mirror of
https://github.com/SHOGGOTH-SECTOR/sica-fondt.git
synced 2026-07-31 08:06:26 +00:00
A real model call is network/process IO, so the LLM seam is now a behaviour with a response callback (ResponseFn), not a synchronous function. StubLLM answers immediately; OpenHermesClient + OpenHermesConfig (OpenAI-compatible url/model) are the real plug, swappable for the stub. CerebellumHarness chains its passes through the async callback. Compiles on ponyc 0.64; demo green. Next: wire the actual chat/completions call behind OpenHermesClient. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015hmgREHNsxYCuim33yUF2c
sica-fondt
AI My Fiosa
i hate restartibg
Description
Languages
R
45.1%
Ada
19.6%
MATLAB
9.9%
COBOL
8.8%
Pony
6.4%
Other
10.2%