Teknium 292d12bed4 fix: case-insensitive model family matching + compressor init logging ...

Two fixes for local model context detection:

1. Hardcoded DEFAULT_CONTEXT_LENGTHS matching was case-sensitive.
   'qwen' didn't match 'Qwen3.5-9B-Q4_K_M.gguf' because of the
   capital Q. Now uses model.lower() for comparison.

2. Added compressor initialization logging showing the detected
   context_length, threshold, model, provider, and base_url.
   This makes turn-1 compression bugs diagnosable from logs —
   previously there was no log of what context length was detected.

2026-03-21 10:47:44 -07:00

28 KiB

Raw Blame History

View Raw