mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(compression): pass configured context_length to feasibility check

Browse source 
_check_compression_model_feasibility() called get_model_context_length()
without passing config_context_length, so custom endpoints that do not
support /models API queries always fell through to the 128K default,
ignoring auxiliary.compression.context_length in config.yaml.

Fix: read auxiliary.compression.context_length from config and pass it
as config_context_length (highest-priority hint) so the user-configured
value is always respected regardless of API availability.

Fixes #8499
This commit is contained in:
ygd58 2026-04-12 18:54:16 +02:00 • committed by Teknium
parent 0d0d27d45e
commit 4a9c356559
1 changed files with 15 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

15
run_agent.py
View file

@ -1748,10 +1748,25 @@ class AIAgent:
aux_base_url = str(getattr(client, "base_url", ""))
aux_api_key = str(getattr(client, "api_key", ""))
# Read user-configured context_length for the compression model.
# Custom endpoints often don't support /models API queries so
# get_model_context_length() falls through to the 128K default,
# ignoring the explicit config value. Pass it as the highest-
# priority hint so the configured value is always respected.
_aux_cfg = (self.config or {}).get("auxiliary", {}).get("compression", {})
_aux_context_config = _aux_cfg.get("context_length") if isinstance(_aux_cfg, dict) else None
if _aux_context_config is not None:
try:
_aux_context_config = int(_aux_context_config)
except (TypeError, ValueError):
_aux_context_config = None
aux_context = get_model_context_length(
aux_model,
base_url=aux_base_url,
api_key=aux_api_key,
config_context_length=_aux_context_config,
)
threshold = self.context_compressor.threshold_tokens