12Release archive
STOLZ A.I. v0.12.0
Live evaluation on the installed Codex CLI and model validated predictable skill routing: refined context/reuse triggers, fail-closed scoring, complete public artifacts, and packaged-reference checks.
§ 1v0.12.0
What changed
- 01
Context selection now targets existing manifests and read records. Result reuse requires a previous result or an identical command already in progress.
- 02
The held-out evaluation recorded 23/24 strict routes and 24/24 required outcomes and permission decisions on the tested Codex CLI/model combination. This does not certify other models.
§ 2v0.12.0
Source and package
Read the original release notes and use the package published for this exact version. The installation guide describes the current release.
Package SHA-256
b5c04072774c0b78c99893b82e4312643c0390b2be704babcb31a27a2ebd1f9a