones you actually select. To use Ollama, select it as your Brain model; there’s no automatic fall-through to local.
API keys are stored in plain text in config.json. This is by design — Wolffish is a local-first app and your workspace is your own. If you version-control your workspace with git, add brain/config.json to .gitignore.