codex-context-diet

Where it calls Jev

export const SYSTEM_ONE_URL = 'https://api.typesafe.ai/v1/systemone';

src/request.ts:3

The link points at the commit we read, so the line number still holds.

What it asks Jev

These question sets are lifted from this project's source exactly as written.

import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    ping: { type: 'boolean', instructions: 'This model is reachable' },
  },
});

import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    a: { type: 'boolean', instructions: 'is it up' },
  },
});

Other projects in this category

• yoshi ▶ — Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy
• jevlogs ▶ — Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.
• omp-jev-compaction ▶ — Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter
• opencode-jev-compactor ▶ — Jev powered OpenCode compaction
• pi-jev-compaction ▶ — Jev-powered context compaction for Pi. Keep critical instructions and tool history, prune the noise, and fall back gracefully.
• fast-jev-compaction — Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
• invalidate — The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.
• jev-recall — Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev