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.