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): remove hardcoded gemini-3-flash-preview as default summary model

Browse source 
Closes #2453

The DEFAULT_CONFIG was hardcoding google/gemini-3-flash-preview as the
summary_model for context compression. This caused unexpected OpenRouter
charges for users who configured a different provider/model, because the
compression task would silently fall back to gemini via OpenRouter even
when the user's main model was on a different provider.

Fix: change summary_model default to empty string. When empty,
call_llm() resolves the model through the standard auto-detection chain
(auxiliary.compression config -> env vars -> main provider), which
correctly uses the user's configured provider and model.

Users who want a dedicated cheap model for compression can still
explicitly set compression.summary_model in their config.yaml.
This commit is contained in:
Mibayy 2026-03-22 11:20:27 +00:00 • committed by Teknium
parent 0962cbb2e5
commit 0698ddb496
No known key found for this signature in database
2 changed files with 4 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
cli.py
View file

@ -180,7 +180,7 @@ def load_cli_config() -> Dict[str, Any]:
"compression": {
"enabled": True, # Auto-compress when approaching context limit
"threshold": 0.50, # Compress at 50% of model's context limit
"summary_model": "google/gemini-3-flash-preview", # Fast/cheap model for summaries
"summary_model": "", # Model for summaries (empty = use main model)
},
"smart_model_routing": {
"enabled": False,

5
hermes_cli/config.py
View file

@ -159,7 +159,7 @@ DEFAULT_CONFIG = {
"compression": {
"enabled": True,
"threshold": 0.50,
"summary_model": "google/gemini-3-flash-preview",
"summary_model": "", # empty = use main configured model
"summary_provider": "auto",
"summary_base_url": None,
},
@ -1659,7 +1659,8 @@ def show_config():
print(f" Enabled: {'yes' if enabled else 'no'}")
if enabled:
print(f" Threshold: {compression.get('threshold', 0.50) * 100:.0f}%")
print(f" Model: {compression.get('summary_model', 'google/gemini-3-flash-preview')}")
_sm = compression.get('summary_model', '') or '(main model)'
print(f" Model: {_sm}")
comp_provider = compression.get('summary_provider', 'auto')
if comp_provider != 'auto':
print(f" Provider: {comp_provider}")