Files
hermes-agent/agent
ismell0992-afk 3e99964789 fix(agent): prefer Ollama Modelfile num_ctx over GGUF training max
_query_local_context_length was checking model_info.context_length
(the GGUF training max) before num_ctx (the Modelfile runtime override),
inverse to query_ollama_num_ctx. The two helpers therefore disagreed on
the same model:

  hermes-brain:qwen3-14b-ctx32k     # Modelfile: num_ctx 32768
  underlying qwen3:14b GGUF         # qwen3.context_length: 40960

query_ollama_num_ctx correctly returned 32768 (the value Ollama will
actually allocate KV cache for). _query_local_context_length returned
40960, which let ContextCompressor grow conversations past 32768 before
triggering compression — at which point Ollama silently truncated the
prefix, corrupting context.

Swap the order so num_ctx is checked first, matching query_ollama_num_ctx.
Adds a parametrized test that seeds both values and asserts num_ctx wins.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-13 04:24:07 -07:00
..