mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
1ddae67b5d
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.5 KiB
1.5 KiB
v3.7.9 Release Notes
Release Date: 2026-03-05
Highlights
Multi-language test generation with 8 new generators, embedding standardization to 384-dim, and trust tier eval infrastructure for 5 skills.
Added
- Multi-language test generation — 8 new generators for Go, Rust, Kotlin, Java, Swift, Flutter, React Native, and C#. Each produces idiomatic tests with language-specific patterns (Go table-driven tests, Rust ownership analysis, Swift Testing macros, etc.)
- Compilation validation loop — Validates generated tests compile before output, with framework-specific fix strategies
- Automatic language detection — Routes source files to the correct test generator based on file extension and content analysis
- Trust tier eval infrastructure — Full eval configs for qcsd-cicd-swarm, qcsd-development-swarm, enterprise-integration-testing, observability-testing-patterns, and middleware-testing-patterns
Fixed
- Embedding dimension standardization — Unified all vector dimensions to 384 (all-MiniLM-L6-v2), fixing mixed 384/768 dimensions across providers, tests, and config defaults
- Agent memory namespace paths — Normalized namespace references in agent definitions
- Asset sync coverage —
prepare-assets.shnow includes all 78 QE skills (previously missed 24)
Changed
- Default embedding model — Switched from
nomic-embed-texttoall-MiniLM-L6-v2 - Trust tier adjustments — debug-loop and pr-review set to tier 0 (advisory-only)