Agent tooling
An eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text.
/** Minimal client for TypeSafe's System One endpoint (POST /v1/systemone). */The link points at the commit we read, so the line number still holds.
These question sets are lifted from this project's source exactly as written.
from scripts/smoke.ts:37
severityscoreHow severe is this?
0 — trivial1 — minor2 — major3 — criticalareachoiceWhich team should own this ticket?
billing — payments and invoicingplatform — availability and errorsdocs — documentationimport { experimental_evaluate as evaluate } from 'ai';
const { answers } = await evaluate({
model: 'typesafe-ai/jev',
state,
questions: {
severity: { type: 'score', instructions: 'How severe is this?',
criteria: ['trivial', 'minor', 'major', 'critical'] },
area: { type: 'choice', instructions: 'Which team should own this ticket?',
criteria: { billing: 'payments and invoicing', platform: 'availability and errors', docs: 'documentation' } },
},
});