What it is
Don't interrupt mid-thought in chat bots.
What it does: Scores message completeness with System One/Jev and delays AstrBot replies until the burst looks finished.
Why it belongs in the showcase: Practical chat UX gate on decision models inside AstrBot.
Caveats: Provider wiring and restart semantics.
Evidence
Public MIT repo, created 2026-11-03, 0 stars as of 2026-11-04. README documents AstrBot 4.29.4+, Decision/System One provider config, completeness curve waits (30→5s), message/char caps, and preview/stats UI.
Caveats
- Uses AstrBot Decision/System One providers — confirm hosted Jev is selected
- Delay heuristics and caps are operator-tuned
- Waiting buffers are not retained across restarts
Unofficial case page. Stars / list position observed for heat; do not treat heat as a quality SLA. Review the upstream README before you depend on it.