MModelTrust
All updates

Release article / project log

v0.3.0Shipped

Verification Core

ModelTrust now produces a secret-free Level 1 evidence report from three bounded endpoint requests, without inventing a trust or identity score.

What changed

  • Implemented repeated operational-integrity sampling with availability, latency, schema, identifier, finish-reason, and usage evidence.
  • Rebuilt reports around observed evidence, experimental boundaries, not-verified items, and benchmark metadata.
  • Hardened endpoint validation, blocked redirects, and added best-effort submission and concurrency limits.
  • Defined a reference-harness contract without shipping fabricated reference distributions.

Verification evidence

  • Endpoint and verification-engine unit tests
  • TypeScript, ESLint, Next.js and OpenNext builds
  • English, Chinese, desktop, mobile, and production routes

Next target

Build and validate the controlled reference-endpoint harness before enabling any Level 2 behavioral comparison.

Release boundary

This article records shipped work and explicit limitations. Experimental results are not promoted by a patch release.