No description
- Python 87.9%
- C# 8.7%
- Shell 2.8%
- Nix 0.6%
Batched question API (noul/choice/score), retrying transport, and a margin-based confidence gate. Every call appends one JSON line of questions and parsed answers to $JEV_TRACE when set; tracing never raises, so it cannot break a run. |
||
|---|---|---|
| docs | ||
| utils | ||
| vendor | ||
| capture.py | ||
| facts.py | ||
| jev.py | ||
| sts2.py | ||
| test_facts.py | ||