Mercury CLI
Documentation

Providers

Jev

JevEval gives the session model a second opinion from TypeSafe's Jev. The model supplies relevant evidence and asks yes/no, choice or score questions. Jev returns numerical answers for the model to consider while deciding what to do next.

Set up Jev

  1. Open /jev.
  2. Enter your own TypeSafe API key.
  3. Set the spending and request limits you want.
  4. Turn the switch on.

Jev is off by default. /jev, the JEV row in /config and the JEV row in Boot Settings read and write the same switch. The tool joins or leaves the model's tool list at the next turn boundary.

The key is held in Mercury's credential store. TYPESAFE_API_KEY, when set, takes precedence over the stored key. Mercury shows whether a key is present and where it comes from, without displaying its value.

Limits and spend

  • Session allowance: Defaults to $20 and resets with /clear. This is a limit on Mercury's own count, not a provider balance.
  • Pace: Defaults to 10 requests per minute.
  • Request ceiling: An optional limit on requests per session; off by default.
  • Sub-agents: Access is off by default and can be enabled separately. Their calls share the session allowance.

Spend appears in /jev and as a separate row in /usage. If the screen has no usable session figure, it reports that the figure is unavailable rather than displaying zero.

Questions and results

The tool can help compare explanations after evidence has been collected, make a judgment after measurements have been taken, or check a proposal against recorded decisions. Several questions can share one request. Each call makes one network attempt.

The evidence is sent to TypeSafe. The tool's instructions require focused excerpts and exclude secrets, full transcripts and whole files. Numerical answers are opinions for the session model to assess; permission prompts and the checks used to verify code keep their usual roles.

Read the status

/jev distinguishes a disabled switch, a missing or invalid key, local spending or request limits, and provider refusals or outages. The tool reports the reason when a request is unavailable. A temporary limit identifies when another attempt is allowed; a lasting refusal stops further Jev calls for that session while ordinary work continues.

Providers and sign-in, Models and effort, Agents and teams, Slash commands