Open reproductions

diffusiongemma-jev-macos

@Saik0s★ 2PythonMITupdated 2026-09-19▶ runnable

Local JEV-style decisions with DiffusionGemma on Apple Silicon, with benchmarks and coding-agent examples.

Saik0s/diffusiongemma-jev-macos ↗

Where it calls Jev

@app.post("/v1/systemone")

src/diffusion_jev/api.py:168

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.

from src/diffusion_jev/benchmark_cases.py:56

  1. enabledtrue/false

    Is enabled true in the supplied state?

  2. colorchoice

    Select the exact color in the supplied state.

    • red — Color is red.
    • green — Color is green.
    • blue — Color is blue.
  3. progressscore

    Rate completed_steps using the exact numeric rubric.

    • 0 — Zero steps completed.
    • 1 — One step completed.
    • 2 — Two steps completed.

Run it on your own text

The code
import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    enabled: { type: 'boolean', instructions: 'Is enabled true in the supplied state?' },
    color: { type: 'choice', instructions: 'Select the exact color in the supplied state.',
      criteria: { red: 'Color is red.', green: 'Color is green.', blue: 'Color is blue.' } },
    progress: { type: 'score', instructions: 'Rate completed_steps using the exact numeric rubric.',
      criteria: ['Zero steps completed.', 'One step completed.', 'Two steps completed.'] },
  },
});

from src/diffusion_jev/examples.py:64

  1. causechoice

    Choose the direct cause supported by the failure.

    • dependency — A declared Python dependency is missing.
    • assertion — An assertion compares two different values.
    • network — A remote HTTP request timed out.
  2. missing_dependencytrue/false

    Does the failure indicate an unavailable Python dependency?

  3. network_timeouttrue/false

    Does the failure indicate a remote network request timed out?

Run it on your own text

The code
import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    cause: { type: 'choice', instructions: 'Choose the direct cause supported by the failure.',
      criteria: { dependency: 'A declared Python dependency is missing.', assertion: 'An assertion compares two different values.', network: 'A remote HTTP request timed out.' } },
    missing_dependency: { type: 'boolean', instructions: 'Does the failure indicate an unavailable Python dependency?' },
    network_timeout: { type: 'boolean', instructions: 'Does the failure indicate a remote network request timed out?' },
  },
});

from src/diffusion_jev/examples.py:102

  1. filechoice

    Select the file most directly responsible for the bug.

    • validators — src/email_validation.py
    • styles — assets/colors.css
    • readme — README.md

Run it on your own text

The code
import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    file: { type: 'choice', instructions: 'Select the file most directly responsible for the bug.',
      criteria: { validators: 'src/email_validation.py', styles: 'assets/colors.css', readme: 'README.md' } },
  },
});

from src/diffusion_jev/examples.py:129

  1. security_regressiontrue/false

    Does this patch remove the authentication check?

  2. review_priorityscore

    Rate the patch's review priority using its observed effect.

    • 0 — Cosmetic change without behavioral impact.
    • 1 — Nonblocking issue without exposing protected resources.
    • 2 — Critical security issue exposing protected resources.

Run it on your own text

The code
import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    security_regression: { type: 'boolean', instructions: 'Does this patch remove the authentication check?' },
    review_priority: { type: 'score', instructions: 'Rate the patch\'s review priority using its observed effect.',
      criteria: ['Cosmetic change without behavioral impact.', 'Nonblocking issue without exposing protected resources.', 'Critical security issue exposing protected resources.'] },
  },
});

Other projects in this category