mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-06-09 08:21:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

fix(ollama): set default_max_tokens for custom/Ollama provider

Browse source 
The custom/Ollama provider profile had no default_max_tokens, so no
max_tokens was sent on requests and Ollama fell back to its internal
num_predict=128 — truncating responses after a few tokens with
finish_reason='length' (#39281, e.g. gemma4).

max_tokens resolution is ephemeral > user model.max_tokens > profile
default, so this is only a floor used when the user hasn't set their own
cap. Set it to 65536 (matching the qwen-oauth tier) rather than a
conservative value, since users can always override per-model.

Fixes #39281
This commit is contained in:
islam666 2026-06-05 06:29:36 +00:00 • committed by Teknium
parent ab0a6270c3
commit 09ec26c66a
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
plugins/model-providers/custom/__init__.py
View file

@ -63,6 +63,11 @@ custom = CustomProfile(
),
env_vars=(), # No fixed key — custom endpoint
base_url="", # User-configured
# Without this, no max_tokens is sent and Ollama falls back to its internal
# num_predict=128, truncating responses after a few tokens (#39281). This is
# only a floor used when the user hasn't set model.max_tokens — they can
# override per-model — so we set it generously rather than lowballing it.
default_max_tokens=65536,
)
register_provider(custom)