jevbooks

← All projects

corbits-system-one

corbitsdev/corbits-system-one

Typed choice, score, and yes/no decisions from Jev models.

Automated README summary

Automatically summarized from the README on 27 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A TypeScript client that sends a JSON state and typed questions to TypeSafe's Jev model, returning validated decisions with probabilities. It works standalone via evaluate() or as an @intx/inference adapter for Corbits and Interchange agents.

How it uses Jev

Jev evaluates structured state against questions (choice, score, boolean/noul, box) in one POST. Each question id gets a validated decision with probabilities and confidence. Failures return a FallbackResult with a reason instead of throwing, so gates can fail closed.

Primitives:choicescorenoul

Technique worth stealing

Treat inference failures as typed data (FallbackResult with reason) rather than exceptions, enabling fail-closed gates without try/catch.

Try it

bun add @corbits/system-one @intx/inference@^0.4.0 @intx/types@^0.4.0, set TYPESAFE_API_KEY, then call evaluate().

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.94
  • Shows a System One patternFound in material0.81
  • Describes handling uncertaintyFound in material0.86
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.92
  • Top-10 learning shortlist signalnot found in the excerpt0.37
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale1.19 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.94Shows a System One pattern0.81Describes handling uncertainty0.86Reports measured numbers0.02Is a runnable tool0.92Top-10 learning shortlist signal0.37Is a replica of the model0.0400.51Solves a common problem (0–2)1.19 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.99Fail open, fail closed0.75Inspection0.3100.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 27 Oct 2026.