stella config

Show the fully resolved configuration for the current session — the provider, model, a redacted key preview, base URL, workspace, and wire dialect.

Synopsis

stella config [global flags]

What it does

stella config resolves every configuration source — global flags, environment variables, settings.json across all three scopes, and credentials.toml — and prints the effective result. It is the fastest way to confirm exactly which provider, model, and base URL a run will use, and that your key resolved without exposing it (the key is shown only as a redacted preview).

The same output is available from the plain line REPL (stella chat --plain) via the /config slash command. The default Command Deck TUI does not have a /config command — run stella config in a separate shell instead.

Flags

stella config takes the global flags. Passing --model or --base-url lets you preview how a specific override resolves before committing to a run. --api-key cannot be previewed on its own — it must be combined with --model provider/model_id, because a bare key doesn't say which provider it is for.

Example

stella config

Representative output (illustrative):

Provider:   Z.ai (GLM 5.2)
Model:      zai/glm-5.2
API Key:    sk-abc…a1b2
Base URL:   https://api.z.ai/api/paas/v4
Workspace:  /Users/you/projects/acme
Dialect:    OpenAI-compatible

The Provider line shows the provider's display name; Model is printed as <provider-id>/<model-id>; and the key is a redacted preview (first six characters, an ellipsis, and the last four).

Preview how an explicit override resolves without starting a run (global flags first):

stella --model anthropic/claude-fable-5 config