Agent tooling
A lightweight Jev-powered router for models, tools, and subagents
this.endpoint = options.endpoint ?? "https://api.typesafe.ai/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 tests/primitives.test.ts:61
severityscoreHow severe is this?
0 — trivial1 — minor2 — major3 — criticalneeds_tooltrue/falseDoes handling this require a tool?
import { 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'] },
needs_tool: { type: 'boolean', instructions: 'Does handling this require a tool?' },
},
});from tests/primitives.test.ts:91
severityscoreHow careful should we be?
0 — casual1 — carefulneeds_tooltrue/falseIs a read needed?
import { experimental_evaluate as evaluate } from 'ai';
const { answers } = await evaluate({
model: 'typesafe-ai/jev',
state,
questions: {
severity: { type: 'score', instructions: 'How careful should we be?',
criteria: ['casual', 'careful'] },
needs_tool: { type: 'boolean', instructions: 'Is a read needed?' },
},
});from tests/primitives.test.ts:111
teamchoiceWhich team should handle this?
payments — billing and checkout issuesfrontend — browser rendering issuesimport { experimental_evaluate as evaluate } from 'ai';
const { answers } = await evaluate({
model: 'typesafe-ai/jev',
state,
questions: {
team: { type: 'choice', instructions: 'Which team should handle this?',
criteria: { payments: 'billing and checkout issues', frontend: 'browser rendering issues' } },
},
});