Hermes Agent service account efaff340a4 openviking: fix VLM model alias and lower max_input_tokens to 1024 ...

- vlm.model was 'llama3.1-8b' which doesn't exist on astro-orbiter's
  /v1/models, causing every summarization call to 400 and endless
  circuit-breaker retries. Correct id: Meta-Llama-3.1-8B-Instruct-Q4_K_M.
- embedding.max_input_tokens=1536 still let chunks through that actually
  tokenized to 2000-2860 real tokens (estimator undercounts vs llama.cpp's
  tokenizer by 1.35x-1.86x on this corpus). Lowered to 1024 for real margin
  under the 2048 n_ctx ceiling.

2026-08-15 00:12:40 -05:00

9.3 KiB

Raw Blame History

View Raw