Evidence and limits
Evidence Note: README exposes multi-turn agent evaluation, scenario checks, test generation, traces, red teaming, and LLM-as-judge boundaries.
Last reviewed: 2026-08-27
What was reviewed: README reviewed only; no runtime test recorded
Source and review details
Snapshot Date: 2026-08-27
Snapshot Commit: cd343d7f5461d9738e554fb6bd7cd8a6f3662557