CLI

CLI: Config & troubleshooting

Signing in and out, picking a default model, and diagnosing the failures that actually happen — plus the fixes.

Sign in, sign out

tempr auth              # interactive prompt (recommended — keeps the key out of shell history)
tempr auth <LICENSE_KEY>  # or pass it directly, e.g. in CI
tempr logout             # clear the stored credential on this machine

The CLI uses the same license as the IDE — Standard, Pro, or Teams all work, no separate subscription.

Default model

Every run needs a model. Set a default once, override per-run when you want:

tempr config set-model <id>   # default for every run
tempr -m <id> "prompt"        # one-run override
tempr --model <id>            # same thing, long form

Inside the REPL, /model shows or switches the active model for the session.

Troubleshooting

SymptomFix
No model configured on every runPass -m <id> or run tempr config set-model <id> — no default is set on this machine.
Auth errors on a machine that used to workRun tempr doctor to check connectivity; if the credential is stale, tempr logout then tempr auth.
Turns fail in a CI container but work locallyCheck that the license key secret is actually set — tempr doctor reports sign-in state — and pass -m explicitly so the run doesn't depend on local config.
Unexpected tool behavior or empty MCP listtempr mcp list shows what's configured; MCP tools only appear once a server is added with tempr mcp add.
Can't tell what the agent didRe-run with --verbose for token usage, or check the saved session with tempr history / tempr --id.

tempr doctor

tempr doctor checks connectivity and sign-in state and reports what looks wrong. When something misbehaves, run it first — it distinguishes "can't reach the server" from "not signed in" from "configured fine," which covers most first-line debugging.

Note

The agent loop runs server-side, so a flaky local connection does not kill an in-flight turn — but doctor is still the fastest way to confirm the machine can reach Tempr at all.